Enable baseline comparison between workloads from the same path (#447)

* Enable baseline comparison between workloads from the same path

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

* Formatting

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

* Change test to verify baseline works with same path

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

* Add three-way comparison test case

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

---------

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>

[ROCm/rocprofiler-compute commit: 13a06f5131]
This commit is contained in:
zichguan-amd
2024-10-24 13:00:36 -04:00
committed by GitHub
parent e188429f06
commit 3328cf8d6c
31 changed files with 492 additions and 41 deletions
@@ -151,7 +151,7 @@ class OmniAnalyze_Base:
self.load_options(normalization_filter)
for d in self.__args.path:
for i, d in enumerate(self.__args.path):
w = schema.Workload()
w.sys_info = file_io.load_sys_info(Path(d[0], "sysinfo.csv"))
arch = w.sys_info.iloc[0]["gpu_arch"]
@@ -161,7 +161,7 @@ class OmniAnalyze_Base:
w.avail_ips = w.sys_info["ip_blocks"].item().split("|")
w.dfs = copy.deepcopy(self._arch_configs[arch].dfs)
w.dfs_type = self._arch_configs[arch].dfs_type
self._runs[d[0]] = w
self._runs[i] = w
return self._runs
@@ -184,15 +184,6 @@ class OmniAnalyze_Base:
# validate profiling data
is_workload_empty(dir[0])
# no using same paths
occurances = set()
for dir in self.__args.path:
dir = dir[0]
if dir in occurances:
console_error("You cannot provide the same path twice.")
else:
occurances.add(dir)
# ----------------------------------------------------
# Required methods to be implemented by child classes
# ----------------------------------------------------
@@ -211,20 +202,20 @@ class OmniAnalyze_Base:
# set filters
if self.__args.gpu_kernel:
for d, gk in zip(self.__args.path, self.__args.gpu_kernel):
self._runs[d[0]].filter_kernel_ids = gk
for i, gk in enumerate(self.__args.gpu_kernel):
self._runs[i].filter_kernel_ids = gk
if self.__args.gpu_id:
if len(self.__args.gpu_id) == 1 and len(self.__args.path) != 1:
for i in range(len(self.__args.path) - 1):
self.__args.gpu_id.extend(self.__args.gpu_id)
for d, gi in zip(self.__args.path, self.__args.gpu_id):
self._runs[d[0]].filter_gpu_ids = gi
for i, gi in enumerate(self.__args.gpu_id):
self._runs[i].filter_gpu_ids = gi
if self.__args.gpu_dispatch_id:
if len(self.__args.gpu_dispatch_id) == 1 and len(self.__args.path) != 1:
for i in range(len(self.__args.path) - 1):
self.__args.gpu_dispatch_id.extend(self.__args.gpu_dispatch_id)
for d, gd in zip(self.__args.path, self.__args.gpu_dispatch_id):
self._runs[d[0]].filter_dispatch_ids = gd
for i, gd in enumerate(self.__args.gpu_dispatch_id):
self._runs[i].filter_dispatch_ids = gd
@abstractmethod
def run_analysis(self):
@@ -38,27 +38,25 @@ class cli_analysis(OmniAnalyze_Base):
super().pre_processing()
if self.get_args().random_port:
console_error("--gui flag is required to enable --random-port")
for d in self.get_args().path:
for i, d in enumerate(self.get_args().path):
file_io.create_df_kernel_top_stats(
raw_data_dir=d[0],
filter_gpu_ids=self._runs[d[0]].filter_gpu_ids,
filter_dispatch_ids=self._runs[d[0]].filter_dispatch_ids,
filter_gpu_ids=self._runs[i].filter_gpu_ids,
filter_dispatch_ids=self._runs[i].filter_dispatch_ids,
time_unit=self.get_args().time_unit,
max_stat_num=self.get_args().max_stat_num,
kernel_verbose=self.get_args().kernel_verbose,
)
# create 'mega dataframe'
self._runs[d[0]].raw_pmc = file_io.create_df_pmc(
self._runs[i].raw_pmc = file_io.create_df_pmc(
d[0], self.get_args().kernel_verbose, self.get_args().verbose
)
# demangle and overwrite original 'Kernel_Name'
kernel_name_shortener(
self._runs[d[0]].raw_pmc, self.get_args().kernel_verbose
)
kernel_name_shortener(self._runs[i].raw_pmc, self.get_args().kernel_verbose)
# create the loaded table
parser.load_table_data(
workload=self._runs[d[0]],
workload=self._runs[i],
dir=d[0],
is_gui=False,
debug=self.get_args().debug,
@@ -73,17 +71,13 @@ class cli_analysis(OmniAnalyze_Base):
tty.show_kernel_stats(
self.get_args(),
self._runs,
self._arch_configs[
self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"]
],
self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]],
self._output,
)
else:
tty.show_all(
self.get_args(),
self._runs,
self._arch_configs[
self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"]
],
self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]],
self._output,
)
@@ -274,20 +274,20 @@ class webui_analysis(OmniAnalyze_Base):
args = self.get_args()
file_io.create_df_kernel_top_stats(
raw_data_dir=self.dest_dir,
filter_gpu_ids=self._runs[self.dest_dir].filter_gpu_ids,
filter_dispatch_ids=self._runs[self.dest_dir].filter_dispatch_ids,
filter_gpu_ids=self._runs[0].filter_gpu_ids,
filter_dispatch_ids=self._runs[0].filter_dispatch_ids,
time_unit=args.time_unit,
max_stat_num=args.max_stat_num,
kernel_verbose=self.get_args().kernel_verbose,
)
# create 'mega dataframe'
self._runs[self.dest_dir].raw_pmc = file_io.create_df_pmc(
self._runs[0].raw_pmc = file_io.create_df_pmc(
self.dest_dir, self.get_args().kernel_verbose, args.verbose
)
# create the loaded kernel stats
parser.load_kernel_top(self._runs[self.dest_dir], self.dest_dir)
parser.load_kernel_top(self._runs[0], self.dest_dir)
# set architecture
self.arch = self._runs[self.dest_dir].sys_info.iloc[0]["gpu_arch"]
self.arch = self._runs[0].sys_info.iloc[0]["gpu_arch"]
else:
console_error(
@@ -300,9 +300,9 @@ class webui_analysis(OmniAnalyze_Base):
super().run_analysis()
args = self.get_args()
input_filters = {
"kernel": self._runs[self.dest_dir].filter_kernel_ids,
"gpu": self._runs[self.dest_dir].filter_gpu_ids,
"dispatch": self._runs[self.dest_dir].filter_dispatch_ids,
"kernel": self._runs[0].filter_kernel_ids,
"gpu": self._runs[0].filter_gpu_ids,
"dispatch": self._runs[0].filter_dispatch_ids,
"normalization": args.normal_unit,
"top_n": args.max_stat_num,
}
@@ -1136,7 +1136,7 @@ def test_baseline():
],
):
omniperf.main()
assert e.value.code == 1
assert e.value.code == 0
with pytest.raises(SystemExit) as e:
with patch(
@@ -1151,7 +1151,53 @@ def test_baseline():
],
):
omniperf.main()
assert e.value.code == 1
assert e.value.code == 0
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
[
"omniperf",
"analyze",
"--path",
"tests/workloads/multikernel/MI200",
"-k",
"0",
"--path",
