================
@@ -0,0 +1,17 @@
+; RUN: llc -verify-machineinstrs -O0 -mtriple=spirv-unknown-unknown %s -o - |
FileCheck %s
+; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv-unknown-unknown %s -o -
-filetype=obj | spirv-val %}
+
+; CHECK-DAG: %[[#bool:]] = OpTypeBool
+; CHECK-DAG: %[[#uint:]] = OpTypeInt 32 0
+; CHECK-DAG: %[[#scope:]] = OpConstant %[[#uint]] 3
+
+; CHECK-LABEL: Begin function test_wave_any
+define i1 @test_wave_any(i1 %p1) {
+entry:
+; CHECK: %[[#param:]] = OpFunctionParameter %[[#bool]]
+; CHECK: %{{.+}} = OpGroupNonUniformAny %[[#bool]] %[[#scope]] %[[#param]]
+ %ret = call i1 @llvm.spv.wave.any(i1 %p1)
----------------
V-FEXrt wrote:
This [similar
commit](https://github.com/llvm/llvm-project/pull/111010/commits/484b2089ae9f0a0fae09b6d68b70171f1007bade#diff-bac84b1c33bc0aee1edd39550243c6e3c5606b6b8538b2f424a55ce3c9977244)
(from which I was basing my changes) seems to have intentionally removed the
convergence intrinsics generated by the frontend. Should we mirror that or
should convergence be added back in to that test?
cc @inbelic
https://github.com/llvm/llvm-project/pull/115902
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
