[llvm] [AMDGPU] - Add s_wqm intrinsics (PR #71048)

[Jay Foad via llvm-commits]

================
@@ -0,0 +1,87 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -global-isel=1 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-delay-alu=0 -global-isel=0 -verify-machineinstrs < %s | FileCheck  -check-prefixes=GFX11 %s
+
+declare i32 @llvm.amdgcn.s.wqm.i32(i32)
+declare i64 @llvm.amdgcn.s.wqm.i64(i64)
+
+define i32 @test_s_wqm_constant_i32() {
+; GFX11-LABEL: test_s_wqm_constant_i32:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT:    s_wqm_b32 s0, 0x85fe3a92
----------------
jayfoad wrote:

As a follow up, could constant fold this at the IR level.

https://github.com/llvm/llvm-project/pull/71048