"tests/workloads/multikernel/MI200",
"-k",
"1",
"--path",
"tests/workloads/multikernel/MI200",
"-k",
"2",
],
):
omniperf.main()
assert e.value.code == 0
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
[
"omniperf",
"analyze",
"--path",
"tests/workloads/multikernel/MI200",
"-k",
"0",
"--path",
"tests/workloads/multikernel/MI200",
"-k",
"1",
"--path",
"tests/workloads/vcopy/MI100",
"-k",
"0",
],
):
omniperf.main()
assert e.value.code == 0
@pytest.mark.misc
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCC_CYCLE[0],TCC_RW_REQ[0],TCC_HIT[0],TCC_MISS[0],TCC_CYCLE[1],TCC_RW_REQ[1],TCC_HIT[1],TCC_MISS[1],TCC_CYCLE[2],TCC_RW_REQ[2],TCC_HIT[2],TCC_MISS[2],TCC_CYCLE[3],TCC_RW_REQ[3],TCC_HIT[3],TCC_MISS[3],TCC_CYCLE[4],TCC_RW_REQ[4],TCC_HIT[4],TCC_MISS[4],TCC_CYCLE[5],TCC_RW_REQ[5],TCC_HIT[5],TCC_MISS[5],TCC_CYCLE[6],TCC_RW_REQ[6],TCC_HIT[6],TCC_MISS[6],TCC_CYCLE[7],TCC_RW_REQ[7],TCC_HIT[7],TCC_MISS[7],TCC_CYCLE[8],TCC_RW_REQ[8],TCC_HIT[8],TCC_MISS[8],TCC_CYCLE[9],TCC_RW_REQ[9],TCC_HIT[9],TCC_MISS[9],TCC_CYCLE[10],TCC_RW_REQ[10],TCC_HIT[10],TCC_MISS[10],TCC_CYCLE[11],TCC_RW_REQ[11],TCC_HIT[11],TCC_MISS[11],TCC_CYCLE[12],TCC_RW_REQ[12],TCC_HIT[12],TCC_MISS[12],TCC_CYCLE[13],TCC_RW_REQ[13],TCC_HIT[13],TCC_MISS[13],TCC_CYCLE[14],TCC_RW_REQ[14],TCC_HIT[14],TCC_MISS[14],TCC_CYCLE[15],TCC_RW_REQ[15],TCC_HIT[15],TCC_MISS[15],TCC_CYCLE[16],TCC_RW_REQ[16],TCC_HIT[16],TCC_MISS[16],TCC_CYCLE[17],TCC_RW_REQ[17],TCC_HIT[17],TCC_MISS[17],TCC_CYCLE[18],TCC_RW_REQ[18],TCC_HIT[18],TCC_MISS[18],TCC_CYCLE[19],TCC_RW_REQ[19],TCC_HIT[19],TCC_MISS[19],TCC_CYCLE[20],TCC_RW_REQ[20],TCC_HIT[20],TCC_MISS[20],TCC_CYCLE[21],TCC_RW_REQ[21],TCC_HIT[21],TCC_MISS[21],TCC_CYCLE[22],TCC_RW_REQ[22],TCC_HIT[22],TCC_MISS[22],TCC_CYCLE[23],TCC_RW_REQ[23],TCC_HIT[23],TCC_MISS[23],TCC_CYCLE[24],TCC_RW_REQ[24],TCC_HIT[24],TCC_MISS[24],TCC_CYCLE[25],TCC_RW_REQ[25],TCC_HIT[25],TCC_MISS[25],TCC_CYCLE[26],TCC_RW_REQ[26],TCC_HIT[26],TCC_MISS[26],TCC_CYCLE[27],TCC_RW_REQ[27],TCC_HIT[27],TCC_MISS[27],TCC_CYCLE[28],TCC_RW_REQ[28],TCC_HIT[28],TCC_MISS[28],TCC_CYCLE[29],TCC_RW_REQ[29],TCC_HIT[29],TCC_MISS[29],TCC_CYCLE[30],TCC_RW_REQ[30],TCC_HIT[30],TCC_MISS[30],TCC_CYCLE[31],TCC_RW_REQ[31],TCC_HIT[31],TCC_MISS[31],CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789017,789017,256,256,0,0,12,4,32,64,0x0,0x7fc39b83d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,15492,15492,9586176074970,9595697581667,9595697588067,9586194080958
1,"global_write(int*, int) [clone .kd]",2,0,1,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,14214,14214,9586194431757,9595697981345,9595697983585,9586195534149
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16792,16792,9586194965600,9595697989025,9595697991265,9586196424752
3,"global_read(int*, int) [clone .kd]",2,0,3,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17066,17066,9586195545500,9595698033025,9595698035745,9586197503640
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b8052c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16835,16835,9586196089011,9595698039905,9595698042305,9586198594409
5,"global_atomic(int*, int) [clone .kd]",2,0,5,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16490,16490,9586196678469,9595698072385,9595698076225,9586199643230
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17235,17235,9586197190792,9595698076225,9595698080065,9586200731796
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31] CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL SPI_CSN_WINDOW_VALID SPI_CSN_BUSY GRBM_COUNT GRBM_GUI_ACTIVE DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 789017 789017 256 256 0 0 12 4 32 64 0x0 0x7fc39b83d800 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 15492 15492 9586176074970 9595697581667 9595697588067 9586194080958
3 1 global_write(int*, int) [clone .kd] 2 0 1 789017 789017 1 1 0 0 4 4 16 64 0x0 0x7fc39b805200 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 14214 14214 9586194431757 9595697981345 9595697983585 9586195534149
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 789017 789017 1 1 4096 0 4 4 48 64 0x0 0x7fc39b805240 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 16792 16792 9586194965600 9595697989025 9595697991265 9586196424752
5 3 global_read(int*, int) [clone .kd] 2 0 3 789017 789017 1 1 0 0 4 4 16 64 0x0 0x7fc39b805280 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 17066 17066 9586195545500 9595698033025 9595698035745 9586197503640
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 789017 789017 1 1 0 0 4 4 16 64 0x0 0x7fc39b8052c0 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 16835 16835 9586196089011 9595698039905 9595698042305 9586198594409
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 789017 789017 1 1 0 0 4 4 16 64 0x0 0x7fc39b805300 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 16490 16490 9586196678469 9595698072385 9595698076225 9586199643230
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 789017 789017 1 1 4096 0 4 4 48 64 0x0 0x7fc39b805340 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 17235 17235 9586197190792 9595698076225 9595698080065 9586200731796
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TCC_REQ[0],TCC_READ[0],TCC_WRITE[0],TCC_ATOMIC[0],TCC_REQ[1],TCC_READ[1],TCC_WRITE[1],TCC_ATOMIC[1],TCC_REQ[2],TCC_READ[2],TCC_WRITE[2],TCC_ATOMIC[2],TCC_REQ[3],TCC_READ[3],TCC_WRITE[3],TCC_ATOMIC[3],TCC_REQ[4],TCC_READ[4],TCC_WRITE[4],TCC_ATOMIC[4],TCC_REQ[5],TCC_READ[5],TCC_WRITE[5],TCC_ATOMIC[5],TCC_REQ[6],TCC_READ[6],TCC_WRITE[6],TCC_ATOMIC[6],TCC_REQ[7],TCC_READ[7],TCC_WRITE[7],TCC_ATOMIC[7],TCC_REQ[8],TCC_READ[8],TCC_WRITE[8],TCC_ATOMIC[8],TCC_REQ[9],TCC_READ[9],TCC_WRITE[9],TCC_ATOMIC[9],TCC_REQ[10],TCC_READ[10],TCC_WRITE[10],TCC_ATOMIC[10],TCC_REQ[11],TCC_READ[11],TCC_WRITE[11],TCC_ATOMIC[11],TCC_REQ[12],TCC_READ[12],TCC_WRITE[12],TCC_ATOMIC[12],TCC_REQ[13],TCC_READ[13],TCC_WRITE[13],TCC_ATOMIC[13],TCC_REQ[14],TCC_READ[14],TCC_WRITE[14],TCC_ATOMIC[14],TCC_REQ[15],TCC_READ[15],TCC_WRITE[15],TCC_ATOMIC[15],TCC_REQ[16],TCC_READ[16],TCC_WRITE[16],TCC_ATOMIC[16],TCC_REQ[17],TCC_READ[17],TCC_WRITE[17],TCC_ATOMIC[17],TCC_REQ[18],TCC_READ[18],TCC_WRITE[18],TCC_ATOMIC[18],TCC_REQ[19],TCC_READ[19],TCC_WRITE[19],TCC_ATOMIC[19],TCC_REQ[20],TCC_READ[20],TCC_WRITE[20],TCC_ATOMIC[20],TCC_REQ[21],TCC_READ[21],TCC_WRITE[21],TCC_ATOMIC[21],TCC_REQ[22],TCC_READ[22],TCC_WRITE[22],TCC_ATOMIC[22],TCC_REQ[23],TCC_READ[23],TCC_WRITE[23],TCC_ATOMIC[23],TCC_REQ[24],TCC_READ[24],TCC_WRITE[24],TCC_ATOMIC[24],TCC_REQ[25],TCC_READ[25],TCC_WRITE[25],TCC_ATOMIC[25],TCC_REQ[26],TCC_READ[26],TCC_WRITE[26],TCC_ATOMIC[26],TCC_REQ[27],TCC_READ[27],TCC_WRITE[27],TCC_ATOMIC[27],TCC_REQ[28],TCC_READ[28],TCC_WRITE[28],TCC_ATOMIC[28],TCC_REQ[29],TCC_READ[29],TCC_WRITE[29],TCC_ATOMIC[29],TCC_REQ[30],TCC_READ[30],TCC_WRITE[30],TCC_ATOMIC[30],TCC_REQ[31],TCC_READ[31],TCC_WRITE[31],TCC_ATOMIC[31],CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,GRBM_SPI_BUSY,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789206,789206,256,256,0,0,12,4,32,64,0x0,0x7f092c135800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7832,9586813518158,9595697581667,9595697588067,9586831878942
