[llvm] [AMDGPU] Avoid unneeded waitcounts before spill stores (PR #108303)
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Sat Sep 14 00:02:19 PDT 2024
https://github.com/rampitec updated https://github.com/llvm/llvm-project/pull/108303
>From 376a9533232e672a71eae95a4f2e64bbc0f0db2c Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Wed, 11 Sep 2024 14:56:06 -0700
Subject: [PATCH 1/5] [AMDGPU] Avoid unneded waitcounts before spill stores
Implicit defs and uses on spill stores were accounted as real
defs and uses, while only exist for liveness accounting. As a
result unneded waits were generated.
Fixes: SWDEV-484177
---
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 2 +-
.../AMDGPU/GlobalISel/vni8-across-blocks.ll | 6 +-
.../AMDGPU/agpr-copy-no-free-registers.ll | 6 +-
llvm/test/CodeGen/AMDGPU/collapse-endcf.ll | 8 +-
llvm/test/CodeGen/AMDGPU/div_i128.ll | 349 ++++++++++--------
.../CodeGen/AMDGPU/indirect-addressing-si.ll | 47 +--
llvm/test/CodeGen/AMDGPU/load-global-i16.ll | 33 +-
llvm/test/CodeGen/AMDGPU/load-global-i32.ll | 14 +-
...uf-legalize-operands-non-ptr-intrinsics.ll | 48 ++-
.../CodeGen/AMDGPU/mubuf-legalize-operands.ll | 52 ++-
.../AMDGPU/preserve-wwm-copy-dst-reg.ll | 8 +-
llvm/test/CodeGen/AMDGPU/rem_i128.ll | 251 +++++++------
.../AMDGPU/sgpr-spills-split-regalloc.ll | 1 -
.../AMDGPU/spill-offset-calculation.ll | 8 +-
.../CodeGen/AMDGPU/spill-scavenge-offset.ll | 334 -----------------
llvm/test/CodeGen/AMDGPU/spill-wait.mir | 25 ++
.../test/CodeGen/AMDGPU/vni8-across-blocks.ll | 4 +-
.../test/CodeGen/AMDGPU/wwm-reserved-spill.ll | 22 +-
llvm/test/CodeGen/AMDGPU/wwm-reserved.ll | 4 +-
19 files changed, 493 insertions(+), 729 deletions(-)
create mode 100644 llvm/test/CodeGen/AMDGPU/spill-wait.mir
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 8ae7f2910ec5a9..ced1d0c508ebc8 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -901,7 +901,7 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
}
} else /* LGKM_CNT || EXP_CNT || VS_CNT || NUM_INST_CNTS */ {
// Match the score to the destination registers.
- for (unsigned I = 0, E = Inst.getNumOperands(); I != E; ++I) {
+ for (unsigned I = 0, E = Inst.getNumExplicitOperands(); I != E; ++I) {
auto &Op = Inst.getOperand(I);
if (!Op.isReg() || !Op.isDef())
continue;
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/vni8-across-blocks.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/vni8-across-blocks.ll
index 1f1c2659e81103..fff06e4ad16c07 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/vni8-across-blocks.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/vni8-across-blocks.ll
@@ -268,7 +268,7 @@ define amdgpu_kernel void @v256i8_liveout(ptr addrspace(1) %src1, ptr addrspace(
; GFX906-NEXT: v_cmp_gt_u32_e32 vcc, 15, v0
; GFX906-NEXT: s_waitcnt vmcnt(0)
; GFX906-NEXT: buffer_store_dword v5, off, s[12:15], 0 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v6, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v7, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v8, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -294,7 +294,7 @@ define amdgpu_kernel void @v256i8_liveout(ptr addrspace(1) %src1, ptr addrspace(
; GFX906-NEXT: global_load_dwordx4 v[0:3], v4, s[6:7]
; GFX906-NEXT: s_waitcnt vmcnt(0)
; GFX906-NEXT: buffer_store_dword v0, off, s[12:15], 0 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v3, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -317,7 +317,7 @@ define amdgpu_kernel void @v256i8_liveout(ptr addrspace(1) %src1, ptr addrspace(
; GFX906-NEXT: s_or_b64 exec, exec, s[2:3]
; GFX906-NEXT: s_waitcnt vmcnt(0)
; GFX906-NEXT: buffer_store_dword v0, off, s[12:15], 0 offset:16 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v1, off, s[12:15], 0 offset:20 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v2, off, s[12:15], 0 offset:24 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v3, off, s[12:15], 0 offset:28 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll b/llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll
index fb96b9ff2952e8..49b450a9af0bc9 100644
--- a/llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll
+++ b/llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll
@@ -185,7 +185,7 @@ define void @no_free_vgprs_at_agpr_to_agpr_copy(float %v0, float %v1) #0 {
; GFX90A-NEXT: s_nop 7
; GFX90A-NEXT: s_nop 2
; GFX90A-NEXT: buffer_store_dword a0, off, s[0:3], s32 ; 4-byte Folded Spill
-; GFX90A-NEXT: s_waitcnt vmcnt(0)
+; GFX90A-NEXT: s_nop 0
; GFX90A-NEXT: buffer_store_dword a1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
; GFX90A-NEXT: buffer_store_dword a2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX90A-NEXT: buffer_store_dword a3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
@@ -215,7 +215,6 @@ define void @no_free_vgprs_at_agpr_to_agpr_copy(float %v0, float %v1) #0 {
; GFX90A-NEXT: buffer_load_dword a7, off, s[0:3], s32 offset:28 ; 4-byte Folded Reload
; GFX90A-NEXT: buffer_load_dword a8, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX90A-NEXT: buffer_load_dword a9, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
-; GFX90A-NEXT: s_waitcnt vmcnt(9)
; GFX90A-NEXT: v_accvgpr_write_b32 a10, v39 ; Reload Reuse
; GFX90A-NEXT: v_accvgpr_write_b32 a11, v38 ; Reload Reuse
; GFX90A-NEXT: v_accvgpr_write_b32 a12, v37 ; Reload Reuse
@@ -1093,7 +1092,7 @@ define void @no_free_vgprs_at_sgpr_to_agpr_copy(float %v0, float %v1) #0 {
