[Mlir-commits] [mlir] Revert "[MLIR][XeGPU] Support vector.contract transpose_a/transpose_b via 'vector-to-gpu' patterns" (PR #184824)

[Dmitry Chigarev]

https://github.com/dchigarev created https://github.com/llvm/llvm-project/pull/184824

Reverts llvm/llvm-project#182885

>From 269f31d29192d27682408804083224c1c9631206 Mon Sep 17 00:00:00 2001
From: Dmitry Chigarev <dmitry.chigarev at intel.com>
Date: Thu, 5 Mar 2026 17:45:26 +0100
Subject: [PATCH] =?UTF-8?q?Revert=20"[MLIR][XeGPU]=20Support=20vector.cont?=
 =?UTF-8?q?ract=20transpose=5Fa/transpose=5Fb=20via=20've=E2=80=A6"?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit a9fb8b06224aec404a2ec9bf101c40e36f46426c.
---
 .../VectorToXeGPU/VectorToXeGPU.cpp           |  2 -
 .../VectorToXeGPU/contract-to-xegpu.mlir      | 86 ++++++++-----------
 2 files changed, 36 insertions(+), 52 deletions(-)

diff --git a/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp b/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
index bbb6340f14c51..0eac704779e7d 100644
--- a/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
+++ b/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
@@ -11,7 +11,6 @@
 //===----------------------------------------------------------------------===//
 
 #include "mlir/Conversion/VectorToXeGPU/VectorToXeGPU.h"
-#include "mlir/Conversion/VectorToGPU/VectorToGPU.h"
 
 #include "mlir/Dialect/Arith/IR/Arith.h"
 #include "mlir/Dialect/MemRef/IR/MemRef.h"
@@ -865,7 +864,6 @@ struct ConvertVectorToXeGPUPass
   void runOnOperation() override {
     RewritePatternSet patterns(&getContext());
     populateVectorToXeGPUConversionPatterns(patterns);
-    populatePrepareVectorToMMAPatterns(patterns);
     if (failed(applyPatternsGreedily(getOperation(), std::move(patterns))))
       return signalPassFailure();
   }
diff --git a/mlir/test/Conversion/VectorToXeGPU/contract-to-xegpu.mlir b/mlir/test/Conversion/VectorToXeGPU/contract-to-xegpu.mlir
index 292e4ff882000..38bda39d3aca2 100644
--- a/mlir/test/Conversion/VectorToXeGPU/contract-to-xegpu.mlir
+++ b/mlir/test/Conversion/VectorToXeGPU/contract-to-xegpu.mlir
@@ -76,56 +76,6 @@ func.func @dpas_large_dims(%lhs: vector<128x512xf16>, %rhs: vector<512x256xf16>,
 
