[Mlir-commits] [mlir] [mlir][vector] Update tests/patterns for vector.transpose (PR #91359)
Andrzej Warzyński
llvmlistbot at llvm.org
Thu May 9 06:55:40 PDT 2024
https://github.com/banach-space updated https://github.com/llvm/llvm-project/pull/91359
>From 819daf804348cf03e48d30ed23405d26150872ed Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Sat, 4 May 2024 14:59:13 +0000
Subject: [PATCH 1/3] [mlir][vector] Update tests/patterns for vector.transpose
Pretty much all logic that we have today for lowering vector.transpose
assumes fixed length vectors (it's done via vector.shuffle that don't
support scalable vectors). This patch updates related tests and patterns
to capture and document that limitation more explicitly.
Note that `vector.transpose` is a valid operation in the context of
scalable vectors, but we are yet to implement the missing lowerings.
Most changes are implemented in the test file. Here's a summary:
* @transpose_nx8x2xf32 is renamed as @transpose_scalable and move near
other test using `lowering_strategy = "shuffle_1d"` (to avoid
duplicating TD sequences)
* tests specific to X86 (`avx2_lowering_strategy = true`) are moved to
a dedicated file (to seperate generic tests from target-specific
tests)
* `@transpose10_nx4xnx1xf32` duplicated `@transpose10_4xnx1xf32` and was
deleted (the latter is renamed as `@transpose10_4x1xf32_scalable` to
match its fixed-width counterpart: `@transpose10_4x1xf32`)
* The changes in LowerVectorTranspose.cpp are NFCs - they just make sure
that "scalable" vectors are filtered out at the very beginning
---
.../Transforms/LowerVectorTranspose.cpp | 1 +
.../Vector/vector-transpose-lowering.mlir | 561 ++----------------
2 files changed, 40 insertions(+), 522 deletions(-)
diff --git a/mlir/lib/Dialect/Vector/Transforms/LowerVectorTranspose.cpp b/mlir/lib/Dialect/Vector/Transforms/LowerVectorTranspose.cpp
index 792550dcfaf22..7011c478fefba 100644
--- a/mlir/lib/Dialect/Vector/Transforms/LowerVectorTranspose.cpp
+++ b/mlir/lib/Dialect/Vector/Transforms/LowerVectorTranspose.cpp
@@ -352,6 +352,7 @@ class TransposeOpLowering : public OpRewritePattern<vector::TransposeOp> {
return success();
}
+ // TODO: Add support for scalable vectors
if (inputType.isScalable())
return failure();
diff --git a/mlir/test/Dialect/Vector/vector-transpose-lowering.mlir b/mlir/test/Dialect/Vector/vector-transpose-lowering.mlir
index 628a8ce509599..219a72df52a19 100644
--- a/mlir/test/Dialect/Vector/vector-transpose-lowering.mlir
+++ b/mlir/test/Dialect/Vector/vector-transpose-lowering.mlir
@@ -110,6 +110,17 @@ func.func @transpose(%arg0: vector<2x4xf32>) -> vector<4x2xf32> {
return %0 : vector<4x2xf32>
}
+/// Scalable vectors are not supported
+
+// CHECK-LABEL: func @transpose_scalable
+// CHECK-NOT: vector.shuffle
+// CHECK-NOT: vector.shape_cast
+// CHECK: vector.transpose
+func.func @transpose_scalable(%arg0: vector<2x[4]xf32>) -> vector<[4]x2xf32> {
+ %0 = vector.transpose %arg0, [1, 0] : vector<2x[4]xf32> to vector<[4]x2xf32>
+ return %0 : vector<[4]x2xf32>
+}
+