; GFX90A-NEXT: s_nop 7
; GFX90A-NEXT: s_nop 2
; GFX90A-NEXT: buffer_store_dword a0, off, s[0:3], s32 ; 4-byte Folded Spill
-; GFX90A-NEXT: s_waitcnt vmcnt(0)
+; GFX90A-NEXT: s_nop 0
; GFX90A-NEXT: buffer_store_dword a1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
; GFX90A-NEXT: buffer_store_dword a2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX90A-NEXT: buffer_store_dword a3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
@@ -1124,7 +1123,6 @@ define void @no_free_vgprs_at_sgpr_to_agpr_copy(float %v0, float %v1) #0 {
; GFX90A-NEXT: buffer_load_dword a8, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX90A-NEXT: buffer_load_dword a9, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GFX90A-NEXT: buffer_load_dword a10, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
-; GFX90A-NEXT: s_waitcnt vmcnt(10)
; GFX90A-NEXT: v_accvgpr_write_b32 a11, v39 ; Reload Reuse
; GFX90A-NEXT: v_accvgpr_write_b32 a12, v38 ; Reload Reuse
; GFX90A-NEXT: v_accvgpr_write_b32 a13, v37 ; Reload Reuse
diff --git a/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll b/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
index 75f5eda608e80a..51f9cf73488ee7 100644
--- a/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
+++ b/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
@@ -708,7 +708,6 @@ define amdgpu_kernel void @nested_if_else_if(ptr addrspace(1) nocapture %arg) {
; GCN-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; GCN-O0-NEXT: v_mov_b32_e32 v6, v2
; GCN-O0-NEXT: buffer_store_dword v5, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v6, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GCN-O0-NEXT: s_mov_b32 s1, 0xf000
; GCN-O0-NEXT: s_mov_b32 s2, 0
@@ -722,6 +721,7 @@ define amdgpu_kernel void @nested_if_else_if(ptr addrspace(1) nocapture %arg) {
; GCN-O0-NEXT: s_mov_b64 s[2:3], exec
; GCN-O0-NEXT: s_and_b64 s[0:1], s[2:3], s[0:1]
; GCN-O0-NEXT: s_xor_b64 s[2:3], s[0:1], s[2:3]
+; GCN-O0-NEXT: s_waitcnt vmcnt(4)
; GCN-O0-NEXT: v_writelane_b32 v0, s2, 0
; GCN-O0-NEXT: v_writelane_b32 v0, s3, 1
; GCN-O0-NEXT: s_or_saveexec_b64 s[8:9], -1
@@ -1159,7 +1159,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: v_mov_b32_e32 v3, s10
; GCN-O0-NEXT: v_mov_b32_e32 v4, s11
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
@@ -1193,7 +1192,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: v_mov_b32_e32 v3, s10
; GCN-O0-NEXT: v_mov_b32_e32 v4, s11
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
@@ -1225,7 +1223,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: v_mov_b32_e32 v2, s6
; GCN-O0-NEXT: v_mov_b32_e32 v3, s7
; GCN-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
@@ -1247,7 +1244,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:20 ; 4-byte Folded Reload
; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
@@ -1269,7 +1265,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
@@ -1343,7 +1338,6 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: s_mov_b64 exec, s[14:15]
; GCN-O0-NEXT: s_waitcnt vmcnt(1)
; GCN-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
-; GCN-O0-NEXT: s_waitcnt vmcnt(0)
; GCN-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
; GCN-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/div_i128.ll b/llvm/test/CodeGen/AMDGPU/div_i128.ll
index fea1303d0a2b76..712cecff40617b 100644
--- a/llvm/test/CodeGen/AMDGPU/div_i128.ll
+++ b/llvm/test/CodeGen/AMDGPU/div_i128.ll
@@ -345,30 +345,30 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: s_mov_b32 s4, 63
; GFX9-O0-NEXT: v_ashrrev_i64 v[13:14], s4, v[13:14]
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v18
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v19
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v6
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v5
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v16
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v17
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v19
@@ -483,14 +483,14 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v9
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; kill: def $vgpr8 killed $vgpr8 def $vgpr8_vgpr9 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v9, v7
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[8:9], v[8:9], s[6:7]
; GFX9-O0-NEXT: s_mov_b64 s[12:13], 0x7f
@@ -538,10 +538,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-O0-NEXT: s_and_b64 s[6:7], s[4:5], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], exec
; GFX9-O0-NEXT: v_writelane_b32 v0, s4, 4
@@ -572,16 +572,19 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:148 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_5
; GFX9-O0-NEXT: .LBB0_3: ; %Flow2
@@ -598,10 +601,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_9
; GFX9-O0-NEXT: .LBB0_4: ; %udiv-loop-exit
@@ -638,10 +641,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_3
; GFX9-O0-NEXT: .LBB0_5: ; %Flow1
@@ -662,16 +665,16 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:92 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_4
; GFX9-O0-NEXT: .LBB0_6: ; %udiv-do-while
@@ -756,11 +759,12 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v10, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v23
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v24
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v11, v14
