Skip to content

Revert the changes that were made for an urgent demo #90

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

Merged
chishuen merged 1 commit into from
Jan 27, 2026
Merged

Revert the changes that were made for an urgent demo #90

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_1d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "1x1x4", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_1d"
csv_path: "../microbenchmarks/all_gather_1d"
xlml_metrics_dir: "../microbenchmarks/all_gather_1d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_2d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2, num_runs: 5} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x32", ici_size_range: 128, sharding_strategy: "1x32", op_dimension: 2, num_runs: 5} # Non Parallel Replica Groups
trace_dir: "../microbenchmarks/all_gather_2d"
csv_path: "../microbenchmarks/all_gather_2d"
xlml_metrics_dir: "../microbenchmarks/all_gather_2d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_3d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3, num_runs: 5} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "4x4x8", op_dimension: 3, num_runs: 5} # Non Parallel Replica Groups
trace_dir: "../microbenchmarks/all_gather_3d"
csv_path: "../microbenchmarks/all_gather_3d"
xlml_metrics_dir: "../microbenchmarks/all_gather_3d"
Expand Down
10 changes: 7 additions & 3 deletions Ironwood/configs/collectives/all_gather_demo.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,13 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1", op_dimension: 1}
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2}
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3}
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1", op_dimension: 1} # Parallel Replica
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "1x1x4", op_dimension: 1} # Non-Parallel Replica
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "4x32", ici_size_range: 128, sharding_strategy: "1x32", op_dimension: 2} # Non Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 512, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "4x4x8", op_dimension: 3} # Non Parallel Replica Groups


