[Mlir-commits] [mlir] [MLIR][XeGPU] Add unroll patterns and blocking pass for XeGPU [2/N] (PR #140163)

[Chao Chen]

================
@@ -0,0 +1,205 @@
+// RUN: mlir-opt --xegpu-blocking -split-input-file %s | FileCheck %s
+
+#a = #xegpu.layout<inst_data = [8, 16], lane_layout = [1, 16], lane_data = [8, 1]>
+#b = #xegpu.layout<inst_data = [16, 16], lane_layout = [1, 16], lane_data = [16, 1]>
+#c = #xegpu.layout<inst_data = [8, 16], lane_layout = [1, 16], lane_data = [8, 1]>
+gpu.module @test_kernel {
+  gpu.func @test_gemm(%A: memref<1024x1024xf16>, %B: memref<1024x1024xf16>, %C: memref<1024x1024xf32>) {
----------------
chencha3 wrote:

fixed

https://github.com/llvm/llvm-project/pull/140163