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v15
; GFX9-O0-NEXT: v_sub_co_u32_e32 v13, vcc, v13, v6
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_subb_co_u32_e32 v12, vcc, v12, v10, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v11, vcc, v11, v4, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v7, vcc, v7, v5, vcc
@@ -846,22 +850,22 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v2
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v15
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v14
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], s[4:5]
; GFX9-O0-NEXT: v_writelane_b32 v16, s6, 6
@@ -873,28 +877,28 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[22:23]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-O0-NEXT: s_cbranch_execnz .LBB0_6
@@ -919,7 +923,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v20, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v21, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v22, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
-; GFX9-O0-NEXT: s_waitcnt vmcnt(9)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[6:7], v4, v[21:22]
@@ -992,10 +996,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v17
; GFX9-O0-NEXT: s_mov_b64 s[8:9], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], s[6:7]
; GFX9-O0-NEXT: v_mov_b32_e32 v15, s9
@@ -1008,28 +1012,28 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[22:23]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_6
; GFX9-O0-NEXT: .LBB0_8: ; %udiv-bb1
@@ -1046,7 +1050,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 1
; GFX9-O0-NEXT: s_mov_b32 s5, s6
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v1
; GFX9-O0-NEXT: s_mov_b32 s4, s7
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
@@ -1057,6 +1061,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s5
; GFX9-O0-NEXT: v_add_co_u32_e32 v9, vcc, v4, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s4
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_addc_co_u32_e32 v2, vcc, v2, v5, vcc
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s8
; GFX9-O0-NEXT: v_addc_co_u32_e32 v1, vcc, v1, v5, vcc
@@ -1073,12 +1078,12 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v1
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:296 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:300 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v10
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:304 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:308 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b32 s4, 0x7f
; GFX9-O0-NEXT: v_sub_u32_e64 v3, s4, v4
@@ -1126,10 +1131,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr7 killed $vgpr7 def $vgpr7_vgpr8 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v3
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v10
@@ -1146,16 +1151,16 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v1, s6
; GFX9-O0-NEXT: v_mov_b32_e32 v2, s7
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], exec
; GFX9-O0-NEXT: s_and_b64 s[4:5], s[6:7], s[4:5]
@@ -1455,7 +1460,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v10, v2
; GFX9-G-O0-NEXT: v_mov_b32_e32 v11, v3
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
@@ -1682,7 +1687,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: s_mov_b64 s[6:7], -1
; GFX9-G-O0-NEXT: s_xor_b64 s[6:7], s[4:5], s[6:7]
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
@@ -1715,12 +1720,13 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:160 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(4)
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(4)
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
@@ -1739,7 +1745,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
@@ -1753,9 +1759,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:200 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:204 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:208 ; 4-byte Folded Reload
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v5
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v6
; GFX9-G-O0-NEXT: v_mov_b32_e32 v5, v7
; GFX9-G-O0-NEXT: s_mov_b32 s4, 1
@@ -1794,7 +1801,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v5
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
@@ -1817,12 +1824,12 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:112 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
@@ -1860,9 +1867,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v12, off, s[0:3], s32 offset:284 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v13, off, s[0:3], s32 offset:288 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_mov_b64 s[4:5], 0
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(16)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(18)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v2
; GFX9-G-O0-NEXT: v_mov_b32_e32 v1, v3
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(16)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-G-O0-NEXT: s_mov_b32 s8, 1
@@ -1912,9 +1920,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, s8
; GFX9-G-O0-NEXT: v_mov_b32_e32 v14, v0
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v1
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(8)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v29, v31
; GFX9-G-O0-NEXT: v_mov_b32_e32 v30, v32
