[Mlir-commits] [mlir] [MLIR][XeGPU]Enhance Pack/Unpack for XeGPUUnroll (PR #163459)

[Jianhui Li]

================
@@ -682,3 +682,46 @@ gpu.module @test_kernel {
     gpu.return
   }
 }
+
+// -----
+gpu.module @test_kernel {
+  // CHECK-LABEL: load_gather
+  // CHECK-COUNT-2: xegpu.load  {{.*}}[{{.*}}], {{.*}} <{chunk_size = 1 : i64, l1_hint = #xegpu.cache_hint<cached>}> : ui64, vector<16xindex>, vector<16xi1> -> vector<16xf32>
+  gpu.func @load_gather(%src: ui64) -> vector<1x1x32xf32> {
+      %cst = arith.constant dense<[[
+      [0,   8,  16,  24,  32,  40,  48,  56,
+      64,  72,  80,  88,  96, 104, 112, 120,
+      128, 136, 144, 152, 160, 168, 176, 184,
+      192, 200, 208, 216, 224, 232, 240, 248]
+      ]]> : vector<1x1x32xindex>
+
+      %mask = arith.constant dense<true> : vector<1x1x32xi1>
+      %ld = xegpu.load %src[%cst], %mask {chunk_size = 1, layout_result_0 = #xegpu.layout<inst_data = [1, 1, 16]>, l1_hint = #xegpu.cache_hint<cached>} : ui64, vector<1x1x32xindex>, vector<1x1x32xi1> -> vector<1x1x32xf32>
----------------
Jianhui-Li wrote:

please check how the input is being extracted from %mask and %cst (the additional shape cast)?

why not add a test with inst_data attached to %cst and %mask and see how they are unrolled all together? 

https://github.com/llvm/llvm-project/pull/163459