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
@@ -132,502 +143,22 @@ func.func @transpose(%arg0: vector<2x4xf32>) -> vector<4x2xf32> {
return %0 : vector<4x2xf32>
}
+/// Scalable vectors are not supported
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
- %func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
- transform.apply_patterns to %func_op {
- transform.apply_patterns.vector.lower_transpose lowering_strategy = "flat_transpose"
- } : !transform.op<"func.func">
- transform.yield
- }
-}
-
-// -----
-
-// CHECK-LABEL: func @transpose4x8
-func.func @transpose4x8xf32(%arg0: vector<4x8xf32>) -> vector<8x4xf32> {
- // CHECK: vector.extract {{.*}}[0]
- // CHECK-NEXT: vector.extract {{.*}}[1]
- // CHECK-NEXT: vector.extract {{.*}}[2]
- // CHECK-NEXT: vector.extract {{.*}}[3]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.shape_cast {{.*}} vector<4x8xf32> to vector<32xf32>
- // CHECK-NEXT: vector.shape_cast {{.*}} vector<32xf32> to vector<8x4xf32>
- %0 = vector.transpose %arg0, [1, 0] : vector<4x8xf32> to vector<8x4xf32>
- return %0 : vector<8x4xf32>
-}
-
-// CHECK-LABEL: func @transpose021_1x4x8
-func.func @transpose021_1x4x8xf32(%arg0: vector<1x4x8xf32>) -> vector<1x8x4xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[0, 1]
- // CHECK-NEXT: vector.extract {{.*}}[0, 2]
- // CHECK-NEXT: vector.extract {{.*}}[0, 3]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.shape_cast {{.*}} vector<4x8xf32> to vector<32xf32>
- // CHECK-NEXT: vector.shape_cast {{.*}} vector<32xf32> to vector<1x8x4xf32>
- %0 = vector.transpose %arg0, [0, 2, 1] : vector<1x4x8xf32> to vector<1x8x4xf32>
- return %0 : vector<1x8x4xf32>
-}
-
-// CHECK-LABEL: func @transpose8x8
-func.func @transpose8x8xf32(%arg0: vector<8x8xf32>) -> vector<8x8xf32> {
- // CHECK: vector.extract {{.*}}[0]
- // CHECK-NEXT: vector.extract {{.*}}[1]
- // CHECK-NEXT: vector.extract {{.*}}[2]
- // CHECK-NEXT: vector.extract {{.*}}[3]
- // CHECK-NEXT: vector.extract {{.*}}[4]
- // CHECK-NEXT: vector.extract {{.*}}[5]
- // CHECK-NEXT: vector.extract {{.*}}[6]
- // CHECK-NEXT: vector.extract {{.*}}[7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- %0 = vector.transpose %arg0, [1, 0] : vector<8x8xf32> to vector<8x8xf32>
- return %0 : vector<8x8xf32>
-}
-
-// CHECK-LABEL: func @transpose021_1x8x8
-func.func @transpose021_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<1x8x8xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[0, 1]
- // CHECK-NEXT: vector.extract {{.*}}[0, 2]
- // CHECK-NEXT: vector.extract {{.*}}[0, 3]
- // CHECK-NEXT: vector.extract {{.*}}[0, 4]
- // CHECK-NEXT: vector.extract {{.*}}[0, 5]
- // CHECK-NEXT: vector.extract {{.*}}[0, 6]
- // CHECK-NEXT: vector.extract {{.*}}[0, 7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
- %0 = vector.transpose %arg0, [0, 2, 1] : vector<1x8x8xf32> to vector<1x8x8xf32>
- return %0 : vector<1x8x8xf32>
-}
-
-// CHECK-LABEL: func @transpose120_8x1x8
-func.func @transpose120_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<1x8x8xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[1, 0]
