Skip to content

Tpu7x for demo #87

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
junjieqian merged 4 commits into from
Jan 23, 2026
Merged

Tpu7x for demo #87

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5feefca
Create tpu7x-4x4x4-ici-all-gather-microbenchmark.yaml
chishuen Jan 23, 2026
b606171
Update all_gather_tpu7x_4x4x4.yaml
chishuen Jan 23, 2026
ab0c0ef
Create tpu7x-2x2x1-matmul-microbenchmark.yaml
chishuen Jan 23, 2026
699edc5
remove unnecessary runs in config files
chishuen Jan 23, 2026
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_1d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_gather_1d"
csv_path: "../microbenchmarks/all_gather_1d"
xlml_metrics_dir: "../microbenchmarks/all_gather_1d"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_2d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_gather_2d"
csv_path: "../microbenchmarks/all_gather_2d"
xlml_metrics_dir: "../microbenchmarks/all_gather_2d"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_3d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_gather_3d"
csv_path: "../microbenchmarks/all_gather_3d"
xlml_metrics_dir: "../microbenchmarks/all_gather_3d"
Expand Down
10 changes: 3 additions & 7 deletions Ironwood/configs/collectives/all_gather_demo.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,9 @@
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} # 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

- {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}

warmup_tries: 10
trace_dir: "../microbenchmarks/all_gather_demo"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_2x2x2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_2x2x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_2x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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: 2 additions & 3 deletions Ironwood/configs/collectives/all_gather_tpu7x_4x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
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: 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
- {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}
Comment thread
junjieqian marked this conversation as resolved.
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_gather_tpu7x_4x4x8.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_1d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_reduce_1d"
csv_path: "../microbenchmarks/all_reduce_1d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_1d"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_2d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_reduce_2d"
csv_path: "../microbenchmarks/all_reduce_2d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_2d"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_3d.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/all_reduce_3d"
csv_path: "../microbenchmarks/all_reduce_3d"
xlml_metrics_dir: "../microbenchmarks/all_reduce_3d"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x1"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x1"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x1"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_2x2x2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x2"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x2"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x2"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_2x2x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/psum_tpu7x_2x2x4"
csv_path: "../microbenchmarks/psum_tpu7x_2x2x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x2x4"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_2x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/psum_tpu7x_2x4x4"
csv_path: "../microbenchmarks/psum_tpu7x_2x4x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_2x4x4"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_4x4x4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
trace_dir: "../microbenchmarks/psum_tpu7x_4x4x4"
csv_path: "../microbenchmarks/psum_tpu7x_4x4x4"
xlml_metrics_dir: "../microbenchmarks/psum_tpu7x_4x4x4"
Expand Down
3 changes: 1 addition & 2 deletions Ironwood/configs/collectives/all_reduce_tpu7x_4x4x8.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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} # Non 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}
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} # Non Parallel Replica
- {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}
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} # Non 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}
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: 1 addition & 2 deletions Ironwood/configs/collectives/all_to_all_tpu7x_2x2x1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
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} # 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
- {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}
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