[llvm] [clang] [AMDGPU] Emit a waitcnt instruction after each memory instruction (PR #79236)

[Pierre van Houtryve via cfe-commits]

================
@@ -0,0 +1,199 @@
+; Testing the -amdgpu-precise-memory-op option
+; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=+amdgpu-precise-memory-op -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX9
+; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -mattr=+amdgpu-precise-memory-op -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX90A
+; COM: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+amdgpu-precise-memory-op -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX10
+; RUN: llc -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global,+enable-flat-scratch,+amdgpu-precise-memory-op -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9-FLATSCR %s
+
+; from atomicrmw-expand.ll
+; covers flat_load, flat_atomic
+define void @syncscope_workgroup_nortn(ptr %addr, float %val) {
+; GFX90A-LABEL: syncscope_workgroup_nortn:
+; GFX90A:  ; %bb.0:
+; GFX90A:         flat_load_dword v5, v[0:1]
+; GFX90A-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX90A:  .LBB0_1: ; %atomicrmw.start
+; GFX90A:         flat_atomic_cmpswap v3, v[0:1], v[4:5] glc
+; GFX90A-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+  %res = atomicrmw fadd ptr %addr, float %val syncscope("workgroup") seq_cst
+  ret void
+}
+
+; from atomicrmw-nand.ll
+; covers global_atomic, global_load
+define i32 @atomic_nand_i32_global(ptr addrspace(1) %ptr) nounwind {
+; GFX9-LABEL: atomic_nand_i32_global:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    global_load_dword v2, v[0:1], off
+; GFX9-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    s_mov_b64 s[4:5], 0
+; GFX9-NEXT:  .LBB1_1: ; %atomicrmw.start
+; GFX9-NEXT:    ; =>This Inner Loop Header: Depth=1
+; GFX9-NOT:     s_waitcnt vmcnt(0)
+; GFX9-NEXT:    v_mov_b32_e32 v3, v2
+; GFX9-NEXT:    v_not_b32_e32 v2, v3
+; GFX9-NEXT:    v_or_b32_e32 v2, -5, v2
+; GFX9-NEXT:    global_atomic_cmpswap v2, v[0:1], v[2:3], off glc
+; GFX9-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    buffer_wbinvl1_vol
+; GFX9-NEXT:    v_cmp_eq_u32_e32 vcc, v2, v3
+; GFX9-NEXT:    s_or_b64 s[4:5], vcc, s[4:5]
+; GFX9-NEXT:    s_andn2_b64 exec, exec, s[4:5]
+; GFX9-NEXT:    s_cbranch_execnz .LBB1_1
+; GFX9-NEXT:  ; %bb.2: ; %atomicrmw.end
+; GFX9-NEXT:    s_or_b64 exec, exec, s[4:5]
+; GFX9-NEXT:    v_mov_b32_e32 v0, v2
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
+  %result = atomicrmw nand ptr addrspace(1) %ptr, i32 4 seq_cst
+  ret i32 %result
+}
+
+; from bf16.ll
+; covers buffer_load, buffer_store, flat_load, flat_store, global_load, global_store
+define void @test_load_store(ptr addrspace(1) %in, ptr addrspace(1) %out) {
+;
+; GFX9-LABEL: test_load_store:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    global_load_ushort v0, v[0:1], off
+; GFX9-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    global_store_short v[2:3], v0, off
+; GFX9-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_load_store:
+; GFX10:       ; %bb.0:
+; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT:    global_load_ushort v0, v[0:1], off
+; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT:    global_store_short v[2:3], v0, off
+; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT:    s_setpc_b64 s[30:31]
+  %val = load bfloat, ptr addrspace(1) %in
+  store bfloat %val, ptr addrspace(1) %out
+  ret void
+}
+
+; from scratch-simple.ll
+; covers scratch_load, scratch_store
+;
+; GFX9-FLATSCR-LABEL: {{^}}vs_main:
+; GFX9-FLATSCR:        scratch_store_dwordx4 off, v[{{[0-9:]+}}],
+; GFX9-FLATSCR-NEXT:   s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-FLATSCR:        scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX9-FLATSCR-NEXT:   s_waitcnt vmcnt(0) lgkmcnt(0)
+define amdgpu_vs float @vs_main(i32 %idx) {
+  %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
----------------
Pierre-vh wrote:

what is that test for/why does it need such a big vector?
if it's to force a spill to stack I think you can do that by playing with the number of available v/sgprs, IIRC there is an attribute or CL opt for that

https://github.com/llvm/llvm-project/pull/79236