- // CHECK-NEXT: vector.extract {{.*}}[2, 0]
- // CHECK-NEXT: vector.extract {{.*}}[3, 0]
- // CHECK-NEXT: vector.extract {{.*}}[4, 0]
- // CHECK-NEXT: vector.extract {{.*}}[5, 0]
- // CHECK-NEXT: vector.extract {{.*}}[6, 0]
- // CHECK-NEXT: vector.extract {{.*}}[7, 0]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
- %0 = vector.transpose %arg0, [1, 2, 0] : vector<8x1x8xf32> to vector<1x8x8xf32>
- return %0 : vector<1x8x8xf32>
-}
-
-// CHECK-LABEL: func @transpose120_8x8x1
-func.func @transpose120_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<8x1x8xf32> {
- // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
- // CHECK-NEXT: vector.extract {{.*}}[0]
- // CHECK-NEXT: vector.extract {{.*}}[1]
- // CHECK-NEXT: vector.extract {{.*}}[2]
- // CHECK-NEXT: vector.extract {{.*}}[3]
- // CHECK-NEXT: vector.extract {{.*}}[4]
- // CHECK-NEXT: vector.extract {{.*}}[5]
- // CHECK-NEXT: vector.extract {{.*}}[6]
- // CHECK-NEXT: vector.extract {{.*}}[7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
- %0 = vector.transpose %arg0, [1, 2, 0] : vector<8x8x1xf32> to vector<8x1x8xf32>
- return %0 : vector<8x1x8xf32>
-}
-
-// CHECK-LABEL: func @transpose102_8x8x1
-func.func @transpose102_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<8x8x1xf32> {
- // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
- // CHECK-NEXT: vector.extract {{.*}}[0]
- // CHECK-NEXT: vector.extract {{.*}}[1]
- // CHECK-NEXT: vector.extract {{.*}}[2]
- // CHECK-NEXT: vector.extract {{.*}}[3]
- // CHECK-NEXT: vector.extract {{.*}}[4]
- // CHECK-NEXT: vector.extract {{.*}}[5]
- // CHECK-NEXT: vector.extract {{.*}}[6]
- // CHECK-NEXT: vector.extract {{.*}}[7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
- %0 = vector.transpose %arg0, [1, 0, 2] : vector<8x8x1xf32> to vector<8x8x1xf32>
- return %0 : vector<8x8x1xf32>
-}
-
-// CHECK-LABEL: func @transpose201_8x1x8
-func.func @transpose201_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<8x8x1xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[1, 0]
- // CHECK-NEXT: vector.extract {{.*}}[2, 0]
- // CHECK-NEXT: vector.extract {{.*}}[3, 0]
- // CHECK-NEXT: vector.extract {{.*}}[4, 0]
- // CHECK-NEXT: vector.extract {{.*}}[5, 0]
- // CHECK-NEXT: vector.extract {{.*}}[6, 0]
- // CHECK-NEXT: vector.extract {{.*}}[7, 0]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
- %0 = vector.transpose %arg0, [2, 0, 1] : vector<8x1x8xf32> to vector<8x8x1xf32>
- return %0 : vector<8x8x1xf32>
-}
-
-// CHECK-LABEL: func @transpose201_1x8x8
-func.func @transpose201_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<8x1x8xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[0, 1]
- // CHECK-NEXT: vector.extract {{.*}}[0, 2]
- // CHECK-NEXT: vector.extract {{.*}}[0, 3]
- // CHECK-NEXT: vector.extract {{.*}}[0, 4]
- // CHECK-NEXT: vector.extract {{.*}}[0, 5]
- // CHECK-NEXT: vector.extract {{.*}}[0, 6]
- // CHECK-NEXT: vector.extract {{.*}}[0, 7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
- %0 = vector.transpose %arg0, [2, 0, 1] : vector<1x8x8xf32> to vector<8x1x8xf32>
