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

Add F4 F6 to roofline for MI350 series (#709)

Browse Source 
Add roofline bins with FP4 FP6 datatypes enabled for gfx950 arch

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
This commit is contained in:
cfallows-amd
2025-05-26 18:36:31 -04:00
committed by GitHub
parent 09b6ef4508
commit cb2d928ecf
7 changed files with 144 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/argparser.py
+4 -4
View File
@@ -390,12 +390,12 @@ Examples:
"-R",
"--roofline-data-type",
required=False,
choices=["FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"],
choices=["FP4", "FP6", "FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"],
metavar="",
nargs="+",
type=str,
default=["FP32"],
help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\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="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 ",
)
# roofline_group.add_argument('-w', '--workgroups', required=False, default=-1, type=int, help="\t\t\tNumber of kernel workgroups (DEFAULT: 1024)")
@@ -605,12 +605,12 @@ Examples:
"-R",
"--roofline-data-type",
required=False,
choices=["FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"],
choices=["FP4", "FP6", "FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"],
metavar="",
nargs="+",
type=str,
default=["FP32"],
help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\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 ",
)
analyze_advanced_group.add_argument(