1,"global_write(int*, int) [clone .kd]",2,0,1,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,4807,9586832277231,9595697981345,9595697983585,9586833234169
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6147,9586832819029,9595697989025,9595697991265,9586834206386
3,"global_read(int*, int) [clone .kd]",2,0,3,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6439,9586833482506,9595698033025,9595698035745,9586835298047
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f92c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6821,9586834006330,9595698039905,9595698042305,9586836377766
5,"global_atomic(int*, int) [clone .kd]",2,0,5,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6708,9586834769875,9595698072385,9595698076225,9586837446956
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7838,9586835336510,9595698076225,9595698080065,9586838514602
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31] CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE GRBM_SPI_BUSY DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 789206 789206 256 256 0 0 12 4 32 64 0x0 0x7f092c135800 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 7832 9586813518158 9595697581667 9595697588067 9586831878942
3 1 global_write(int*, int) [clone .kd] 2 0 1 789206 789206 1 1 0 0 4 4 16 64 0x0 0x7f092c0f9200 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 4807 9586832277231 9595697981345 9595697983585 9586833234169
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 789206 789206 1 1 4096 0 4 4 48 64 0x0 0x7f092c0f9240 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 6147 9586832819029 9595697989025 9595697991265 9586834206386
5 3 global_read(int*, int) [clone .kd] 2 0 3 789206 789206 1 1 0 0 4 4 16 64 0x0 0x7f092c0f9280 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 6439 9586833482506 9595698033025 9595698035745 9586835298047
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 789206 789206 1 1 0 0 4 4 16 64 0x0 0x7f092c0f92c0 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 6821 9586834006330 9595698039905 9595698042305 9586836377766
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 789206 789206 1 1 0 0 4 4 16 64 0x0 0x7f092c0f9300 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 6708 9586834769875 9595698072385 9595698076225 9586837446956
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 789206 789206 1 1 4096 0 4 4 48 64 0x0 0x7f092c0f9340 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 7838 9586835336510 9595698076225 9595698080065 9586838514602
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789393,789393,256,256,0,0,12,4,32,64,0x0,0x7f96ea49d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587521927328,9595697581667,9595697588067,9587540188696
1,"global_write(int*, int) [clone .kd]",2,0,1,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587540565083,9595697981345,9595697983585,9587541639562
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541115507,9595697989025,9595697991265,9587542609585
3,"global_read(int*, int) [clone .kd]",2,0,3,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541696489,9595698033025,9595698035745,9587543620214
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea4652c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542237877,9595698039905,9595698042305,9587544716895
5,"global_atomic(int*, int) [clone .kd]",2,0,5,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542873531,9595698072385,9595698076225,9587545756779
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587543404819,9595698076225,9595698080065,9587546843111
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 789393 789393 256 256 0 0 12 4 32 64 0x0 0x7f96ea49d800 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587521927328 9595697581667 9595697588067 9587540188696
3 1 global_write(int*, int) [clone .kd] 2 0 1 789393 789393 1 1 0 0 4 4 16 64 0x0 0x7f96ea465200 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587540565083 9595697981345 9595697983585 9587541639562
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 789393 789393 1 1 4096 0 4 4 48 64 0x0 0x7f96ea465240 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587541115507 9595697989025 9595697991265 9587542609585
5 3 global_read(int*, int) [clone .kd] 2 0 3 789393 789393 1 1 0 0 4 4 16 64 0x0 0x7f96ea465280 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587541696489 9595698033025 9595698035745 9587543620214
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 789393 789393 1 1 0 0 4 4 16 64 0x0 0x7f96ea4652c0 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587542237877 9595698039905 9595698042305 9587544716895
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 789393 789393 1 1 0 0 4 4 16 64 0x0 0x7f96ea465300 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587542873531 9595698072385 9595698076225 9587545756779
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 789393 789393 1 1 4096 0 4 4 48 64 0x0 0x7f96ea465340 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 16384.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 25626 16384 0 9587543404819 9595698076225 9595698080065 9587546843111
