Skip to content

[Fix][Manifest] add at least 2 workloads to 21 binary elementwise ops (cherry-pick #1392) #1395

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
Ibuki-wind merged 1 commit into from
May 9, 2026
+63 −42
Merged

[Fix][Manifest] add at least 2 workloads to 21 binary elementwise ops (cherry-pick #1392) #1395

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
105 changes: 63 additions & 42 deletions tileops/manifest/elementwise_binary.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,8 +150,9 @@ AddFwdOp:
# Output follows PyTorch broadcasting; numel uses the broadcast shape.
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.add_fwd_roofline"

Expand All @@ -178,8 +179,9 @@ SubFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.sub_fwd_roofline"

Expand All @@ -204,8 +206,9 @@ MulFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.mul_fwd_roofline"

Expand Down Expand Up @@ -233,8 +236,9 @@ DivFwdOp:
- "output.shape == broadcast_shapes(input.shape, other.shape)"
- "rounding_mode is None or rounding_mode in ('trunc', 'floor')"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.div_fwd_roofline"

Expand All @@ -259,8 +263,9 @@ RemainderFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.remainder_fwd_roofline"

Expand All @@ -285,8 +290,9 @@ PowFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, exponent.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], exponent_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], exponent_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.pow_fwd_roofline"

Expand All @@ -311,8 +317,9 @@ FloorDivideFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.floor_divide_fwd_roofline"

Expand Down Expand Up @@ -342,8 +349,9 @@ LerpFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, end.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], end_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], end_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.lerp_fwd_roofline"

Expand All @@ -368,8 +376,9 @@ MaximumFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.maximum_fwd_roofline"

Expand All @@ -394,8 +403,9 @@ MinimumFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.minimum_fwd_roofline"

Expand Down Expand Up @@ -424,8 +434,9 @@ EqFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.eq_fwd_roofline"

Expand All @@ -450,8 +461,9 @@ NeFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.ne_fwd_roofline"

Expand All @@ -476,8 +488,9 @@ GtFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.gt_fwd_roofline"

Expand All @@ -502,8 +515,9 @@ LtFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.lt_fwd_roofline"

Expand All @@ -528,8 +542,9 @@ GeFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.ge_fwd_roofline"

Expand All @@ -554,8 +569,9 @@ LeFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.le_fwd_roofline"

Expand Down Expand Up @@ -584,8 +600,9 @@ LogicalAndFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [bool, float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [bool, float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.logical_and_fwd_roofline"

Expand All @@ -610,8 +627,9 @@ LogicalOrFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [bool, float16, bfloat16, float32], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [bool, float16, bfloat16, float32], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.logical_or_fwd_roofline"

Expand Down Expand Up @@ -640,8 +658,9 @@ BitwiseAndFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [bool, int32, int64], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [bool, int32, int64], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.bitwise_and_fwd_roofline"

Expand All @@ -666,8 +685,9 @@ BitwiseOrFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [bool, int32, int64], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [bool, int32, int64], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.bitwise_or_fwd_roofline"

Expand All @@ -692,8 +712,9 @@ BitwiseXorFwdOp:
shape_rules:
- "output.shape == broadcast_shapes(input.shape, other.shape)"

workloads: []

workloads:
- {input_shape: [2048, 4096], other_shape: [2048, 4096], dtypes: [bool, int32, int64], label: hidden-state-prefill}
- {input_shape: [16, 256, 56, 56], other_shape: [256, 1, 1], dtypes: [bool, int32, int64], label: cnn-feat-broadcast}
roofline:
func: "tileops.perf.formulas.bitwise_xor_fwd_roofline"

Expand Down
Loading