-
Notifications
You must be signed in to change notification settings - Fork 14.6k
[mlir][linalg] Allow pack consumer fusion if the tile size is greater than dimension size. #149438
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.
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
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -451,6 +451,56 @@ module attributes {transform.with_named_sequence} { | |
|
||
// ----- | ||
|
||
#map = affine_map<(d0) -> (-d0 + 4, 16)> | ||
func.func @fuse_pack_consumer_if_single_iteration(%arg0: tensor<4x4xf32>) -> tensor<1x4x16x1xf32> { | ||
%0 = tensor.empty() : tensor<1x4x16x1xf32> | ||
%1 = tensor.empty() : tensor<4x4xf32> | ||
%2 = scf.forall (%arg1) = (0) to (4) step (16) shared_outs(%arg2 = %1) -> (tensor<4x4xf32>) { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Q: wouldn't/shouldn't this (and in general one-iteration loops) be folded away? Probably it should happen at a different point/place, but still just wondering :) There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. If this is |
||
%3 = affine.min #map(%arg1) | ||
%extracted_slice = tensor.extract_slice %arg0[%arg1, 0] [%3, 4] [1, 1] : tensor<4x4xf32> to tensor<?x4xf32> | ||
%extracted_slice_0 = tensor.extract_slice %arg2[%arg1, 0] [%3, 4] [1, 1] : tensor<4x4xf32> to tensor<?x4xf32> | ||
%4 = linalg.exp ins(%extracted_slice : tensor<?x4xf32>) outs(%extracted_slice_0 : tensor<?x4xf32>) -> tensor<?x4xf32> | ||
scf.forall.in_parallel { | ||
tensor.parallel_insert_slice %4 into %arg2[%arg1, 0] [%3, 4] [1, 1] : tensor<?x4xf32> into tensor<4x4xf32> | ||
} | ||
} | ||
%cst = arith.constant 0.000000e+00 : f32 | ||
%pack = linalg.pack %2 padding_value(%cst : f32) outer_dims_perm = [0, 1] inner_dims_pos = [0, 1] inner_tiles = [16, 1] into %0 : tensor<4x4xf32> -> tensor<1x4x16x1xf32> | ||
return %pack : tensor<1x4x16x1xf32> | ||
} | ||
|
||
module attributes {transform.with_named_sequence} { | ||
transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) { | ||
%0 = transform.structured.match ops{["tensor.parallel_insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op | ||
%1 = transform.structured.match ops{["scf.forall"]} in %arg0 : (!transform.any_op) -> !transform.any_op | ||
%consumer, %fused_consumer = transform.test.fuse_consumer %0 in(%1) : (!transform.any_op, !transform.any_op) -> (!transform.any_op, !transform.any_op) | ||
transform.yield | ||
} | ||
} | ||
// CHECK: #[[MAP:.*]] = affine_map<(d0) -> (-d0 + 4, 16)> | ||
// CHECK: func.func @fuse_pack_consumer_if_single_iteration( | ||
// CHECK-SAME: %[[ARG0:[a-zA-Z0-9]+]] | ||
// CHECK-DAG: %[[PACK_INIT:.*]] = tensor.empty() : tensor<1x4x16x1xf32> | ||
// CHECK-DAG: %[[ELEM_INIT:.*]] = tensor.empty() : tensor<4x4xf32> | ||
// CHECK-DAG: %[[PAD_VAL:.*]] = arith.constant 0.000000e+00 : f32 | ||
// CHECK: %{{.*}}:2 = scf.forall (%[[IV:.*]]) = (0) to (4) step (16) | ||
// CHECK-SAME: shared_outs(%[[ELEM_OUT_ARG:.*]] = %[[ELEM_INIT]], %[[PACK_OUT_ARG:.*]] = %[[PACK_INIT]]) | ||
// CHECK-DAG: %[[SIZE:.+]] = affine.min #[[MAP]](%[[IV]]) | ||
// CHECK-DAG: %[[ELEM_SRC:.*]] = tensor.extract_slice %[[ARG0]][%[[IV]], 0] [%[[SIZE]], 4] [1, 1] | ||
// CHECK-DAG: %[[ELEM_DEST:.*]] = tensor.extract_slice %[[ELEM_OUT_ARG]][%[[IV]], 0] [%[[SIZE]], 4] [1, 1] | ||
// CHECK: %[[ELEM:.*]] = linalg.exp | ||
// CHECK-SAME: ins(%[[ELEM_SRC]] | ||
// CHECK-SAME: outs(%[[ELEM_DEST]] | ||
// CHECK-DAG: %[[TILED_PACK_DEST:.*]] = tensor.extract_slice %[[PACK_OUT_ARG]][%[[IV]], 0, 0, 0] [1, 4, 16, 1] [1, 1, 1, 1] | ||
// CHECK: %[[PACK:.*]] = linalg.pack %[[ELEM]] | ||
// CHECK-SAME: padding_value(%[[PAD_VAL]] : f32) | ||
// CHECK-SAME: outer_dims_perm = [0, 1] inner_dims_pos = [0, 1] inner_tiles = [16, 1] | ||
// CHECK-SAME: into %[[TILED_PACK_DEST]] | ||
// CHECK: scf.forall.in_parallel { | ||
// CHECK: tensor.parallel_insert_slice %[[ELEM]] into %[[ELEM_OUT_ARG]][%[[IV]], 0] [%[[SIZE]], 4] [1, 1] | ||
// CHECK: tensor.parallel_insert_slice %[[PACK]] into %[[PACK_OUT_ARG]][%[[IV]], 0, 0, 0] [1, 4, 16, 1] [1, 1, 1, 1] | ||
|
||
// ----- | ||
|
||
func.func @fuse_perfect_tiling_pack_consumer_with_outer_dims_perm(%arg0: tensor<64x32xf32>, %arg1: tensor<64x32xf32>, %arg2: tensor<2x64x16x1xf32>) -> tensor<2x64x16x1xf32> { | ||
%0 = scf.forall (%arg3) = (0) to (32) step (16) shared_outs(%arg4 = %arg1) -> (tensor<64x32xf32>) { | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A comment here explaining the
<
would be nice, something like what you have in the description.