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCC_EA_ATOMIC[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_ATOMIC_LEVEL[0],TCC_EA_ATOMIC[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_ATOMIC_LEVEL[1],TCC_EA_ATOMIC[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_ATOMIC_LEVEL[2],TCC_EA_ATOMIC[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_ATOMIC_LEVEL[3],TCC_EA_ATOMIC[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_ATOMIC_LEVEL[4],TCC_EA_ATOMIC[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_ATOMIC_LEVEL[5],TCC_EA_ATOMIC[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_ATOMIC_LEVEL[6],TCC_EA_ATOMIC[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_ATOMIC_LEVEL[7],TCC_EA_ATOMIC[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_ATOMIC_LEVEL[8],TCC_EA_ATOMIC[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_ATOMIC_LEVEL[9],TCC_EA_ATOMIC[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_ATOMIC_LEVEL[10],TCC_EA_ATOMIC[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_ATOMIC_LEVEL[11],TCC_EA_ATOMIC[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_ATOMIC_LEVEL[12],TCC_EA_ATOMIC[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_ATOMIC_LEVEL[13],TCC_EA_ATOMIC[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_ATOMIC_LEVEL[14],TCC_EA_ATOMIC[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_ATOMIC_LEVEL[15],TCC_EA_ATOMIC[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_ATOMIC_LEVEL[16],TCC_EA_ATOMIC[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_ATOMIC_LEVEL[17],TCC_EA_ATOMIC[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_ATOMIC_LEVEL[18],TCC_EA_ATOMIC[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_ATOMIC_LEVEL[19],TCC_EA_ATOMIC[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_ATOMIC_LEVEL[20],TCC_EA_ATOMIC[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_ATOMIC_LEVEL[21],TCC_EA_ATOMIC[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_ATOMIC_LEVEL[22],TCC_EA_ATOMIC[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_ATOMIC_LEVEL[23],TCC_EA_ATOMIC[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_ATOMIC_LEVEL[24],TCC_EA_ATOMIC[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_ATOMIC_LEVEL[25],TCC_EA_ATOMIC[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_ATOMIC_LEVEL[26],TCC_EA_ATOMIC[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_ATOMIC_LEVEL[27],TCC_EA_ATOMIC[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_ATOMIC_LEVEL[28],TCC_EA_ATOMIC[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_ATOMIC_LEVEL[29],TCC_EA_ATOMIC[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_ATOMIC_LEVEL[30],TCC_EA_ATOMIC[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ_LEVEL[31],TCC_EA_ATOMIC_LEVEL[31],CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789581,789581,256,256,0,0,12,4,32,64,0x0,0x7fa983c4d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588165999404,9595697581667,9595697588067,9588184873222
1,"global_write(int*, int) [clone .kd]",2,0,1,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185231295,9595697981345,9595697983585,9588186170961
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185747445,9595697989025,9595697991265,9588187051836
3,"global_read(int*, int) [clone .kd]",2,0,3,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186416192,9595698033025,9595698035745,9588187966405
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c152c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186956707,9595698039905,9595698042305,9588188690015
5,"global_atomic(int*, int) [clone .kd]",2,0,5,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588187589306,9595698072385,9595698076225,9588189838613
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588188228397,9595698076225,9595698080065,9588190792135
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31] CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 789581 789581 256 256 0 0 12 4 32 64 0x0 0x7fa983c4d800 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588165999404 9595697581667 9595697588067 9588184873222
3 1 global_write(int*, int) [clone .kd] 2 0 1 789581 789581 1 1 0 0 4 4 16 64 0x0 0x7fa983c15200 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588185231295 9595697981345 9595697983585 9588186170961
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 789581 789581 1 1 4096 0 4 4 48 64 0x0 0x7fa983c15240 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588185747445 9595697989025 9595697991265 9588187051836
5 3 global_read(int*, int) [clone .kd] 2 0 3 789581 789581 1 1 0 0 4 4 16 64 0x0 0x7fa983c15280 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588186416192 9595698033025 9595698035745 9588187966405
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 789581 789581 1 1 0 0 4 4 16 64 0x0 0x7fa983c152c0 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588186956707 9595698039905 9595698042305 9588188690015
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 789581 789581 1 1 0 0 4 4 16 64 0x0 0x7fa983c15300 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588187589306 9595698072385 9595698076225 9588189838613
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 789581 789581 1 1 4096 0 4 4 48 64 0x0 0x7fa983c15340 0 0 0 0 0 0 0 0 16384.0 0.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 0 16384 0 9588188228397 9595698076225 9595698080065 9588190792135
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_CPC_UTCL2IU_STALL,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789767,789767,256,256,0,0,12,4,32,64,0x0,0x7f0b7a335800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,15256,15256,9588800635588,9595697581667,9595697588067,9588818795995
1,"global_write(int*, int) [clone .kd]",2,0,1,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,14215,14215,9588819151083,9595697981345,9595697983585,9588820066433
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16303,16303,9588819631105,9595697989025,9595697991265,9588820711946
3,"global_read(int*, int) [clone .kd]",2,0,3,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17633,17633,9588820290945,9595698033025,9595698035745,9588821548468
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a3192c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16725,16725,9588820914807,9595698039905,9595698042305,9588822390240
5,"global_atomic(int*, int) [clone .kd]",2,0,5,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17452,17452,9588821374712,9595698072385,9595698076225,9588823186356
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17418,17418,9588822047877,9595698076225,9595698080065,9588824015775
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] CPC_ME1_BUSY_FOR_PACKET_DECODE CPC_CPC_UTCL2IU_STALL SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN GRBM_COUNT GRBM_GUI_ACTIVE DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 789767 789767 256 256 0 0 12 4 32 64 0x0 0x7f0b7a335800 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 15256 15256 9588800635588 9595697581667 9595697588067 9588818795995
