From 3ec4b745d647140d43204a036997edf18005a3f1 Mon Sep 17 00:00:00 2001 From: chenyu Date: Thu, 25 Apr 2024 18:33:40 -0400 Subject: [PATCH] JIT=2 for mac cifar benchmark (#4300) also double BS for resnet training benchmark to match submission target --- .github/workflows/benchmark.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index c9c8fa2c03..01e365207b 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -61,9 +61,9 @@ jobs: - name: Train MNIST run: time PYTHONPATH=. TARGET_EVAL_ACC_PCT=97.3 python3 examples/beautiful_mnist.py | tee beautiful_mnist.txt - name: Run 10 CIFAR training steps - run: STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar.txt + run: JIT=2 STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar.txt - name: Run 10 CIFAR training steps w HALF - run: STEPS=10 DEFAULT_FLOAT=HALF python3 examples/hlb_cifar10.py | tee train_cifar_half.txt + run: JIT=2 STEPS=10 DEFAULT_FLOAT=HALF python3 examples/hlb_cifar10.py | tee train_cifar_half.txt #- name: Run 10 CIFAR training steps w BF16 # run: STEPS=10 DEFAULT_FLOAT=BFLOAT16 python3 examples/hlb_cifar10.py | tee train_cifar_bf16.txt # TODO: this is flaky too @@ -292,9 +292,9 @@ jobs: - name: Run MLPerf resnet eval on training data run: time HSA=1 MODEL=resnet python3 examples/mlperf/model_eval.py - name: Run 10 MLPerf ResNet50 training steps (1 gpu) - run: HSA=1 DEFAULT_FLOAT=HALF BENCHMARK=10 BS=128 GPUS=1 MODEL=resnet python3 examples/mlperf/model_train.py | tee train_resnet_one_gpu.txt + run: HSA=1 DEFAULT_FLOAT=HALF BENCHMARK=10 BS=256 GPUS=1 MODEL=resnet python3 examples/mlperf/model_train.py | tee train_resnet_one_gpu.txt - name: Run 10 MLPerf ResNet50 training steps (6 gpu) - run: HSA=1 DEFAULT_FLOAT=HALF BENCHMARK=10 BS=768 GPUS=6 MODEL=resnet python3 examples/mlperf/model_train.py | tee train_resnet.txt + run: HSA=1 DEFAULT_FLOAT=HALF BENCHMARK=10 BS=1536 GPUS=6 MODEL=resnet python3 examples/mlperf/model_train.py | tee train_resnet.txt - uses: actions/upload-artifact@v4 with: name: Speed (AMD Training)