 // -----
 
-#map = affine_map<(d0, d1, d2) -> (d2, d0)>
-#map1 = affine_map<(d0, d1, d2) -> (d2, d1)>
-#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
-func.func @gemm_transpose_a(%lhs: vector<16x8xf16>, %rhs: vector<16x16xf16>,
-    %acc: vector<8x16xf32>) -> vector<8x16xf32> {
-  %3 = vector.contract
-    {indexing_maps = [#map, #map1, #map2],
-    iterator_types = ["parallel", "parallel", "reduction"],
-    kind = #vector.kind<add>} %lhs, %rhs, %acc
-    : vector<16x8xf16>, vector<16x16xf16> into vector<8x16xf32>
-  return %3 : vector<8x16xf32>
-}
-
-// CHECK-LABEL: @gemm_transpose_a(
-// CHECK-SAME:  %[[LHS:.+]]: vector<16x8xf16>,
-// CHECK-SAME:  %[[RHS:.+]]: vector<16x16xf16>,
-// CHECK-SAME:  %[[ACC:.+]]: vector<8x16xf32>
-// CHECK:       %[[LHS_TRANSPOSED:.+]] = vector.transpose %[[LHS]], [1, 0] : vector<16x8xf16> to vector<8x16xf16>
-// CHECK:       %[[DPAS:.+]] = xegpu.dpas
-// CHECK-SAME:    %[[LHS_TRANSPOSED]], %[[RHS]], %[[ACC]]
-// CHECK-SAME:    {{.*}}-> vector<8x16xf32>
-// CHECK:       return %[[DPAS]]
-
-// -----
-
-#map = affine_map<(d0, d1, d2) -> (d0, d2)>
-#map1 = affine_map<(d0, d1, d2) -> (d1, d2)>
-#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
-func.func @gemm_transpose_b(%lhs: vector<8x16xf16>, %rhs: vector<16x16xf16>,
-    %acc: vector<8x16xf32>) -> vector<8x16xf32> {
-  %3 = vector.contract
-    {indexing_maps = [#map, #map1, #map2],
-    iterator_types = ["parallel", "parallel", "reduction"],
-    kind = #vector.kind<add>} %lhs, %rhs, %acc
-    : vector<8x16xf16>, vector<16x16xf16> into vector<8x16xf32>
-  return %3 : vector<8x16xf32>
-}
-
-// CHECK-LABEL: @gemm_transpose_b(
-// CHECK-SAME:  %[[LHS:.+]]: vector<8x16xf16>,
-// CHECK-SAME:  %[[RHS:.+]]: vector<16x16xf16>,
-// CHECK-SAME:  %[[ACC:.+]]: vector<8x16xf32>
-// CHECK:       %[[RHS_TRANSPOSED:.+]] = vector.transpose %[[RHS]], [1, 0] : vector<16x16xf16> to vector<16x16xf16>
-// CHECK:       %[[DPAS:.+]] = xegpu.dpas
-// CHECK-SAME:    %[[LHS]], %[[RHS_TRANSPOSED]], %[[ACC]]
-// CHECK-SAME:    {{.*}}-> vector<8x16xf32>
-// CHECK:       return %[[DPAS]]
-
-// -----
-
 // For simplicity, only plain data layouts are currently supported.
 // VNNI packing is applied later as a separate lowering step.
 
@@ -180,3 +130,39 @@ func.func @negative_accumulator_shape(%lhs: vector<8x16xf16>, %rhs: vector<16x16
 
 // CHECK-LABEL: @negative_accumulator_shape(
 // CHECK:       vector.contract
+
+// -----
+
+#map = affine_map<(d0, d1, d2) -> (d2, d0)>
+#map1 = affine_map<(d0, d1, d2) -> (d2, d1)>
+#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
+func.func @negative_gemm_transpose_a(%lhs: vector<16x8xf16>, %rhs: vector<16x16xf16>,
+    %acc: vector<8x16xf32>) -> vector<8x16xf32> {
+  %3 = vector.contract
+    {indexing_maps = [#map, #map1, #map2],
+    iterator_types = ["parallel", "parallel", "reduction"],
+    kind = #vector.kind<add>} %lhs, %rhs, %acc
+    : vector<16x8xf16>, vector<16x16xf16> into vector<8x16xf32>
+  return %3 : vector<8x16xf32>
+}
+
+// CHECK-LABEL: @negative_gemm_transpose_a(
+// CHECK:       vector.contract
+
+// -----
+
+#map = affine_map<(d0, d1, d2) -> (d0, d2)>
+#map1 = affine_map<(d0, d1, d2) -> (d1, d2)>
+#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
+func.func @negative_gemm_transpose_b(%lhs: vector<8x16xf16>, %rhs: vector<16x16xf16>,
+    %acc: vector<8x16xf32>) -> vector<8x16xf32> {
+  %3 = vector.contract
+    {indexing_maps = [#map, #map1, #map2],
+    iterator_types = ["parallel", "parallel", "reduction"],
+    kind = #vector.kind<add>} %lhs, %rhs, %acc
+    : vector<8x16xf16>, vector<16x16xf16> into vector<8x16xf32>
+  return %3 : vector<8x16xf32>
+}
+
+// CHECK-LABEL: @negative_gemm_transpose_b(
+// CHECK:       vector.contract