3 1 global_write(int*, int) [clone .kd] 2 0 1 789767 789767 1 1 0 0 4 4 16 64 0x0 0x7f0b7a319200 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 14215 14215 9588819151083 9595697981345 9595697983585 9588820066433
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 789767 789767 1 1 4096 0 4 4 48 64 0x0 0x7f0b7a319240 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 16303 16303 9588819631105 9595697989025 9595697991265 9588820711946
5 3 global_read(int*, int) [clone .kd] 2 0 3 789767 789767 1 1 0 0 4 4 16 64 0x0 0x7f0b7a319280 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 17633 17633 9588820290945 9595698033025 9595698035745 9588821548468
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 789767 789767 1 1 0 0 4 4 16 64 0x0 0x7f0b7a3192c0 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 16725 16725 9588820914807 9595698039905 9595698042305 9588822390240
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 789767 789767 1 1 0 0 4 4 16 64 0x0 0x7f0b7a319300 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 17452 17452 9588821374712 9595698072385 9595698076225 9588823186356
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 789767 789767 1 1 4096 0 4 4 48 64 0x0 0x7f0b7a319340 0 0 0 0 0 0 0 0 16384.0 0.0 131072.0 131072.0 0.0 971473.0 1102230 965274 0 0 0 0 0 0 1213216 992963 0 0 0 0 0 0 1175854 1033860 0 0 1520989 1091404 0 0 1468827 1047492 0 0 0 0 0 0 1239120 1082184 0 0 1072038 981313 0 0 1024755 978955 0 0 1114067 1067349 0 0 1125538 973712 0 0 1092006 1136315 0 0 1488950 1046986 0 0 1420108 1188281 0 0 1087014 957831 0 0 1079591 979515 0 0 1200842 1084335 0 0 0 0 0 0 1085995 1022303 0 0 1295858 1104205 0 0 1049908 1014016 0 0 1533784 1320993 0 0 1166083 1076118 0 0 1122956 992991 0 0 998575 952668 0 0 1169185 1082850 0 0 1178114 999491 0 0 1062056 1000641 0 0 1153969 999775 0 0 1310176 1179285 0 0 14941 11278 16384 0 17418 17418 9588822047877 9595698076225 9595698080065 9588824015775
@@ -0,0 +1,270 @@
Omniperf version: 2.1.0
Profiler choice: rocprofv1
Path: /home/zichguan/omniperf_test/omniperf/tests/workloads/multikernel/MI210
Target: MI200
Command: ./sample/vmem
Kernel Selection: None
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt
|-> [rocprof] RPL: on '241022_154555' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154555_788857'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154555_788857/input0_results_241022_154555'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154555_788857/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 152 metrics
|-> [rocprof] SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TCC_CYCLE[0], TCC_RW_REQ[0], TCC_HIT[0], TCC_MISS[0], TCC_CYCLE[1], TCC_RW_REQ[1], TCC_HIT[1], TCC_MISS[1], TCC_CYCLE[2], TCC_RW_REQ[2], TCC_HIT[2], TCC_MISS[2], TCC_CYCLE[3], TCC_RW_REQ[3], TCC_HIT[3], TCC_MISS[3], TCC_CYCLE[4], TCC_RW_REQ[4], TCC_HIT[4], TCC_MISS[4], TCC_CYCLE[5], TCC_RW_REQ[5], TCC_HIT[5], TCC_MISS[5], TCC_CYCLE[6], TCC_RW_REQ[6], TCC_HIT[6], TCC_MISS[6], TCC_CYCLE[7], TCC_RW_REQ[7], TCC_HIT[7], TCC_MISS[7], TCC_CYCLE[8], TCC_RW_REQ[8], TCC_HIT[8], TCC_MISS[8], TCC_CYCLE[9], TCC_RW_REQ[9], TCC_HIT[9], TCC_MISS[9], TCC_CYCLE[10], TCC_RW_REQ[10], TCC_HIT[10], TCC_MISS[10], TCC_CYCLE[11], TCC_RW_REQ[11], TCC_HIT[11], TCC_MISS[11], TCC_CYCLE[12], TCC_RW_REQ[12], TCC_HIT[12], TCC_MISS[12], TCC_CYCLE[13], TCC_RW_REQ[13], TCC_HIT[13], TCC_MISS[13], TCC_CYCLE[14], TCC_RW_REQ[14], TCC_HIT[14], TCC_MISS[14], TCC_CYCLE[15], TCC_RW_REQ[15], TCC_HIT[15], TCC_MISS[15], TCC_CYCLE[16], TCC_RW_REQ[16], TCC_HIT[16], TCC_MISS[16], TCC_CYCLE[17], TCC_RW_REQ[17], TCC_HIT[17], TCC_MISS[17], TCC_CYCLE[18], TCC_RW_REQ[18], TCC_HIT[18], TCC_MISS[18], TCC_CYCLE[19], TCC_RW_REQ[19], TCC_HIT[19], TCC_MISS[19], TCC_CYCLE[20], TCC_RW_REQ[20], TCC_HIT[20], TCC_MISS[20], TCC_CYCLE[21], TCC_RW_REQ[21], TCC_HIT[21], TCC_MISS[21], TCC_CYCLE[22], TCC_RW_REQ[22], TCC_HIT[22], TCC_MISS[22], TCC_CYCLE[23], TCC_RW_REQ[23], TCC_HIT[23], TCC_MISS[23], TCC_CYCLE[24], TCC_RW_REQ[24], TCC_HIT[24], TCC_MISS[24], TCC_CYCLE[25], TCC_RW_REQ[25], TCC_HIT[25], TCC_MISS[25], TCC_CYCLE[26], TCC_RW_REQ[26], TCC_HIT[26], TCC_MISS[26], TCC_CYCLE[27], TCC_RW_REQ[27], TCC_HIT[27], TCC_MISS[27], TCC_CYCLE[28], TCC_RW_REQ[28], TCC_HIT[28], TCC_MISS[28], TCC_CYCLE[29], TCC_RW_REQ[29], TCC_HIT[29], TCC_MISS[29], TCC_CYCLE[30], TCC_RW_REQ[30], TCC_HIT[30], TCC_MISS[30], TCC_CYCLE[31], TCC_RW_REQ[31], TCC_HIT[31], TCC_MISS[31], CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, GRBM_COUNT, GRBM_GUI_ACTIVE
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154555_788857/input0_results_241022_154555
|-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_IFETCH_LEVEL.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789045'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789045/input0_results_241022_154556'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789045/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 151 metrics
|-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TCC_REQ[0], TCC_READ[0], TCC_WRITE[0], TCC_ATOMIC[0], TCC_REQ[1], TCC_READ[1], TCC_WRITE[1], TCC_ATOMIC[1], TCC_REQ[2], TCC_READ[2], TCC_WRITE[2], TCC_ATOMIC[2], TCC_REQ[3], TCC_READ[3], TCC_WRITE[3], TCC_ATOMIC[3], TCC_REQ[4], TCC_READ[4], TCC_WRITE[4], TCC_ATOMIC[4], TCC_REQ[5], TCC_READ[5], TCC_WRITE[5], TCC_ATOMIC[5], TCC_REQ[6], TCC_READ[6], TCC_WRITE[6], TCC_ATOMIC[6], TCC_REQ[7], TCC_READ[7], TCC_WRITE[7], TCC_ATOMIC[7], TCC_REQ[8], TCC_READ[8], TCC_WRITE[8], TCC_ATOMIC[8], TCC_REQ[9], TCC_READ[9], TCC_WRITE[9], TCC_ATOMIC[9], TCC_REQ[10], TCC_READ[10], TCC_WRITE[10], TCC_ATOMIC[10], TCC_REQ[11], TCC_READ[11], TCC_WRITE[11], TCC_ATOMIC[11], TCC_REQ[12], TCC_READ[12], TCC_WRITE[12], TCC_ATOMIC[12], TCC_REQ[13], TCC_READ[13], TCC_WRITE[13], TCC_ATOMIC[13], TCC_REQ[14], TCC_READ[14], TCC_WRITE[14], TCC_ATOMIC[14], TCC_REQ[15], TCC_READ[15], TCC_WRITE[15], TCC_ATOMIC[15], TCC_REQ[16], TCC_READ[16], TCC_WRITE[16], TCC_ATOMIC[16], TCC_REQ[17], TCC_READ[17], TCC_WRITE[17], TCC_ATOMIC[17], TCC_REQ[18], TCC_READ[18], TCC_WRITE[18], TCC_ATOMIC[18], TCC_REQ[19], TCC_READ[19], TCC_WRITE[19], TCC_ATOMIC[19], TCC_REQ[20], TCC_READ[20], TCC_WRITE[20], TCC_ATOMIC[20], TCC_REQ[21], TCC_READ[21], TCC_WRITE[21], TCC_ATOMIC[21], TCC_REQ[22], TCC_READ[22], TCC_WRITE[22], TCC_ATOMIC[22], TCC_REQ[23], TCC_READ[23], TCC_WRITE[23], TCC_ATOMIC[23], TCC_REQ[24], TCC_READ[24], TCC_WRITE[24], TCC_ATOMIC[24], TCC_REQ[25], TCC_READ[25], TCC_WRITE[25], TCC_ATOMIC[25], TCC_REQ[26], TCC_READ[26], TCC_WRITE[26], TCC_ATOMIC[26], TCC_REQ[27], TCC_READ[27], TCC_WRITE[27], TCC_ATOMIC[27], TCC_REQ[28], TCC_READ[28], TCC_WRITE[28], TCC_ATOMIC[28], TCC_REQ[29], TCC_READ[29], TCC_WRITE[29], TCC_ATOMIC[29], TCC_REQ[30], TCC_READ[30], TCC_WRITE[30], TCC_ATOMIC[30], TCC_REQ[31], TCC_READ[31], TCC_WRITE[31], TCC_ATOMIC[31], CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, GRBM_SPI_BUSY
