================
@@ -0,0 +1,35 @@
+// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \
+// RUN: dxil-pc-shadermodel6.6-library %s -emit-llvm -disable-llvm-passes -o
- | \
+// RUN: FileCheck %s --check-prefixes=CHECK,DXCHECK
+
+// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \
+// RUN: spirv-pc-vulkan-library %s -emit-llvm -disable-llvm-passes -o - | \
+// RUN: FileCheck %s --check-prefixes=CHECK,SPVCHECK
+
+// Test basic lowering of HLSL InterlockedCompareStoreFloatBitwise to `cmpxchg
+// monotonic`. `cmpxchg` takes an integer, so the float arguments become their
+// bit patterns first. The operation reports nothing, so the `cmpxchg` result
+// stays unused.
+
+groupshared float gs_f32;
+
+// CHECK-LABEL: define {{.*}}void @{{.*}}test_float
+// CHECK: [[CMP:%.*]] = bitcast float %{{.*}} to i32
+// CHECK-NEXT: [[VAL:%.*]] = bitcast float %{{.*}} to i32
+// DXCHECK-NEXT: cmpxchg ptr addrspace(3) {{.*}}@gs_f32{{.*}}, i32 [[CMP]],
i32 [[VAL]] syncscope("workgroup") monotonic monotonic
+// SPVCHECK-NEXT: cmpxchg ptr addrspace(3) {{.*}}@gs_f32{{.*}}, i32 [[CMP]],
i32 [[VAL]] syncscope("workgroup") monotonic monotonic
----------------
hekota wrote:
```suggestion
// CHECK-NEXT: cmpxchg ptr addrspace(3) {{.*}}@gs_f32{{.*}}, i32 [[CMP]], i32
[[VAL]] syncscope("workgroup") monotonic monotonic
```
https://github.com/llvm/llvm-project/pull/222166
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