- return %0 : vector<8x1x8xf32>
-}
-
-// CHECK-LABEL: func @transpose210_8x1x8
-func.func @transpose210_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<8x1x8xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[1, 0]
- // CHECK-NEXT: vector.extract {{.*}}[2, 0]
- // CHECK-NEXT: vector.extract {{.*}}[3, 0]
- // CHECK-NEXT: vector.extract {{.*}}[4, 0]
- // CHECK-NEXT: vector.extract {{.*}}[5, 0]
- // CHECK-NEXT: vector.extract {{.*}}[6, 0]
- // CHECK-NEXT: vector.extract {{.*}}[7, 0]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
- %0 = vector.transpose %arg0, [2, 1, 0] : vector<8x1x8xf32> to vector<8x1x8xf32>
- return %0 : vector<8x1x8xf32>
-}
-
-// CHECK-LABEL: func @transpose210_8x8x1
-func.func @transpose210_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<1x8x8xf32> {
- // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
- // CHECK-NEXT: vector.extract {{.*}}[0]
- // CHECK-NEXT: vector.extract {{.*}}[1]
- // CHECK-NEXT: vector.extract {{.*}}[2]
- // CHECK-NEXT: vector.extract {{.*}}[3]
- // CHECK-NEXT: vector.extract {{.*}}[4]
- // CHECK-NEXT: vector.extract {{.*}}[5]
- // CHECK-NEXT: vector.extract {{.*}}[6]
- // CHECK-NEXT: vector.extract {{.*}}[7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
- %0 = vector.transpose %arg0, [2, 1, 0] : vector<8x8x1xf32> to vector<1x8x8xf32>
- return %0 : vector<1x8x8xf32>
-}
-
-// CHECK-LABEL: func @transpose210_1x8x8
-func.func @transpose210_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<8x8x1xf32> {
- // CHECK: vector.extract {{.*}}[0, 0]
- // CHECK-NEXT: vector.extract {{.*}}[0, 1]
- // CHECK-NEXT: vector.extract {{.*}}[0, 2]
- // CHECK-NEXT: vector.extract {{.*}}[0, 3]
- // CHECK-NEXT: vector.extract {{.*}}[0, 4]
- // CHECK-NEXT: vector.extract {{.*}}[0, 5]
- // CHECK-NEXT: vector.extract {{.*}}[0, 6]
- // CHECK-NEXT: vector.extract {{.*}}[0, 7]
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
- // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
- // CHECK-NEXT: vector.insert {{.*}}[0]
- // CHECK-NEXT: vector.insert {{.*}}[1]
- // CHECK-NEXT: vector.insert {{.*}}[2]
- // CHECK-NEXT: vector.insert {{.*}}[3]
- // CHECK-NEXT: vector.insert {{.*}}[4]
- // CHECK-NEXT: vector.insert {{.*}}[5]
- // CHECK-NEXT: vector.insert {{.*}}[6]
- // CHECK-NEXT: vector.insert {{.*}}[7]
- // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
- %0 = vector.transpose %arg0, [2, 1, 0] : vector<1x8x8xf32> to vector<8x8x1xf32>
- return %0 : vector<8x8x1xf32>
+// CHECK-LABEL: func @transpose_scalable(
+func.func @transpose_scalable(%arg0: vector<2x[4]xf32>) -> vector<[4]x2xf32> {
+ // CHECK-NOT: vector.shape_cast
+ // CHECK-NOT: vector.flat_transpose
+ // CHECK: vector.transpose
+ %0 = vector.transpose %arg0, [1, 0] : vector<2x[4]xf32> to vector<[4]x2xf32>
+ return %0 : vector<[4]x2xf32>
}
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
%func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
transform.apply_patterns to %func_op {
- transform.apply_patterns.vector.lower_transpose avx2_lowering_strategy = true