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789045/input0_results_241022_154556
|-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_LDS.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789233'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789233/input0_results_241022_154556'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789233/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 150 metrics
|-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31], CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789233/input0_results_241022_154556
|-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_SMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [rocprof] RPL: on '241022_154557' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154557_789421'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154557_789421/input0_results_241022_154557'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154557_789421/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 148 metrics
|-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCC_EA_ATOMIC[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_ATOMIC_LEVEL[0], TCC_EA_ATOMIC[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_ATOMIC_LEVEL[1], TCC_EA_ATOMIC[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_ATOMIC_LEVEL[2], TCC_EA_ATOMIC[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_ATOMIC_LEVEL[3], TCC_EA_ATOMIC[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_ATOMIC_LEVEL[4], TCC_EA_ATOMIC[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_ATOMIC_LEVEL[5], TCC_EA_ATOMIC[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_ATOMIC_LEVEL[6], TCC_EA_ATOMIC[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_ATOMIC_LEVEL[7], TCC_EA_ATOMIC[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_ATOMIC_LEVEL[8], TCC_EA_ATOMIC[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_ATOMIC_LEVEL[9], TCC_EA_ATOMIC[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_ATOMIC_LEVEL[10], TCC_EA_ATOMIC[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_ATOMIC_LEVEL[11], TCC_EA_ATOMIC[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_ATOMIC_LEVEL[12], TCC_EA_ATOMIC[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_ATOMIC_LEVEL[13], TCC_EA_ATOMIC[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_ATOMIC_LEVEL[14], TCC_EA_ATOMIC[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_ATOMIC_LEVEL[15], TCC_EA_ATOMIC[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_ATOMIC_LEVEL[16], TCC_EA_ATOMIC[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_ATOMIC_LEVEL[17], TCC_EA_ATOMIC[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_ATOMIC_LEVEL[18], TCC_EA_ATOMIC[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_ATOMIC_LEVEL[19], TCC_EA_ATOMIC[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_ATOMIC_LEVEL[20], TCC_EA_ATOMIC[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_ATOMIC_LEVEL[21], TCC_EA_ATOMIC[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_ATOMIC_LEVEL[22], TCC_EA_ATOMIC[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_ATOMIC_LEVEL[23], TCC_EA_ATOMIC[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_ATOMIC_LEVEL[24], TCC_EA_ATOMIC[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_ATOMIC_LEVEL[25], TCC_EA_ATOMIC[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_ATOMIC_LEVEL[26], TCC_EA_ATOMIC[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_ATOMIC_LEVEL[27], TCC_EA_ATOMIC[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_ATOMIC_LEVEL[28], TCC_EA_ATOMIC[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_ATOMIC_LEVEL[29], TCC_EA_ATOMIC[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_ATOMIC_LEVEL[30], TCC_EA_ATOMIC[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ_LEVEL[31], TCC_EA_ATOMIC_LEVEL[31], CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154557_789421/input0_results_241022_154557
|-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_VMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt
|-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789607'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789607/input0_results_241022_154558'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789607/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 148 metrics
|-> [rocprof] SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], CPC_ME1_BUSY_FOR_PACKET_DECODE, CPC_CPC_UTCL2IU_STALL, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, GRBM_COUNT, GRBM_GUI_ACTIVE
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789607/input0_results_241022_154558
|-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_LEVEL_WAVES.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt
|-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789792'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789792/input0_results_241022_154558'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789792/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 114 metrics
|-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_FLAT, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_CYCLE_sum, CPC_ME1_DC0_SPI_BUSY, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789792/input0_results_241022_154558
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_0.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt
|-> [rocprof] RPL: on '241022_154559' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154559_789978'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154559_789978/input0_results_241022_154559'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154559_789978/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum, TCC_NC_REQ_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154559_789978/input0_results_241022_154559
