Skip to content

Fix benchmarks #503

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

Closed
wants to merge 2 commits into from
Closed

Fix benchmarks #503

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0e4678
Fix benchmarks
Sep 12, 2022
4b635e9
Fix syntax circleCI
Sep 12, 2022
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
29 changes: 21 additions & 8 deletions .circleci/config.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,7 +247,10 @@ commands:
default: "cpu"
type: string
layers:
default: "mha dpmha gsm_dpmha embedding gsm_embedding instancenorm gsm_instancenorm groupnorm gsm_groupnorm layernorm gsm_layernorm lstm dplstm gsm_dplstm rnn dprnn gsm_dprnn linear gsm_linear gru dpgru gsm_dpgru"
default: "mha dpmha embedding instancenorm groupnorm layernorm lstm dplstm rnn dprnn linear gru dpgru"
type: string
grad_sample_modes:
default: "baseline hooks"
type: string
runtime_ratio_threshold:
default: "7.0"
Expand Down Expand Up @@ -363,52 +366,62 @@ jobs:
- run_nvidia_smi
- benchmark_layers_integration_test:
device: "cuda"
layers: "groupnorm gsm_groupnorm instancenorm gsm_instancenorm layernorm gsm_layernorm mha dpmha"
layers: "groupnorm instancenorm layernorm mha dpmha"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "3.0"
memory_ratio_threshold: "1.6"
- benchmark_layers_integration_test:
device: "cuda"
layers: "linear gsm_linear"
layers: "linear"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "3.6"
memory_ratio_threshold: "13.0"
- benchmark_layers_integration_test:
device: "cuda"
layers: "mha gsm_dpmha"
layers: "mha"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "3.5"
memory_ratio_threshold: "2.0"
- benchmark_layers_integration_test:
device: "cuda"
layers: "gru dpgru"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "18.5"
memory_ratio_threshold: "1.2"
- benchmark_layers_integration_test:
device: "cuda"
layers: "gru gsm_dpgru"
layers: "gru"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "40"
memory_ratio_threshold: "1.6"
- benchmark_layers_integration_test:
device: "cuda"
layers: "lstm dplstm"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "16.5"
memory_ratio_threshold: "1.2"
- benchmark_layers_integration_test:
device: "cuda"
layers: "lstm gsm_dplstm"
layers: "lstm"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "38.0"
memory_ratio_threshold: "1.8"
- benchmark_layers_integration_test:
device: "cuda"
layers: "rnn dprnn"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "10.0"
memory_ratio_threshold: "1.2"
- benchmark_layers_integration_test:
device: "cuda"
layers: "rnn gsm_dprnn"
layers: "rnn"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "33.0"
memory_ratio_threshold: "1.2"
- benchmark_layers_integration_test:
device: "cuda"
layers: "embedding gsm_embedding"
layers: "embedding"
grad_sample_modes: "baseline hooks"
runtime_ratio_threshold: "8.0"
memory_ratio_threshold: "15.0"

Expand Down