Correcting peak VALU Roofline profiling and analysis by removing FP8 VALU and BF16 VALU benchmarking. (#1442)

* Removing FP8 from peak VALU datatypes - PEAK_OPS_DATATYPES.

* Similar change for BF16.

* Roofline binaries from rocm-amdgpu-bench generated 10/22.
https://github.com/ROCm/rocm-amdgpu-bench/commit/2113ef1f5eada8a4a6e44e6d07fd6abac9b0a3f8
Bins include change that removes FP8 and BF16 peak VALU benchmarks.
Built and tested on rhel8, azl3, ubuntu22.04, sles15sp6.

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

* Re-committing the bins

accidentally copied over bins from the wrong folder earlier, caught by Gowthami during testing.

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

* Updated changelog

* gersemi fix

* Changelog corrected.

* Changelog fix.

* Adding this to the 7.2.0 section to be picked up in an RC build.

* Moving changelog entry into unreleasesd section - team reconfirmed cutoff date after I requested this change so I am just quickly correcting my mistake in my ask.

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

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: JeniferC99 <150404595+JeniferC99@users.noreply.github.com>

projects/rocprofiler-compute/CHANGELOG.md

@@ -34,6 +34,8 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.
 
 * Fix the functioning of --dispatch option to act as 1-based index and ensure that correct kernel iterations are being profiled
 
+* Corrected peak VALU Roofline profiling and analysis by removing `FP8` VALU and `BF16` VALU benchmarking.
+
 ## ROCm Compute Profiler 3.4.0 for ROCm 7.2.0
 
 ### Added
@@ -96,7 +98,6 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.
 * Improved Roofline Benchmarking by updating the `flops_benchmark` calculation.
 
 ### Resolved issues
-
 * Bugfixes for stability
 
 ## ROCm Compute Profiler 3.3.0 for ROCm 7.1.0
@@ -254,7 +255,7 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.
   * A workaround has been implemented using max(0, calculated_value) to prevent negative display values while the root cause is under investigation.
 
 * The profile mode crashes when `--format-rocprof-output json` is selected.
-  * As a workaround, this option should either not be provided or should be set to `csv` instead of `json`. This issue does not affect the profiling results since both `csv` and `json` output formats lead to the same profiling data.  
+  * As a workaround, this option should either not be provided or should be set to `csv` instead of `json`. This issue does not affect the profiling results since both `csv` and `json` output formats lead to the same profiling data.
 
 ### Upcoming changes
 

projects/rocprofiler-compute/src/utils/roofline_calc.py

@@ -101,7 +101,7 @@ SUPPORTED_DATATYPES: dict[str, list[str]] = {
     ],  # Unsupported:
 }
 
-PEAK_OPS_DATATYPES = ["FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"]
+PEAK_OPS_DATATYPES = ["FP16", "FP32", "FP64", "I8", "I32", "I64"]
 MFMA_DATATYPES = ["FP4", "FP6", "FP8", "FP16", "BF16", "FP32", "FP64", "I8"]
 CACHE_HIERARCHY = ["HBM", "L2", "L1", "LDS"]