Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix MFU printing #585

Closed
wants to merge 2 commits into from
Closed

Fix MFU printing #585

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0e708fe
Fix mfu print when no device; add H100 PCIe
gordicaleksa Jun 13, 2024
cbe2054
Allocate mfu str on stack not heap
gordicaleksa Jun 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions llmc/mfu.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@ static GPUEntry gpu_db[] = {
{"NVIDIA GeForce RTX 4070", &ADA, 184, 2475},
{"NVIDIA GeForce RTX 4060 Ti", &ADA, 136, 2535},
{"NVIDIA GeForce RTX 4060", &ADA, 96, 2460},
{"NVIDIA H100 PCIe", &HOPPER, 456, 1620},
{"NVIDIA H100 80GB HBM3", &HOPPER, 528, 1830}, // HBM3 = SXM5
};

Expand Down
18 changes: 10 additions & 8 deletions train_gpt2.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1239,7 +1239,7 @@ void gpt2_multi_gpu_param_gather(GPT2 *model, MultiGpuConfig* multi_gpu_config)
cudaCheck(cudaDeviceSynchronize());
}

float gpt2_estimate_mfu(GPT2 *model, int num_tokens, float dt) {
void gpt2_estimate_mfu(GPT2 *model, int num_tokens, float dt, char* mfu_str) {
/*
Estimate model flops utilization (MFU)
ref: Section 2.1 of https://arxiv.org/pdf/2001.08361
Expand All @@ -1261,11 +1261,12 @@ float gpt2_estimate_mfu(GPT2 *model, int num_tokens, float dt) {
// express our flops throughput as ratio of A100 bfloat16 peak flops
float flops_achieved = (float)flops_per_step * (1.0f / dt); // per second
float flops_promised = get_flops_promised(deviceProp.name, PRECISION_MODE) * 1e12f;
if(flops_promised < 0) {
return -1.f; // don't know
if(flops_promised < 0) { // don't know
snprintf(mfu_str, sizeof(mfu_str), "n/a");
} else {
float mfu = flops_achieved / flops_promised;
snprintf(mfu_str, sizeof(mfu_str), "%.1f%%", 100 * mfu);
}
float mfu = flops_achieved / flops_promised;
return mfu;
}

void gpt2_free(GPT2 *model) {
Expand Down Expand Up @@ -1671,6 +1672,7 @@ int main(int argc, char *argv[]) {
}

// train
char mfu_str[16];
cudaEvent_t start, end;
cudaCheck(cudaEventCreate(&start));
cudaCheck(cudaEventCreate(&end));
Expand Down Expand Up @@ -1851,10 +1853,10 @@ int main(int argc, char *argv[]) {
bias_corrected_ema_tokens_per_second = ema_tokens_per_second / (1.0f - powf(0.95f, step));
}
float accumulated_loss = multi_gpu_config.num_processes == 1 ? model.mean_loss : model.accumulated_mean_loss;
float mfu = gpt2_estimate_mfu(&model, B * T * grad_accum_steps, time_elapsed_ms / 1000.0f);
printf0("step %4d/%d | train loss %7.6f | norm %6.4f | lr %.2e | %.2f ms | %.1f%% bf16 MFU | %.0f tok/s\n",
gpt2_estimate_mfu(&model, B * T * grad_accum_steps, time_elapsed_ms / 1000.0f, mfu_str);
printf0("step %4d/%d | train loss %7.6f | norm %6.4f | lr %.2e | %.2f ms | %s bf16 MFU | %.0f tok/s\n",
step + 1, train_num_batches, accumulated_loss, grad_norm, step_learning_rate,
time_elapsed_ms, 100*mfu, bias_corrected_ema_tokens_per_second);
time_elapsed_ms, mfu_str, bias_corrected_ema_tokens_per_second);
logger_log_train(&logger, step, model.mean_loss, step_learning_rate, grad_norm);

// disable the profiler after 3 steps of optimization
Expand Down