Benchmarks: Micro benchmarks - Update hipblaslt metric unit to tflops (#604)

**Description**
Benchmarks: Micro benchmarks - Update hipblaslt metric unit to tflops

.github/workflows/build-image.yml

@@ -29,14 +29,17 @@ jobs:
           dockerfile: cuda12.2
           tags: superbench/main:cuda12.2
           runner: [self-hosted, rocm-build]
+          build_args: "NUM_MAKE_JOBS=64"
         - name: cuda11.1.1
           dockerfile: cuda11.1.1
           tags: superbench/main:cuda11.1.1,superbench/superbench:latest
           runner: ubuntu-latest
+          build_args: "NUM_MAKE_JOBS=8"
         - name: rocm5.7
           dockerfile: rocm5.7.x
           tags: superbench/main:rocm5.7
           runner: [self-hosted, rocm-build]
+          build_args: "NUM_MAKE_JOBS=64"
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -76,7 +79,7 @@ jobs:
           fi
           DOCKERFILE=dockerfile/${{ matrix.dockerfile }}.dockerfile
 
-          BUILD_ARGS="NUM_MAKE_JOBS=8"
+          BUILD_ARGS=${{ matrix.build_args }}
           if [[ "${{ matrix.extra_args }}" ]]; then
             BUILD_ARGS="${BUILD_ARGS} ${{ matrix.extra_args }}"
           fi
@@ -108,7 +111,7 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       - name: Pull cache image
-        run: sudo docker pull $(cut -d, -f1 <<<${{ steps.metadata.outputs.tags }})
+        run: sudo docker pull ${{ steps.metadata.outputs.tags }}
         continue-on-error: true
       - name: Login to the GitHub Container Registry
         uses: docker/login-action@v1

docs/user-tutorial/benchmarks/micro-benchmarks.md

@@ -58,17 +58,18 @@ Large scale matmul operation using `torch.matmul` with one GPU.
 |--------------------------------|-----------|--------------------------------|
 | pytorch-matmul/nosharding_time | time (ms) | Time of pure matmul operation. |
 
-### `cublaslt-gemm`
+### `cublaslt-gemm` / `hipblaslt-gemm`
 
 #### Introduction
 
-Measure the GEMM performance of [`cublasLtMatmul`](https://docs.nvidia.com/cuda/cublas/#cublasltmatmul).
+Measure the GEMM performance of [`cublasLtMatmul`](https://docs.nvidia.com/cuda/cublas/#cublasltmatmul) or [`hipblasLt-bench`](https://github.com/ROCm/hipBLASLt/blob/develop/clients/benchmarks/README.md).
 
 #### Metrics
 
 | Name                                                      | Unit           | Description                     |
-|----------------------------------------------------------|----------------|---------------------------------|
+|-----------------------------------------------------------|----------------|---------------------------------|
 | cublaslt-gemm/${dtype}\_${batch}\_${m}\_${n}\_${k}_flops  | FLOPS (TFLOPS) | TFLOPS of measured GEMM kernel. |
+| hipblaslt-gemm/${dtype}\_${batch}\_${m}\_${n}\_${k}_flops | FLOPS (TFLOPS) | TFLOPS of measured GEMM kernel. |
 
 ### `cublas-function`
 

superbench/benchmarks/micro_benchmarks/hipblaslt_function.py

@@ -103,7 +103,8 @@ def _process_raw_result(self, cmd_idx, raw_output):
                 raise ValueError('Invalid result')
 
             self._result.add_result(
-                f'{self._precision_in_commands[cmd_idx]}_{fields[3]}_{"_".join(fields[4:7])}_flops', float(fields[-2])
+                f'{self._precision_in_commands[cmd_idx]}_{fields[3]}_{"_".join(fields[4:7])}_flops',
+                float(fields[-2]) / 1000
             )
         except BaseException as e:
             self._result.set_return_code(ReturnCode.MICROBENCHMARK_RESULT_PARSING_FAILURE)

tests/benchmarks/micro_benchmarks/test_hipblaslt_function.py

@@ -102,7 +102,7 @@ def test_hipblaslt_gemm_result_parsing(self):
         self.assertEqual(ReturnCode.SUCCESS, benchmark.return_code)
 
         self.assertEqual(2, len(benchmark.result))
-        self.assertEqual(58624.5, benchmark.result['fp16_1_896_896_896_flops'][0])
+        self.assertEqual(58.6245, benchmark.result['fp16_1_896_896_896_flops'][0])
 
         # Negative case - invalid raw output
         self.assertFalse(benchmark._process_raw_result(1, 'HipBLAS API failed'))

third_party/Makefile

@@ -216,21 +216,21 @@ apex_rocm:
 cuda_msccl: sb_micro_path
 ifneq (,$(wildcard msccl/executor/msccl-executor-nccl/Makefile))
 	cd ./msccl/executor/msccl-executor-nccl && \
-	make -j4 src.build && \
+	make -j $(shell nproc --ignore=2) src.build && \
 	cd ../../..
 	mkdir -p $(SB_MICRO_PATH)/lib/msccl-executor-nccl && \
 	cp -r -v ./msccl/executor/msccl-executor-nccl/build/* $(SB_MICRO_PATH)/lib/msccl-executor-nccl/
 endif
 ifneq (,$(wildcard msccl/scheduler/msccl-scheduler/Makefile))
 	cd ./msccl/scheduler/msccl-scheduler && \
-	CXX=nvcc BIN_HOME=$(SB_MICRO_PATH)/lib/msccl-executor-nccl SRC_HOME=../../../msccl/executor/msccl-executor-nccl make -j4 && \
+	CXX=nvcc BIN_HOME=$(SB_MICRO_PATH)/lib/msccl-executor-nccl SRC_HOME=../../../msccl/executor/msccl-executor-nccl make -j $(shell nproc --ignore=2) && \
 	cd ../../..
 	mkdir -p $(SB_MICRO_PATH)/lib/msccl-scheduler && \
 	cp -r -v ./msccl/scheduler/msccl-scheduler/build/* $(SB_MICRO_PATH)/lib/msccl-scheduler/
 endif
 ifneq (,$(wildcard msccl/tests/msccl-tests-nccl/Makefile))
 	cd ./msccl/tests/msccl-tests-nccl && \
-	make MPI=1 MPI_HOME=$(MPI_HOME) NCCL_HOME=$(SB_MICRO_PATH)/lib/msccl-executor-nccl -j4 && cd ../../..
+	make MPI=1 MPI_HOME=$(MPI_HOME) NCCL_HOME=$(SB_MICRO_PATH)/lib/msccl-executor-nccl -j $(shell nproc --ignore=2) && cd ../../..
 	mkdir -p $(SB_MICRO_PATH)/bin/msccl-tests-nccl && \
 	cp -r -v ./msccl/tests/msccl-tests-nccl/build/* $(SB_MICRO_PATH)/bin/msccl-tests-nccl/
 endif