update for 5.0

This commit is contained in:
Chen-Yu Yang 2025-04-28 14:32:08 -04:00
commit 12c6573cf6
16 changed files with 92 additions and 265 deletions

View file

@ -1,15 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="bert"
export DEFAULT_FLOAT="HALF" GPUS=1 BS=128 EVAL_BS=128
export BEAM=3 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
# export BEAM_LOG_SURPASS_MAX=1
# export BASEDIR="/raid/datasets/wiki"
export RESET_STEP=1
export BENCHMARK=10 BERT_LAYERS=2 DEBUG=2
python3 examples/mlperf/model_train.py

View file

@ -0,0 +1,69 @@
# 1. Problem
This problem uses BERT for NLP.
## Requirements
Install tinygrad and mlperf-logging (uncomment mlperf from setup.py) from branch mlperf_training_v5.0.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"
```
Also install gdown (for dataset), numpy, tqdm and tensorflow.
```
pip install gdown numpy tqdm tensorflow
```
### tinybox_green
Install the p2p driver per [README](https://github.com/tinygrad/open-gpu-kernel-modules/blob/550.54.15-p2p/README.md)
This is the default on production tinybox green.
# 2. Directions
## Steps to download and verify data
### 1. Download raw data
```
BASEDIR="/raid/datasets/wiki" WIKI_TRAIN=1 VERIFY_CHECKSUM=1 python3 extra/datasets/wikipedia_download.py
```
### 2. Preprocess train and validation data
Note: The number of threads used for preprocessing is limited by available memory. With 128GB of RAM, a maximum of 16 threads is recommended.
#### Training:
```
BASEDIR="/raid/datasets/wiki" NUM_WORKERS=16 python3 extra/datasets/wikipedia.py pre-train all
```
Generating a specific topic (Between 0 and 499)
```
BASEDIR="/raid/datasets/wiki" python3 extra/datasets/wikipedia.py pre-train 42
```
#### Validation:
```
BASEDIR="/raid/datasets/wiki" python3 extra/datasets/wikipedia.py pre-eval
```
## Running
### tinybox_green
#### Steps to run benchmark
```
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
```
### tinybox_red
#### Steps to run benchmark
```
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
```
### tinybox_8xMI300X
#### Steps to run benchmark
```
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_8xMI300X/run_and_time.sh
```

View file

@ -4,14 +4,14 @@ This problem uses BERT for NLP.
## Requirements
Install tinygrad and mlperf-logging from master.
Install tinygrad and mlperf-logging (uncomment mlperf from setup.py) from branch mlperf_training_v5.0.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"
```
Also install tqdm and tensorflow.
Also install gdown (for dataset), numpy, tqdm and tensorflow.
```
pip install tqdm tensorflow
pip install gdown numpy tqdm tensorflow
```
### tinybox_green
@ -52,12 +52,18 @@ BASEDIR="/raid/datasets/wiki" python3 extra/datasets/wikipedia.py pre-eval
#### Steps to run benchmark
```
examples/mlperf/training_submission_v4.1/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
```
### tinybox_red
#### Steps to run benchmark
```
examples/mlperf/training_submission_v4.1/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
```
### tinybox_8xMI300X
#### Steps to run benchmark
```
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_8xMI300X/run_and_time.sh
```

View file

@ -4,14 +4,14 @@ This problem uses BERT for NLP.
## Requirements
Install tinygrad and mlperf-logging from master.
Install tinygrad and mlperf-logging (uncomment mlperf from setup.py) from branch mlperf_training_v5.0.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"
```
Also install tqdm and tensorflow.
Also install gdown (for dataset), numpy, tqdm and tensorflow.
```
pip install tqdm tensorflow
pip install gdown numpy tqdm tensorflow
```
### tinybox_green
@ -52,12 +52,18 @@ BASEDIR="/raid/datasets/wiki" python3 extra/datasets/wikipedia.py pre-eval
#### Steps to run benchmark
```
examples/mlperf/training_submission_v4.1/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
```
### tinybox_red
#### Steps to run benchmark
```
examples/mlperf/training_submission_v4.1/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
```
### tinybox_8xMI300X
#### Steps to run benchmark
```
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_8xMI300X/run_and_time.sh
```

View file

@ -1,50 +0,0 @@
# 1. Problem
This problem uses the ResNet-50 CNN to do image classification.
## Requirements
Install tinygrad and mlperf-logging from master.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"
```
### tinybox_green
Install the p2p driver per [README](https://github.com/tinygrad/open-gpu-kernel-modules/blob/550.54.15-p2p/README.md)
This is the default on production tinybox green.
### tinybox_red
Disable cwsr
This is the default on production tinybox red.
```
sudo vi /etc/modprobe.d/amdgpu.conf
cat <<EOF > /etc/modprobe.d/amdgpu.conf
options amdgpu cwsr_enable=0
EOF
sudo update-initramfs -u
sudo reboot
# validate
sudo cat /sys/module/amdgpu/parameters/cwsr_enable #= 0
```
# 2. Directions
## Steps to download and verify data
```
IMGNET_TRAIN=1 python3 extra/datasets/imagenet_download.py
```
## Steps for one time setup
### tinybox_red
```
examples/mlperf/training_submission_v4.0/tinycorp/benchmarks/resnet/implementations/tinybox_red/setup.sh
```
## Steps to run benchmark
```
examples/mlperf/training_submission_v4.0/tinycorp/benchmarks/resnet/implementations/tinybox_red/run_and_time.sh
```