+ transform.apply_patterns.vector.lower_transpose lowering_strategy = "flat_transpose"
} : !transform.op<"func.func">
transform.yield
}
@@ -635,6 +166,7 @@ module attributes {transform.with_named_sequence} {
// -----
+// CHECK-LABEL: @transpose_shuffle16x16xf32(
func.func @transpose_shuffle16x16xf32(%arg0: vector<16x16xf32>) -> vector<16x16xf32> {
// CHECK: vector.shuffle {{.*}} [0, 16, 1, 17, 4, 20, 5, 21, 8, 24, 9, 25, 12, 28, 13, 29] : vector<16xf32>, vector<16xf32>
// CHECK: vector.shuffle {{.*}} [2, 18, 3, 19, 6, 22, 7, 23, 10, 26, 11, 27, 14, 30, 15, 31] : vector<16xf32>, vector<16xf32>
@@ -704,6 +236,14 @@ func.func @transpose_shuffle16x16xf32(%arg0: vector<16x16xf32>) -> vector<16x16x
return %0 : vector<16x16xf32>
}
+// CHECK-LABEL: @transpose_shuffle16x16xf32_scalable(
+func.func @transpose_shuffle16x16xf32_scalable(%arg0: vector<16x[16]xf32>) -> vector<[16]x16xf32> {
+ // CHECK-NOT: vector.shuffle
+ // CHECK: vector.transpose
+ %0 = vector.transpose %arg0, [1, 0] : vector<16x[16]xf32> to vector<[16]x16xf32>
+ return %0 : vector<[16]x16xf32>
+}
+
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
%func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
@@ -786,6 +326,14 @@ func.func @transpose021_shuffle16x16xf32(%arg0: vector<1x16x16xf32>) -> vector<1
return %0 : vector<1x16x16xf32>
}
+// CHECK-LABEL: func @transpose021_shuffle16x16xf32_scalable
+func.func @transpose021_shuffle16x16xf32_scalable(%arg0: vector<1x16x[16]xf32>) -> vector<1x[16]x16xf32> {
+ // CHECK-NOT: vector.shuffle
+ // CHECK: vector.transpose
+ %0 = vector.transpose %arg0, [0, 2, 1] : vector<1x16x[16]xf32> to vector<1x[16]x16xf32>
+ return %0 : vector<1x[16]x16xf32>
+}
+
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
%func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
@@ -830,23 +378,14 @@ func.func @transpose10_1xnx4xf32(%arg0: vector<1x[4]xf32>) -> vector<[4]x1xf32>
/// Scalable unit dim should not be lowered to shape_cast.
-// CHECK-LABEL: func @transpose10_4xnx1xf32
-func.func @transpose10_4xnx1xf32(%arg0: vector<4x[1]xf32>) -> vector<[1]x4xf32> {
+// CHECK-LABEL: func @transpose10_4x1xf32_scalable
+func.func @transpose10_4x1xf32_scalable(%arg0: vector<4x[1]xf32>) -> vector<[1]x4xf32> {
// CHECK-NOT: vector.shape_cast
// CHECK: vector.transpose %{{.*}} : vector<4x[1]xf32> to vector<[1]x4xf32>
%0 = vector.transpose %arg0, [1, 0] : vector<4x[1]xf32> to vector<[1]x4xf32>
return %0 : vector<[1]x4xf32>
}
-// CHECK-LABEL: func @transpose10_nx4xnx1xf32
-func.func @transpose10_nx4xnx1xf32(%arg0: vector<4x[1]xf32>) -> vector<[1]x4xf32> {
- // CHECK-NOT: vector.shape_cast
- // CHECK: vector.transpose %{{.*}} : vector<4x[1]xf32> to vector<[1]x4xf32>
- %0 = vector.transpose %arg0, [1, 0] : vector<4x[1]xf32> to vector<[1]x4xf32>
-
- return %0 : vector<[1]x4xf32>
-}
-
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
%func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
@@ -856,25 +395,3 @@ module attributes {transform.with_named_sequence} {
transform.yield
}
}
-
-// -----
-
-// Scalable transposes should not be lowered to vector.shuffle.