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(8)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v25, v33
; GFX9-G-O0-NEXT: v_mov_b32_e32 v26, v34
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v29
@@ -2001,7 +2010,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-G-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-G-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v19, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v20, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
@@ -2010,7 +2019,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-G-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-G-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v19, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v20, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
@@ -2024,22 +2033,22 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: s_mov_b64 exec, s[20:21]
; GFX9-G-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
@@ -2142,22 +2151,22 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v13, s5
; GFX9-G-O0-NEXT: v_mov_b32_e32 v12, s4
; GFX9-G-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
@@ -2195,7 +2204,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v16, v8
; GFX9-G-O0-NEXT: v_mov_b32_e32 v17, v7
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:308 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:312 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 offset:316 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:320 ; 4-byte Folded Spill
@@ -2246,7 +2255,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v9
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:296 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:300 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:304 ; 4-byte Folded Spill
@@ -2260,7 +2269,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v7, s4
; GFX9-G-O0-NEXT: v_cmp_ne_u64_e64 s[4:5], v[5:6], v[7:8]
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
@@ -2269,7 +2278,7 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, s10
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, s11
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
@@ -2296,9 +2305,10 @@ define i128 @v_sdiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v10, off, s[0:3], s32 offset:168 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v11, off, s[0:3], s32 offset:172 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v12, off, s[0:3], s32 offset:176 ; 4-byte Folded Reload
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v1, v9
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v10
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v9, v11
; GFX9-G-O0-NEXT: v_mov_b32_e32 v10, v12
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v1
@@ -2553,22 +2563,23 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v12
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(3)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v1
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v14
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v2
@@ -2579,6 +2590,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr1 killed $vgpr1 def $vgpr1_vgpr2 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v2, v3
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
+; GFX9-O0-NEXT: s_waitcnt vmcnt(8)
; GFX9-O0-NEXT: v_writelane_b32 v0, s6, 0
; GFX9-O0-NEXT: v_writelane_b32 v0, s7, 1
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], v[1:2], s[6:7]
@@ -2688,14 +2700,14 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v9
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; kill: def $vgpr8 killed $vgpr8 def $vgpr8_vgpr9 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v9, v7
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[8:9], v[8:9], s[6:7]
; GFX9-O0-NEXT: s_mov_b64 s[12:13], 0x7f
@@ -2743,10 +2755,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-O0-NEXT: s_and_b64 s[6:7], s[4:5], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], exec
; GFX9-O0-NEXT: v_writelane_b32 v0, s4, 2
@@ -2777,16 +2789,19 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:132 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_5
; GFX9-O0-NEXT: .LBB1_3: ; %Flow2
@@ -2803,10 +2818,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_9
; GFX9-O0-NEXT: .LBB1_4: ; %udiv-loop-exit
@@ -2843,10 +2858,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_3
; GFX9-O0-NEXT: .LBB1_5: ; %Flow1
@@ -2867,16 +2882,16 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:76 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_4
; GFX9-O0-NEXT: .LBB1_6: ; %udiv-do-while
@@ -2961,11 +2976,12 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v10, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v23
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v24
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v11, v14
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v15
; GFX9-O0-NEXT: v_sub_co_u32_e32 v13, vcc, v13, v6
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_subb_co_u32_e32 v12, vcc, v12, v10, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v11, vcc, v11, v4, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v7, vcc, v7, v5, vcc
@@ -3051,22 +3067,22 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v2
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v15
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v14