warmup_tries: 10
trace_dir: "../microbenchmarks/all_gather_demo"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_2x2x1"
csv_path: "../microbenchmarks/all_gather_tpu7x_2x2x1"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_2x2x1"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_tpu7x_2x2x2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_2x2x2"
csv_path: "../microbenchmarks/all_gather_tpu7x_2x2x2"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_2x2x2"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_tpu7x_2x2x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_2x2x4"
csv_path: "../microbenchmarks/all_gather_tpu7x_2x2x4"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_2x2x4"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_tpu7x_2x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_2x4x4"
csv_path: "../microbenchmarks/all_gather_tpu7x_2x4x4"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_2x4x4"
Expand Down
5 changes: 3 additions & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_4x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x1", op_dimension: 1, num_runs: 10}
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_4x4x4"
csv_path: "../microbenchmarks/all_gather_tpu7x_4x4x4"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_4x4x4"
xla_dump_dir: "../microbenchmarks/all_gather_tpu7x_4x4x4/hlo_graphs"
xla_dump_dir: "../microbenchmarks/all_gather_tpu7x_4x4x4/hlo_graphs"
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_gather_tpu7x_4x4x8.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_gather
benchmark_sweep_params:
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_gather_tpu7x_4x4x8"
csv_path: "../microbenchmarks/all_gather_tpu7x_4x4x8"
xlml_metrics_dir: "../microbenchmarks/all_gather_tpu7x_4x4x8"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_1d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1" , op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "1x4x1" , op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "1x1x4", op_dimension: 1, num_runs: 5} # Non Parallel Replica
trace_dir: "../microbenchmarks/all_reduce_1d"
csv_path: "../microbenchmarks/all_reduce_1d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_1d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_2d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x16x2", ici_size_range: 128, sharding_strategy: "1x16x1", op_dimension: 2, num_runs: 5} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x32", ici_size_range: 128, sharding_strategy: "1x32", op_dimension: 2, num_runs: 5} # Non Parallel Replica Groups
trace_dir: "../microbenchmarks/all_reduce_2d"
csv_path: "../microbenchmarks/all_reduce_2d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_2d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_3d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "64x2", ici_size_range: 128, sharding_strategy: "64x1", op_dimension: 3, num_runs: 5} # Parallel Replica Groups
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "4x4x8", op_dimension: 3, num_runs: 5} # Non Parallel Replica Groups
trace_dir: "../microbenchmarks/all_reduce_3d"
csv_path: "../microbenchmarks/all_reduce_3d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_3d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x1"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x1"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x1"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_2x2x2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x2x2", ici_size_range: 16, sharding_strategy: "4x2x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x2"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x2"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x2"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_2x2x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 16, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x2", ici_size_range: 32, sharding_strategy: "4x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x4"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x4"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_2x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 32, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "8x4x2", ici_size_range: 64, sharding_strategy: "8x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_2x4x4"
csv_path: "../microbenchmarks/psum_tpu7x_2x4x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x4x4"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_4x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 64, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "16x4x2", ici_size_range: 128, sharding_strategy: "16x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_4x4x4"
csv_path: "../microbenchmarks/psum_tpu7x_4x4x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_4x4x4"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_reduce_tpu7x_4x4x8.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: psum
benchmark_sweep_params:
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 128, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "32x4x2", ici_size_range: 256, sharding_strategy: "32x4x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/psum_tpu7x_4x4x8"
csv_path: "../microbenchmarks/psum_tpu7x_4x4x8"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_4x4x8"
Expand Down
2 changes: 1 addition & 1 deletion Ironwood/configs/collectives/all_to_all_1d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
benchmarks:
- benchmark_name: all_to_all
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "1x1x4", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "1x1x4", op_dimension: 1, num_runs: 5} # Non Parallel Replica
trace_dir: "../microbenchmarks/all_to_all_1d"
csv_path: "../microbenchmarks/all_to_all_1d"
xlml_metrics_dir: "../microbenchmarks/all_to_all_1d"
Expand Down
2 changes: 1 addition & 1 deletion Ironwood/configs/collectives/all_to_all_2d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
benchmarks:
- benchmark_name: all_to_all
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x32", ici_size_range: 128, sharding_strategy: "1x32", op_dimension: 2, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x32", ici_size_range: 128, sharding_strategy: "1x32", op_dimension: 2, num_runs: 5} # Non Parallel Replica
trace_dir: "../microbenchmarks/all_to_all_2d"
csv_path: "../microbenchmarks/all_to_all_2d"
xlml_metrics_dir: "../microbenchmarks/all_to_all_2d"
Expand Down
2 changes: 1 addition & 1 deletion Ironwood/configs/collectives/all_to_all_3d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
benchmarks:
- benchmark_name: all_to_all
benchmark_sweep_params:
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "4x4x8", op_dimension: 3, num_runs: 5}
- {matrix_dim_range: {start: 2, end: 8192, multiplier: 2}, dtype: "float32", mesh_shape: "4x4x8", ici_size_range: 128, sharding_strategy: "4x4x8", op_dimension: 3, num_runs: 5} # Non Parallel Replica Groups
trace_dir: "../microbenchmarks/all_to_all_3d"
csv_path: "../microbenchmarks/all_to_all_3d"
xlml_metrics_dir: "../microbenchmarks/all_to_all_3d"
Expand Down
3 changes: 2 additions & 1 deletion Ironwood/configs/collectives/all_to_all_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
benchmarks:
- benchmark_name: all_to_all
benchmark_sweep_params:
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5}
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x1", op_dimension: 1, num_runs: 5} # Parallel Replica
- {matrix_dim_range: {start: 8, end: 16384, multiplier: 2}, dtype: "float32", mesh_shape: "2x2x2", ici_size_range: 8, sharding_strategy: "2x2x2", op_dimension: 1, num_runs: 5} # Non-Parallel Replica
trace_dir: "../microbenchmarks/all_to_all_tpu7x_2x2x1"
csv_path: "../microbenchmarks/all_to_all_tpu7x_2x2x1"
xlml_metrics_dir: "../microbenchmarks/all_to_all_tpu7x_2x2x1"
Expand Down
Loading