-
-// CHECK-LABEL: func @transpose_nx8x2xf32
-func.func @transpose_nx8x2xf32(%arg0: vector<[8]x2xf32>) -> vector<2x[8]xf32> {
- // CHECK-NOT: vector.shuffle
- // CHECK: vector.transpose %{{.*}} : vector<[8]x2xf32> to vector<2x[8]xf32>
- %0 = vector.transpose %arg0, [1, 0] : vector<[8]x2xf32> to vector<2x[8]xf32>
- return %0 : vector<2x[8]xf32>
-}
-
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
- %func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
- transform.apply_patterns to %func_op {
- transform.apply_patterns.vector.lower_transpose lowering_strategy = "shuffle_1d"
- } : !transform.op<"func.func">
- transform.yield
- }
-}
>From 9ba1222c528a5cc2644e1a3721040aa1c0ba04db Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Wed, 8 May 2024 13:50:17 +0000
Subject: [PATCH 2/3] fixup! [mlir][vector] Update tests/patterns for
vector.transpose
Add missing file
---
.../CPU/X86/vector-transpose-lowering.mlir | 492 ++++++++++++++++++
1 file changed, 492 insertions(+)
create mode 100644 mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
diff --git a/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir b/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
new file mode 100644
index 0000000000000..9e16f3a082376
--- /dev/null
+++ b/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
@@ -0,0 +1,492 @@
+// RUN: mlir-opt %s --transform-interpreter --split-input-file | FileCheck %s
+
+// NOTE: This file tests lowering from the X86 dialect. Since X86 does not
+// support scalable vectors, all examples in this file use fixed-width vectors.
+
+// CHECK-LABEL: func @transpose4x8
+func.func @transpose4x8xf32(%arg0: vector<4x8xf32>) -> vector<8x4xf32> {
+ // CHECK: vector.extract {{.*}}[0]
+ // CHECK-NEXT: vector.extract {{.*}}[1]
+ // CHECK-NEXT: vector.extract {{.*}}[2]
+ // CHECK-NEXT: vector.extract {{.*}}[3]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.shape_cast {{.*}} vector<4x8xf32> to vector<32xf32>
+ // CHECK-NEXT: vector.shape_cast {{.*}} vector<32xf32> to vector<8x4xf32>
+ %0 = vector.transpose %arg0, [1, 0] : vector<4x8xf32> to vector<8x4xf32>
+ return %0 : vector<8x4xf32>
+}
+
+// CHECK-LABEL: func @transpose021_1x4x8
+func.func @transpose021_1x4x8xf32(%arg0: vector<1x4x8xf32>) -> vector<1x8x4xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 1]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 2]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 3]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 8, 9, 4, 5, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 3, 10, 11, 6, 7, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.shape_cast {{.*}} vector<4x8xf32> to vector<32xf32>
+ // CHECK-NEXT: vector.shape_cast {{.*}} vector<32xf32> to vector<1x8x4xf32>
+ %0 = vector.transpose %arg0, [0, 2, 1] : vector<1x4x8xf32> to vector<1x8x4xf32>
+ return %0 : vector<1x8x4xf32>
+}
+
+// CHECK-LABEL: func @transpose8x8
+func.func @transpose8x8xf32(%arg0: vector<8x8xf32>) -> vector<8x8xf32> {
+ // CHECK: vector.extract {{.*}}[0]
+ // CHECK-NEXT: vector.extract {{.*}}[1]
+ // CHECK-NEXT: vector.extract {{.*}}[2]
+ // CHECK-NEXT: vector.extract {{.*}}[3]
+ // CHECK-NEXT: vector.extract {{.*}}[4]
+ // CHECK-NEXT: vector.extract {{.*}}[5]
+ // CHECK-NEXT: vector.extract {{.*}}[6]
+ // CHECK-NEXT: vector.extract {{.*}}[7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ %0 = vector.transpose %arg0, [1, 0] : vector<8x8xf32> to vector<8x8xf32>
+ return %0 : vector<8x8xf32>
+}
+
+// CHECK-LABEL: func @transpose021_1x8x8
+func.func @transpose021_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<1x8x8xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 1]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 2]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 3]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 4]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 5]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 6]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
+ %0 = vector.transpose %arg0, [0, 2, 1] : vector<1x8x8xf32> to vector<1x8x8xf32>