View file

@ -1,13 +0,0 @@
#!/bin/bash
export PYTHONPATH="." NV=1
export MODEL="resnet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=1500 BEAM_UPCAST_MAX=64 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=10 BEAM_PADTO=0
export BENCHMARK=10 DEBUG=2
python3 examples/mlperf/model_train.py

View file

@ -1,15 +0,0 @@
#!/bin/bash
export PYTHONPATH="." NV=1
export MODEL="resnet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=1500 BEAM_UPCAST_MAX=64 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=10 BEAM_PADTO=0
export EVAL_START_EPOCH=3 EVAL_FREQ=4
export WANDB=1 PARALLEL=0
python3 examples/mlperf/model_train.py

View file

@ -1,23 +0,0 @@
#!/bin/bash
export PYTHONPATH="." NV=1
export MODEL="resnet"
export SUBMISSION_PLATFORM="tinybox_green"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=1500 BEAM_UPCAST_MAX=64 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=10 BEAM_PADTO=0
# pip install -e ".[mlperf]"
export LOGMLPERF=1
export SEED=$RANDOM
DATETIME=$(date "+%m%d%H%M")
LOGFILE="resnet_green_${DATETIME}_${SEED}.log"
# init
BENCHMARK=10 INITMLPERF=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
# run
PARALLEL=0 RUNMLPERF=1 EVAL_START_EPOCH=3 EVAL_FREQ=4 python3 examples/mlperf/model_train.py | tee -a $LOGFILE

View file

@ -1,50 +0,0 @@
# 1. Problem
This problem uses the ResNet-50 CNN to do image classification.
## Requirements
Install tinygrad and mlperf-logging from master.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"
```
### tinybox_green
Install the p2p driver per [README](https://github.com/tinygrad/open-gpu-kernel-modules/blob/550.54.15-p2p/README.md)
This is the default on production tinybox green.
### tinybox_red
Disable cwsr
This is the default on production tinybox red.
```
sudo vi /etc/modprobe.d/amdgpu.conf
cat <<EOF > /etc/modprobe.d/amdgpu.conf
options amdgpu cwsr_enable=0
EOF
sudo update-initramfs -u
sudo reboot
# validate
sudo cat /sys/module/amdgpu/parameters/cwsr_enable #= 0
```
# 2. Directions
## Steps to download and verify data
```
IMGNET_TRAIN=1 python3 extra/datasets/imagenet_download.py
```
## Steps for one time setup
### tinybox_red
```
examples/mlperf/training_submission_v4.0/tinycorp/benchmarks/resnet/implementations/tinybox_red/setup.sh
```
## Steps to run benchmark
```
examples/mlperf/training_submission_v4.0/tinycorp/benchmarks/resnet/implementations/tinybox_red/run_and_time.sh
```

View file

@ -1,13 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="resnet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=2000 BEAM_UPCAST_MAX=96 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5 BEAM_PADTO=0
export BENCHMARK=10 DEBUG=2
python3 examples/mlperf/model_train.py

View file

@ -1,15 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="resnet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=2000 BEAM_UPCAST_MAX=96 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5 BEAM_PADTO=0
export EVAL_START_EPOCH=3 EVAL_FREQ=4
export WANDB=1 PARALLEL=0
python3 examples/mlperf/model_train.py

View file

@ -1,23 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="resnet"
export SUBMISSION_PLATFORM="tinybox_red"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=1536 EVAL_BS=192
export RESET_STEP=0
export TRAIN_BEAM=4 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=2000 BEAM_UPCAST_MAX=96 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5 BEAM_PADTO=0
# pip install -e ".[mlperf]"
export LOGMLPERF=1
export SEED=$RANDOM
DATETIME=$(date "+%m%d%H%M")
LOGFILE="resnet_red_${DATETIME}_${SEED}.log"
# init
BENCHMARK=10 INITMLPERF=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
# run
PARALLEL=0 RUNMLPERF=1 EVAL_START_EPOCH=3 EVAL_FREQ=4 python3 examples/mlperf/model_train.py | tee -a $LOGFILE

View file

@ -1,8 +0,0 @@
#!/bin/bash
rocm-smi --setprofile compute
rocm-smi --setmclk 3
rocm-smi --setperflevel high
# power cap to 350W
echo "350000000" | sudo tee /sys/class/drm/card{1..6}/device/hwmon/hwmon*/power1_cap

View file

@ -4,7 +4,7 @@ This problem uses RetinaNet for SSD.
## Requirements
Install tinygrad and mlperf-logging from master.
Install tinygrad and mlperf-logging (uncomment mlperf from setup.py) from branch mlperf_training_v5.0.
```
git clone https://github.com/tinygrad/tinygrad.git
python3 -m pip install -e ".[mlperf]"

View file

@ -1,14 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="retinanet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=96 EVAL_BS=96
export BASEDIR="/raid/datasets/openimages"
# export RESET_STEP=0
export TRAIN_BEAM=2 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=1500 BEAM_UPCAST_MAX=64 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5 BEAM_PADTO=0
export BENCHMARK=5 DEBUG=2
python examples/mlperf/model_train.py

View file

@ -1,15 +0,0 @@
#!/bin/bash
export PYTHONPATH="." AMD=1
export MODEL="retinanet"
export DEFAULT_FLOAT="HALF" GPUS=6 BS=96 EVAL_BS=96
export BASEDIR="/raid/datasets/openimages"
# export RESET_STEP=0
export TRAIN_BEAM=2 IGNORE_JIT_FIRST_BEAM=1 BEAM_UOPS_MAX=1500 BEAM_UPCAST_MAX=64 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5 BEAM_PADTO=0
export WANDB=1 PARALLEL=0
export RUNMLPERF=1
python examples/mlperf/model_train.py