2
0

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

Add roofline bins with FP4 FP6 datatypes enabled for gfx950 arch

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: cb2d928ecf]
Este cometimento está contido em:
cfallows-amd
2025-05-26 18:36:31 -04:00
cometido por GitHub
ascendente ba61cc36f5
cometimento 689746e2cd
7 ficheiros modificados com 144 adições e 66 eliminações
+1 -1
Ver ficheiro
@@ -20,7 +20,7 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.
* Default is FP32, but user can specify as many types as desired to overlay on the same plot output
* Additional datatypes for roofline profiling
* Now supports FP8, FP16, BF16, FP32, FP64, I8, I32, I64 (dependent on gpu architecture)
* Now supports FP4, FP6, FP8, FP16, BF16, FP32, FP64, I8, I32, I64 (dependent on gpu architecture)
* Support host-trap PC Sampling on CLI (beta version)