[Mlir-commits] [mlir] [mlir][ArithToAMDGPU] Use native packing support (PR #150342)
Krzysztof Drewniak
llvmlistbot at llvm.org
Thu Jul 24 09:01:19 PDT 2025
================
@@ -449,7 +449,8 @@ LogicalResult
ScalingExtFRewritePattern::matchAndRewrite(arith::ScalingExtFOp op,
PatternRewriter &rewriter) const {
Location loc = op.getLoc();
- constexpr int64_t opWidth = 2;
+ constexpr int64_t opOutWidth = 2;
+ constexpr int64_t opInWidth = 8;
----------------
krzysz00 wrote:
... Right, yeah, `opInWidth` is data type dependent, good catch
https://github.com/llvm/llvm-project/pull/150342
More information about the Mlir-commits
mailing list