[Mlir-commits] [mlir] [MLIR][XeGPU] fix load/store/prefetch op offset verifier (PR #166137)

[llvmlistbot at llvm.org]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mlir-gpu

Author: Tuomas Kärnä (tkarna)

<details>
<summary>Changes</summary>

The verifier of `xegpu.{load/store/prefetch}_nd` op verifier fails if `offset` a mix of static and dynamic values, e.g. `offset = [0, %c0]`. In this case the length of dynamic offsets is 1 and the check `offsetSize != tDescRank` (=2) fails. Instead, we should check the length of `getMixedOffsets()`.

---
Full diff: https://github.com/llvm/llvm-project/pull/166137.diff


2 Files Affected:

- (modified) mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp (+6-15) 
- (modified) mlir/test/Dialect/XeGPU/ops.mlir (+9) 


``````````diff
diff --git a/mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp b/mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp
index abd12e2e69ac0..0bfc8a12ea552 100644
--- a/mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp
+++ b/mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp
@@ -472,11 +472,8 @@ LogicalResult PrefetchNdOp::verify() {
     return emitOpError("invalid l3_hint: ") << getL3HintAttr();
 
   int64_t tDescRank = tdescTy.getRank();
-  int64_t offsetSize = static_cast<int64_t>(getOffsets().size());
-  int64_t constOffsetSize =
-      getConstOffsetsAttr() ? getConstOffsetsAttr().size() : 0;
-  if (((offsetSize != 0) && (offsetSize != tDescRank)) ||
-      ((constOffsetSize != 0) && (constOffsetSize != tDescRank)))
+  int64_t offsetSize = getMixedOffsets().size();
+  if (offsetSize != 0 && offsetSize != tDescRank)
     return emitOpError(
         "Mismatched ranks between offsets and tensor descriptor");
 
@@ -597,11 +594,8 @@ LogicalResult LoadNdOp::verify() {
                          << tdescTy;
 
   int64_t tDescRank = tdescTy.getRank();
-  int64_t offsetSize = static_cast<int64_t>(getOffsets().size());
-  int64_t constOffsetSize =
-      getConstOffsetsAttr() ? getConstOffsetsAttr().size() : 0;
-  if (((offsetSize != 0) && (offsetSize != tDescRank)) ||
-      ((constOffsetSize != 0) && (constOffsetSize != tDescRank)))
+  int64_t offsetSize = getMixedOffsets().size();
+  if (offsetSize != 0 && offsetSize != tDescRank)
     return emitOpError(
         "Mismatched ranks between offsets and tensor descriptor");
 
@@ -691,11 +685,8 @@ LogicalResult StoreNdOp::verify() {
                          << dstTy;
 
   int64_t tDescRank = dstTy.getRank();
-  int64_t offsetSize = static_cast<int64_t>(getOffsets().size());
-  int64_t constOffsetSize =
-      getConstOffsetsAttr() ? getConstOffsetsAttr().size() : 0;
-  if (((offsetSize != 0) && (offsetSize != tDescRank)) ||
-      ((constOffsetSize != 0) && (constOffsetSize != tDescRank)))
+  int64_t offsetSize = getMixedOffsets().size();
+  if (offsetSize != 0 && offsetSize != tDescRank)
     return emitOpError(
         "Mismatched ranks between offsets and tensor descriptor");
 
diff --git a/mlir/test/Dialect/XeGPU/ops.mlir b/mlir/test/Dialect/XeGPU/ops.mlir
index 0a10f6814ae96..9b3829664108d 100644
--- a/mlir/test/Dialect/XeGPU/ops.mlir
+++ b/mlir/test/Dialect/XeGPU/ops.mlir
@@ -278,6 +278,15 @@ gpu.func @subgroup_load_nd_offset_1(%src: memref<24x32xf32>, %x : index, %y : in
   gpu.return
 }
 
+// CHECK: func @subgroup_load_nd_offset_2(%[[arg0:.*]]: memref<24x32xf32>, %arg1: index) {
+gpu.func @subgroup_load_nd_offset_2(%src: memref<24x32xf32>, %x : index) {
+  // CHECK: %[[R0:.*]] = xegpu.create_nd_tdesc %arg0 : memref<24x32xf32> -> !xegpu.tensor_desc<16x8xf32>
+  %1 = xegpu.create_nd_tdesc %src : memref<24x32xf32> -> !xegpu.tensor_desc<16x8xf32>
+  // CHECK: %[[R1:.*]] = xegpu.load_nd %[[R0]][%arg1, 0] <{l1_hint = #xegpu.cache_hint<cached>, l2_hint = #xegpu.cache_hint<uncached>, transpose = array<i64: 1, 0>}> : !xegpu.tensor_desc<16x8xf32> -> vector<8x16xf32>
+  %2 = xegpu.load_nd %1[%x, 0] <{l1_hint = #xegpu.cache_hint<cached>, l2_hint = #xegpu.cache_hint<uncached>, transpose = array<i64: 1, 0>}> : !xegpu.tensor_desc<16x8xf32> -> vector<8x16xf32>
+  gpu.return
+}
+
 // CHECK: func @simt_load_nd_8(%[[arg0:.*]]: memref<24x32xf32>) {
 gpu.func @simt_load_nd_8(%src: memref<24x32xf32>) {
   // CHECK: %[[R0:.*]] = xegpu.create_nd_tdesc %arg0[0, 0] : memref<24x32xf32> -> !xegpu.tensor_desc<16x8xf32>

``````````

</details>


https://github.com/llvm/llvm-project/pull/166137