+ return %0 : vector<1x8x8xf32>
+}
+
+// CHECK-LABEL: func @transpose120_8x1x8
+func.func @transpose120_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<1x8x8xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[1, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[2, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[3, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[4, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[5, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[6, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[7, 0]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
+ %0 = vector.transpose %arg0, [1, 2, 0] : vector<8x1x8xf32> to vector<1x8x8xf32>
+ return %0 : vector<1x8x8xf32>
+}
+
+// CHECK-LABEL: func @transpose120_8x8x1
+func.func @transpose120_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<8x1x8xf32> {
+ // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
+ // CHECK-NEXT: vector.extract {{.*}}[0]
+ // CHECK-NEXT: vector.extract {{.*}}[1]
+ // CHECK-NEXT: vector.extract {{.*}}[2]
+ // CHECK-NEXT: vector.extract {{.*}}[3]
+ // CHECK-NEXT: vector.extract {{.*}}[4]
+ // CHECK-NEXT: vector.extract {{.*}}[5]
+ // CHECK-NEXT: vector.extract {{.*}}[6]
+ // CHECK-NEXT: vector.extract {{.*}}[7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
+ %0 = vector.transpose %arg0, [1, 2, 0] : vector<8x8x1xf32> to vector<8x1x8xf32>
+ return %0 : vector<8x1x8xf32>
+}
+
+// CHECK-LABEL: func @transpose102_8x8x1
+func.func @transpose102_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<8x8x1xf32> {
+ // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
+ // CHECK-NEXT: vector.extract {{.*}}[0]
+ // CHECK-NEXT: vector.extract {{.*}}[1]
+ // CHECK-NEXT: vector.extract {{.*}}[2]
+ // CHECK-NEXT: vector.extract {{.*}}[3]
+ // CHECK-NEXT: vector.extract {{.*}}[4]
+ // CHECK-NEXT: vector.extract {{.*}}[5]
+ // CHECK-NEXT: vector.extract {{.*}}[6]
+ // CHECK-NEXT: vector.extract {{.*}}[7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
+ %0 = vector.transpose %arg0, [1, 0, 2] : vector<8x8x1xf32> to vector<8x8x1xf32>
+ return %0 : vector<8x8x1xf32>
+}
+
+// CHECK-LABEL: func @transpose201_8x1x8
+func.func @transpose201_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<8x8x1xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[1, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[2, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[3, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[4, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[5, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[6, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[7, 0]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
+ %0 = vector.transpose %arg0, [2, 0, 1] : vector<8x1x8xf32> to vector<8x8x1xf32>
+ return %0 : vector<8x8x1xf32>
+}
+
+// CHECK-LABEL: func @transpose201_1x8x8
+func.func @transpose201_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<8x1x8xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 1]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 2]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 3]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 4]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 5]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 6]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
+ %0 = vector.transpose %arg0, [2, 0, 1] : vector<1x8x8xf32> to vector<8x1x8xf32>
+ return %0 : vector<8x1x8xf32>
+}
+
+// CHECK-LABEL: func @transpose210_8x1x8
+func.func @transpose210_8x1x8xf32(%arg0: vector<8x1x8xf32>) -> vector<8x1x8xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[1, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[2, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[3, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[4, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[5, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[6, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[7, 0]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x1x8xf32>
+ %0 = vector.transpose %arg0, [2, 1, 0] : vector<8x1x8xf32> to vector<8x1x8xf32>
