AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support stochastic pc sampling

Browse Source
This commit is contained in:
Fei Zheng
2025-06-06 12:43:52 -06:00
committed by GitHub
parent ca0cdaf948
commit d756aeb3fd
14 changed files with 249 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/argparser.py
+25 -6
View File
@@ -30,7 +30,7 @@ from pathlib import Path
def print_avail_arch(avail_arch: list):
ret_str = "\t\t\tList all available metrics for analysis on specified arch:"
ret_str = "\t\tList all available metrics for analysis on specified arch:"
for arch in avail_arch:
ret_str += "\n\t\t\t {}".format(arch)
return ret_str
@@ -324,13 +324,22 @@ Examples:
help="\t\t\tSet the format of output file of rocprof.",
)
profile_group.add_argument(
"--pc-sampling-method",
required=False,
metavar="",
dest="pc_sampling_method",
default="stochastic",
help="\t\t\tSet the method of pc sampling, stochastic or host_trap. Support stochastic only >= MI300",
)
profile_group.add_argument(
"--pc-sampling-interval",
required=False,
metavar="",
dest="pc_sampling_interval",
default=1,
help="\t\t\tSet the interval of pc sampling in microsecond (DEFAULT: 1).",
default=1048576,
help="\t\t\tSet the interval of pc sampling.\n\t\t\t For stochastic sampling, the interval is in cycles.\n\t\t\t For host_trap sampling, the interval is in microsecond (DEFAULT: 1048576).",
)
profile_group.add_argument(
@@ -395,7 +404,7 @@ Examples:
nargs="+",
type=str,
default=["FP32"],
help="Choose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t FP4\n\t\t\t FP6\n\t\t\t FP8\n\t\t\t FP16\n\t\t\t BF16\n\t\t\t FP32\n\t\t\t FP64\n\t\t\t I8\n\t\t\t I32\n\t\t\t I64\n\t\t\t ",
help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t FP4\n\t\t\t FP6\n\t\t\t FP8\n\t\t\t FP16\n\t\t\t BF16\n\t\t\t FP32\n\t\t\t FP64\n\t\t\t I8\n\t\t\t I32\n\t\t\t I64\n\t\t\t ",
)
# roofline_group.add_argument('-w', '--workgroups', required=False, default=-1, type=int, help="\t\t\tNumber of kernel workgroups (DEFAULT: 1024)")
@@ -584,7 +593,7 @@ Examples:
required=False,
default=False,
action="store_true",
help="\t\t\tMode of spatial multiplexing.",
help="\t\tMode of spatial multiplexing.",
)
analyze_group.add_argument(
"-o",
@@ -614,7 +623,17 @@ Examples:
nargs="+",
type=str,
default=["FP32"],
help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t FP4\n\t\t\t FP6\n\t\t\t FP8\n\t\t\t FP16\n\t\t\t BF16\n\t\t\t FP32\n\t\t\t FP64\n\t\t\t I8\n\t\t\t I32\n\t\t\t I64\n\t\t\t ",
help="\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t FP4\n\t\t\t FP6\n\t\t\t FP8\n\t\t\t FP16\n\t\t\t BF16\n\t\t\t FP32\n\t\t\t FP64\n\t\t\t I8\n\t\t\t I32\n\t\t\t I64\n\t\t\t ",
)
analyze_group.add_argument(
"--pc-sampling-sorting-type",
required=False,
metavar="",
dest="pc_sampling_sorting_type",
default="offset",
type=str,
help="\t\tSet the sorting type of pc sampling: offset or count (DEFAULT: offset).",
)
analyze_advanced_group.add_argument(