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_1.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt
|-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790176'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790176/input0_results_241022_154600'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790176/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum, TCC_REQ_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790176/input0_results_241022_154600
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_2.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt
|-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790361'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790361/input0_results_241022_154600'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790361/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 18 metrics
|-> [rocprof] SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum, TCC_READ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790361/input0_results_241022_154600
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_3.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt
|-> [rocprof] RPL: on '241022_154601' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154601_790548'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154601_790548/input0_results_241022_154601'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154601_790548/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 16 metrics
|-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum, TCC_EA_WRREQ_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154601_790548/input0_results_241022_154601
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_4.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt
|-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790732'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790732/input0_results_241022_154602'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790732/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 12 metrics
|-> [rocprof] SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum, TCC_EA_WRREQ_STALL_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790732/input0_results_241022_154602
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_5.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt
|-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790917'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790917/input0_results_241022_154602'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790917/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 12 metrics
|-> [rocprof] SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790917/input0_results_241022_154602
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_6.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt
|-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791101'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791101/input0_results_241022_154603'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791101/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 12 metrics
|-> [rocprof] SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791101/input0_results_241022_154603
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_7.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt
|-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791285'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791285/input0_results_241022_154603'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791285/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 10 metrics
|-> [rocprof] SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791285/input0_results_241022_154603
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_8.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt
|-> [rocprof] RPL: on '241022_154604' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154604_791469'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154604_791469/input0_results_241022_154604'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154604_791469/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 2 metrics
|-> [rocprof] TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154604_791469/input0_results_241022_154604
|-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_9.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/timestamps.txt
|-> [rocprof] RPL: on '241022_154605' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf'
|-> [rocprof] RPL: profiling '""./sample/vmem""'
|-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/timestamps.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154605_791667'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154605_791667/input0_results_241022_154605'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154605_791667/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [rocprof] range =
|-> [rocprof] 0 metrics
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154605_791667/input0_results_241022_154605
|-> [rocprof] File 'tests/workloads/multikernel/MI210/timestamps.csv' is generating
|-> [rocprof]
[roofline] Checking for roofline.csv in tests/workloads/multikernel/MI210
[roofline] No roofline data found. Generating...
@@ -0,0 +1,5 @@
pmc: SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31] CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL SPI_CSN_WINDOW_VALID SPI_CSN_BUSY GRBM_COUNT GRBM_GUI_ACTIVE
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31] CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE GRBM_SPI_BUSY
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31] CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] CPC_ME1_BUSY_FOR_PACKET_DECODE CPC_CPC_UTCL2IU_STALL SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN GRBM_COUNT GRBM_GUI_ACTIVE
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_FLAT SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_CYCLE_sum CPC_ME1_DC0_SPI_BUSY SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum TCC_NC_REQ_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum TCC_REQ_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum TCC_READ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum TCC_EA_WRREQ_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_WRREQ_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBufferAligned.kd,2