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], s[4:5]
; GFX9-O0-NEXT: v_writelane_b32 v16, s6, 4
@@ -3078,28 +3094,28 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[18:19]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-O0-NEXT: s_cbranch_execnz .LBB1_6
@@ -3124,7 +3140,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v20, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v21, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v22, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
-; GFX9-O0-NEXT: s_waitcnt vmcnt(9)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[6:7], v4, v[21:22]
@@ -3197,10 +3213,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v17
; GFX9-O0-NEXT: s_mov_b64 s[8:9], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], s[6:7]
; GFX9-O0-NEXT: v_mov_b32_e32 v15, s9
@@ -3213,28 +3229,28 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[18:19]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_6
; GFX9-O0-NEXT: .LBB1_8: ; %udiv-bb1
@@ -3251,7 +3267,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 1
; GFX9-O0-NEXT: s_mov_b32 s5, s6
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v1
; GFX9-O0-NEXT: s_mov_b32 s4, s7
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
@@ -3262,6 +3278,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s5
; GFX9-O0-NEXT: v_add_co_u32_e32 v9, vcc, v4, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s4
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_addc_co_u32_e32 v2, vcc, v2, v5, vcc
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s8
; GFX9-O0-NEXT: v_addc_co_u32_e32 v1, vcc, v1, v5, vcc
@@ -3278,12 +3295,12 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v1
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v10
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b32 s4, 0x7f
; GFX9-O0-NEXT: v_sub_u32_e64 v3, s4, v4
@@ -3331,10 +3348,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr7 killed $vgpr7 def $vgpr7_vgpr8 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v3
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v10
@@ -3351,16 +3368,16 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v1, s6
; GFX9-O0-NEXT: v_mov_b32_e32 v2, s7
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], exec
; GFX9-O0-NEXT: s_and_b64 s[4:5], s[6:7], s[4:5]
@@ -3601,7 +3618,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v10, v2
; GFX9-G-O0-NEXT: v_mov_b32_e32 v11, v3
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
@@ -3622,7 +3639,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v8, v9
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
@@ -3798,7 +3815,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: s_mov_b64 s[6:7], -1
; GFX9-G-O0-NEXT: s_xor_b64 s[6:7], s[4:5], s[6:7]
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
@@ -3831,12 +3848,13 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:132 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(4)
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(4)
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
@@ -3855,7 +3873,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
@@ -3869,9 +3887,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:172 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:176 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:180 ; 4-byte Folded Reload
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v5
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v6
; GFX9-G-O0-NEXT: v_mov_b32_e32 v5, v7
; GFX9-G-O0-NEXT: s_mov_b32 s4, 1
@@ -3910,7 +3929,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v5
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
@@ -3933,12 +3952,12 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:84 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
@@ -3976,9 +3995,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v10, off, s[0:3], s32 offset:256 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v11, off, s[0:3], s32 offset:260 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_mov_b64 s[4:5], 0
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(16)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(18)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v2
; GFX9-G-O0-NEXT: v_mov_b32_e32 v1, v3
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(16)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-G-O0-NEXT: s_mov_b32 s8, 1
@@ -4028,9 +4048,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, s8
; GFX9-G-O0-NEXT: v_mov_b32_e32 v12, v0
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v1
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(8)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v29, v31
; GFX9-G-O0-NEXT: v_mov_b32_e32 v30, v32
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(8)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v21, v33
; GFX9-G-O0-NEXT: v_mov_b32_e32 v22, v34
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v29
@@ -4125,7 +4146,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-G-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-G-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v19, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v20, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
