Enable roofline for MI350 series (#677)
Rework of roofline binaries generated from rocm-amdgpu-bench - removed arch identifier in bin name - removed rocm5 bins altogether Updated required distros for roofline - updated distro checks and bin naming - moved up ubuntu20.04->22.04 and sles15.3->15.6 per rocm support Enabled ctests for mi350 for test_roof_* - removed mi350 series check to skip these specific tests --------- Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
pmc: SQ_INSTS_VALU_ADD_F16 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 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32
|
||||
|
||||
pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TCP_TCC_READ_REQ_sum TCC_EA0_RDREQ_32B_sum TCC_EA0_RDREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WRREQ_sum TCC_BUBBLE_sum
|
||||
|
||||
pmc: SQ_LDS_IDX_ACTIVE SQ_LDS_BANK_CONFLICT TCP_TOTAL_CACHE_ACCESSES_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum
|
||||
|
||||
#ROOF:MI300 series and above
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_F8
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernels:
|
||||
@@ -46,17 +46,6 @@ class gfx950_soc(OmniSoC_Base):
|
||||
)
|
||||
)
|
||||
)
|
||||
else:
|
||||
# NB: We're using generalized Mi300 perfmon configs
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
"gfx950",
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
|
||||
Reference in New Issue
Block a user