1,"global_write(int*, int) [clone .kd]",2
2,"generic_write(int*, int, int) [clone .kd]",2
3,"global_read(int*, int) [clone .kd]",2
4,"generic_read(int*, int, int) [clone .kd]",2
5,"global_atomic(int*, int) [clone .kd]",2
6,"generic_atomic(int*, int, int) [clone .kd]",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBufferAligned.kd 2
3 1 global_write(int*, int) [clone .kd] 2
4 2 generic_write(int*, int, int) [clone .kd] 2
5 3 global_read(int*, int) [clone .kd] 2
6 4 generic_read(int*, int, int) [clone .kd] 2
7 5 global_atomic(int*, int) [clone .kd] 2
8 6 generic_atomic(int*, int, int) [clone .kd] 2
File diff suppressed because one or more lines are too long
@@ -0,0 +1,4 @@
device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
0,1392.4641,1391.8217,1393.1066,5012.8921,4999.646,5026.1382,9233.5303,9232.7051,9234.3555,21014.016,21012.709,21015.322,20999.16,20998.666,20999.654,20187.006,19967.416,20406.596,170734.45,170729.66,170739.25,165067.44,165061.97,165072.91,41480.547,41479.074,41482.02,41303.828,40844.742,41762.914,166839.7,166833.48,166845.92
1,1391.9521,1391.3705,1392.5338,5005.9937,4997.5942,5014.3931,9197.5605,9196.7617,9198.3594,20984.785,20983.42,20986.15,20944.287,20943.701,20944.873,20222.557,20221.738,20223.375,170379.27,170372.45,170386.08,164480.19,164473.75,164486.62,41338.699,41336.965,41340.434,41397.539,41395.738,41399.34,166265.69,166259,166272.38
2,1383.8199,1367.1714,1400.4685,5018.9521,5012.7114,5025.1929,9215.9326,9215.2646,9216.6006,21009.275,21007.996,21010.555,20973.949,20973.555,20974.344,20256.393,20255.896,20256.889,170535.72,170531.75,170539.69,164753.2,164748.77,164757.64,41403.738,41402.945,41404.531,41465.727,41464.988,41466.465,166533.73,166531.06,166536.41
1 device HBMBw HBMBwLow hbmBwHigh L2Bw L2BwLow L2BwHigh L1Bw L1BwLow L1BwHigh LDSBw LDSBwLow LDSBwHigh FP32Flops FP32FlopsLow FP32FlopsHigh FP64Flops FP64FlopsLow FP64FlopsHigh MFMABF16Flops MFMABF16FlopsLow MFMABF16FlopsHigh MFMAF16Flops MFMAF16FlopsLow MFMAF16FlopsHigh MFMAF32Flops MFMAF32FlopsLow MFMAF32FlopsHigh MFMAF64Flops MFMAF64FlopsLow MFMAF64FlopsHigh MFMAI8Ops MFMAFI8OpsLow MFMAI8OpsHigh
2 0 1392.4641 1391.8217 1393.1066 5012.8921 4999.646 5026.1382 9233.5303 9232.7051 9234.3555 21014.016 21012.709 21015.322 20999.16 20998.666 20999.654 20187.006 19967.416 20406.596 170734.45 170729.66 170739.25 165067.44 165061.97 165072.91 41480.547 41479.074 41482.02 41303.828 40844.742 41762.914 166839.7 166833.48 166845.92
3 1 1391.9521 1391.3705 1392.5338 5005.9937 4997.5942 5014.3931 9197.5605 9196.7617 9198.3594 20984.785 20983.42 20986.15 20944.287 20943.701 20944.873 20222.557 20221.738 20223.375 170379.27 170372.45 170386.08 164480.19 164473.75 164486.62 41338.699 41336.965 41340.434 41397.539 41395.738 41399.34 166265.69 166259 166272.38
4 2 1383.8199 1367.1714 1400.4685 5018.9521 5012.7114 5025.1929 9215.9326 9215.2646 9216.6006 21009.275 21007.996 21010.555 20973.949 20973.555 20974.344 20256.393 20255.896 20256.889 170535.72 170531.75 170539.69 164753.2 164748.77 164757.64 41403.738 41402.945 41404.531 41465.727 41464.988 41466.465 166533.73 166531.06 166536.41
@@ -0,0 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,chip_id,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
multikernel,./sample/vmem,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Tue 22 Oct 2024 03:45:54 PM (CDT),2,dell-rack-10,AMD EPYC 7313 16-Core Processor,Dell Inc.2.2.5,Ubuntu 20.04.6 LTS,5.15.0-122-generic,,527949684,,6.2.1-99,113-D67301-064D,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,29711,32,1700,1600,1700,1600,32,32,56,4,1638.4,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size chip_id max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 multikernel ./sample/vmem SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Tue 22 Oct 2024 03:45:54 PM (CDT) 2 dell-rack-10 AMD EPYC 7313 16-Core Processor Dell Inc.2.2.5 Ubuntu 20.04.6 LTS 5.15.0-122-generic 527949684 6.2.1-99 113-D67301-064D NA NA MI200 gfx90a 16 8192 104 4 8 64 1024 29711 32 1700 1600 1700 1600 32 32 56 4 1638.4 1
@@ -0,0 +1,8 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,__amd_rocclr_fillBufferAligned.kd,2,0,0,791827,791827,256,256,0,0,12,4,32,64,0x0,0x7fd72f815800,9595697470571,9595697581667,9595697588067,9595697604693
1,"global_write(int*, int) [clone .kd]",2,0,1,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9200,9595697964779,9595697981345,9595697983585,9595697985168
2,"generic_write(int*, int, int) [clone .kd]",2,0,2,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9240,9595697979166,9595697989025,9595697991265,9595698006628
3,"global_read(int*, int) [clone .kd]",2,0,3,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9280,9595697986791,9595698033025,9595698035745,9595698036745
4,"generic_read(int*, int, int) [clone .kd]",2,0,4,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d92c0,9595698029551,9595698039905,9595698042305,9595698049348
5,"global_atomic(int*, int) [clone .kd]",2,0,5,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9300,9595698036745,9595698072385,9595698076225,9595698076890
6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9340,9595698067583,9595698076225,9595698080065,9595698086618
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 2 0 0 791827 791827 256 256 0 0 12 4 32 64 0x0 0x7fd72f815800 9595697470571 9595697581667 9595697588067 9595697604693
3 1 global_write(int*, int) [clone .kd] 2 0 1 791827 791827 1 1 0 0 4 4 16 64 0x0 0x7fd72e4d9200 9595697964779 9595697981345 9595697983585 9595697985168
4 2 generic_write(int*, int, int) [clone .kd] 2 0 2 791827 791827 1 1 4096 0 4 4 48 64 0x0 0x7fd72e4d9240 9595697979166 9595697989025 9595697991265 9595698006628
5 3 global_read(int*, int) [clone .kd] 2 0 3 791827 791827 1 1 0 0 4 4 16 64 0x0 0x7fd72e4d9280 9595697986791 9595698033025 9595698035745 9595698036745
6 4 generic_read(int*, int, int) [clone .kd] 2 0 4 791827 791827 1 1 0 0 4 4 16 64 0x0 0x7fd72e4d92c0 9595698029551 9595698039905 9595698042305 9595698049348
7 5 global_atomic(int*, int) [clone .kd] 2 0 5 791827 791827 1 1 0 0 4 4 16 64 0x0 0x7fd72e4d9300 9595698036745 9595698072385 9595698076225 9595698076890
8 6 generic_atomic(int*, int, int) [clone .kd] 2 0 6 791827 791827 1 1 4096 0 4 4 48 64 0x0 0x7fd72e4d9340 9595698067583 9595698076225 9595698080065 9595698086618