+ return %0 : vector<8x1x8xf32>
+}
+
+// CHECK-LABEL: func @transpose210_8x8x1
+func.func @transpose210_8x8x1xf32(%arg0: vector<8x8x1xf32>) -> vector<1x8x8xf32> {
+ // CHECK: vector.shape_cast %{{.*}} : vector<8x8x1xf32> to vector<8x8xf32>
+ // CHECK-NEXT: vector.extract {{.*}}[0]
+ // CHECK-NEXT: vector.extract {{.*}}[1]
+ // CHECK-NEXT: vector.extract {{.*}}[2]
+ // CHECK-NEXT: vector.extract {{.*}}[3]
+ // CHECK-NEXT: vector.extract {{.*}}[4]
+ // CHECK-NEXT: vector.extract {{.*}}[5]
+ // CHECK-NEXT: vector.extract {{.*}}[6]
+ // CHECK-NEXT: vector.extract {{.*}}[7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<1x8x8xf32>
+ %0 = vector.transpose %arg0, [2, 1, 0] : vector<8x8x1xf32> to vector<1x8x8xf32>
+ return %0 : vector<1x8x8xf32>
+}
+
+// CHECK-LABEL: func @transpose210_1x8x8
+func.func @transpose210_1x8x8xf32(%arg0: vector<1x8x8xf32>) -> vector<8x8x1xf32> {
+ // CHECK: vector.extract {{.*}}[0, 0]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 1]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 2]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 3]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 4]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 5]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 6]
+ // CHECK-NEXT: vector.extract {{.*}}[0, 7]
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [0, 8, 1, 9, 4, 12, 5, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.shuffle {{.*}} [2, 10, 3, 11, 6, 14, 7, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [2, 3, 8, 9, 6, 7, 12, 13] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0xcc", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-NEXT: llvm.inline_asm asm_dialect = intel "vblendps $0, $1, $2, 0x33", "=x,x,x" {{.*}} : (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [0, 1, 2, 3, 8, 9, 10, 11] : vector<8xf32>, vector<8xf32>
+ // CHECK-COUNT-4: vector.shuffle {{.*}} [4, 5, 6, 7, 12, 13, 14, 15] : vector<8xf32>, vector<8xf32>
+ // CHECK-NEXT: vector.insert {{.*}}[0]
+ // CHECK-NEXT: vector.insert {{.*}}[1]
+ // CHECK-NEXT: vector.insert {{.*}}[2]
+ // CHECK-NEXT: vector.insert {{.*}}[3]
+ // CHECK-NEXT: vector.insert {{.*}}[4]
+ // CHECK-NEXT: vector.insert {{.*}}[5]
+ // CHECK-NEXT: vector.insert {{.*}}[6]
+ // CHECK-NEXT: vector.insert {{.*}}[7]
+ // CHECK-NEXT: vector.shape_cast %{{.*}} : vector<8x8xf32> to vector<8x8x1xf32>
+ %0 = vector.transpose %arg0, [2, 1, 0] : vector<1x8x8xf32> to vector<8x8x1xf32>
+ return %0 : vector<8x8x1xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+ transform.named_sequence @__transform_main(%root : !transform.any_op {transform.readonly}) {
+ %func_op = transform.structured.match ops{["func.func"]} in %root : (!transform.any_op) -> !transform.op<"func.func">
+ transform.apply_patterns to %func_op {
+ transform.apply_patterns.vector.lower_transpose avx2_lowering_strategy = true
+ } : !transform.op<"func.func">
+ transform.yield
+ }
+}
>From e27d11cf73dd589e2a1df5af9ab2d0a40606226d Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Thu, 9 May 2024 13:52:28 +0000
Subject: [PATCH 3/3] fixup! [mlir][vector] Update tests/patterns for
vector.transpose
fix comments
---
.../Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir b/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
index 9e16f3a082376..ae2b5393ca449 100644
--- a/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
+++ b/mlir/test/Dialect/Vector/CPU/X86/vector-transpose-lowering.mlir
@@ -1,7 +1,8 @@
// RUN: mlir-opt %s --transform-interpreter --split-input-file | FileCheck %s
-// NOTE: This file tests lowering from the X86 dialect. Since X86 does not
-// support scalable vectors, all examples in this file use fixed-width vectors.
+// NOTE: This file tests lowerings that are implemented in the X86Vector
+// dialect. Since X86 does not support scalable vectors, all examples in this
+// file use fixed-width vectors.
// CHECK-LABEL: func @transpose4x8
func.func @transpose4x8xf32(%arg0: vector<4x8xf32>) -> vector<8x4xf32> {
More information about the Mlir-commits
mailing list