[Mlir-commits] [mlir] [mlir][AMDGPU] Rename gfx1250 packed extension ops, change firstScale… (PR #170718)

[Erick Ochoa Lopez]

================
@@ -1627,34 +1628,35 @@ LogicalResult ExtPackedFp8OpLowering::matchAndRewrite(
   return success();
 }
 
-int32_t getScaleSel(int32_t blockSize, unsigned bitWidth,
-                    int32_t firstScaleLane, int32_t firstScaleByte) {
-  // When lowering amdgpu.scaled_ext_packed816 to rocdl.cvt.scale.pk*.f*.f*
-  // operations, the attributes blockSize, sourceType, firstScaleLane and
+int32_t getScaleSel(int32_t blockSize, unsigned bitWidth, int32_t scaleWaveHalf,
+                    int32_t firstScaleByte) {
+  // When lowering amdgpu.scaled_ext_packed_matrix to rocdl.cvt.scale.pk*.f*.f*
+  // operations, the attributes blockSize, sourceType, scaleWaveHalf, and
   // firstScaleByte are merged into a single attribute scaleSel. This is how
-  // those values are merged together.
+  // those values are merged together. (Note: scaleWaveHalf isn't a high-level
+  // attribute but is derifed from firstScaleLane).
   assert(llvm::is_contained({16, 32}, blockSize));
   assert(llvm::is_contained(llvm::ArrayRef<unsigned>{4, 6, 8}, bitWidth));
 
-  const bool is_fp8 = bitWidth == 8;
-  const bool is_block_16 = blockSize == 16;
+  const bool isFp8 = bitWidth == 8;
+  const bool isBlock16 = blockSize == 16;
 
-  if (!is_fp8) {
-    int bit_0 = is_block_16;
+  if (!isFp8) {
+    int32_t bit0 = isBlock16;
     assert(llvm::is_contained({0, 1, 2}, firstScaleByte));
-    int bit_1 = (firstScaleByte == 2) << 1;
+    int32_t bit1 = (firstScaleByte == 2) << 1;
     assert(llvm::is_contained({0, 1}, firstScaleLane));
-    int bit_2 = firstScaleLane << 2;
-    return bit_2 | bit_1 | bit_0;
+    int32_t bit2 = scaleWaveHalf << 2;
+    return bit2 | bit1 | bit0;
   }
 
-  int bit_0 = is_block_16;
+  int32_t bit0 = isBlock16;
   // firstScaleByte is guaranteed to be defined by two bits.
   assert(llvm::is_contained({0, 1, 2, 3}, firstScaleByte));
-  int bit_2_and_1 = firstScaleByte << 1;
+  int32_t bits2and1 = firstScaleByte << 1;
   assert(llvm::is_contained({0, 1}, firstScaleLane));
----------------
amd-eochoalo wrote:

```suggestion
  assert(llvm::is_contained({0, 1}, scaleWaveHalf));
```

https://github.com/llvm/llvm-project/pull/170718