@@ -4134,7 +4155,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-G-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-G-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v19, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v20, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
@@ -4148,22 +4169,22 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: s_mov_b64 exec, s[18:19]
; GFX9-G-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
@@ -4192,9 +4213,10 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:64 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:68 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: s_mov_b32 s4, 64
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v16, v5
; GFX9-G-O0-NEXT: v_mov_b32_e32 v15, v4
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v22, v7
; GFX9-G-O0-NEXT: v_mov_b32_e32 v21, v6
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, s4
@@ -4270,22 +4292,22 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v13, s5
; GFX9-G-O0-NEXT: v_mov_b32_e32 v12, s4
; GFX9-G-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
@@ -4323,7 +4345,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v15, v8
; GFX9-G-O0-NEXT: v_mov_b32_e32 v16, v7
; GFX9-G-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
@@ -4374,7 +4396,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v9
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
@@ -4388,7 +4410,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v7, s4
; GFX9-G-O0-NEXT: v_cmp_ne_u64_e64 s[4:5], v[5:6], v[7:8]
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
@@ -4397,7 +4419,7 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, s10
; GFX9-G-O0-NEXT: v_mov_b32_e32 v4, s11
; GFX9-G-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_nop 0
; GFX9-G-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
; GFX9-G-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
@@ -4420,10 +4442,13 @@ define i128 @v_udiv_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-G-O0-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:140 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:144 ; 4-byte Folded Reload
; GFX9-G-O0-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:148 ; 4-byte Folded Reload
-; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(3)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v0, v5
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v1, v6
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v2, v7
+; GFX9-G-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-G-O0-NEXT: v_mov_b32_e32 v3, v8
; GFX9-G-O0-NEXT: ; kill: killed $vgpr4
; GFX9-G-O0-NEXT: s_xor_saveexec_b64 s[4:5], -1
diff --git a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
index a33142fd0ab1f3..b4fe112438b4f7 100644
--- a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
+++ b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
@@ -1581,7 +1581,6 @@ define amdgpu_kernel void @extract_neg_offset_vgpr(ptr addrspace(1) %out) {
; NOOPT-NEXT: v_mov_b32_e32 v15, v18
; NOOPT-NEXT: v_mov_b32_e32 v16, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:4 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:12 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[20:23], 0 offset:16 ; 4-byte Folded Spill
@@ -4089,7 +4088,6 @@ define amdgpu_kernel void @insert_neg_offset_vgpr(ptr addrspace(1) %in, ptr addr
; NOOPT-NEXT: v_mov_b32_e32 v14, v18
; NOOPT-NEXT: v_mov_b32_e32 v15, v17
; NOOPT-NEXT: buffer_store_dword v0, off, s[20:23], 0 offset:72 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:76 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:80 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:84 ; 4-byte Folded Spill
@@ -4115,7 +4113,6 @@ define amdgpu_kernel void @insert_neg_offset_vgpr(ptr addrspace(1) %in, ptr addr
; NOOPT-NEXT: s_mov_b64 exec, s[16:17]
; NOOPT-NEXT: s_waitcnt expcnt(2)
; NOOPT-NEXT: buffer_store_dword v0, off, s[20:23], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:12 ; 4-byte Folded Spill
@@ -4166,7 +4163,6 @@ define amdgpu_kernel void @insert_neg_offset_vgpr(ptr addrspace(1) %in, ptr addr
; NOOPT-NEXT: s_add_i32 m0, s2, 0xfffffe00
; NOOPT-NEXT: v_movreld_b32_e32 v1, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:140 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:144 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:148 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[20:23], 0 offset:152 ; 4-byte Folded Spill
@@ -4184,7 +4180,6 @@ define amdgpu_kernel void @insert_neg_offset_vgpr(ptr addrspace(1) %in, ptr addr
; NOOPT-NEXT: buffer_store_dword v16, off, s[20:23], 0 offset:200 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[20:23], 0 offset:12 ; 4-byte Folded Spill
@@ -4242,19 +4237,22 @@ define amdgpu_kernel void @insert_neg_offset_vgpr(ptr addrspace(1) %in, ptr addr
; NOOPT-NEXT: buffer_load_dword v29, off, s[20:23], 0 offset:192 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v30, off, s[20:23], 0 offset:196 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v31, off, s[20:23], 0 offset:200 ; 4-byte Folded Reload
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
+; NOOPT-NEXT: s_waitcnt vmcnt(12)
; NOOPT-NEXT: v_mov_b32_e32 v5, v19
; NOOPT-NEXT: v_mov_b32_e32 v6, v18
; NOOPT-NEXT: v_mov_b32_e32 v7, v17
; NOOPT-NEXT: v_mov_b32_e32 v1, v16
+; NOOPT-NEXT: s_waitcnt vmcnt(8)
; NOOPT-NEXT: v_mov_b32_e32 v2, v23
; NOOPT-NEXT: v_mov_b32_e32 v3, v22
; NOOPT-NEXT: v_mov_b32_e32 v4, v21
; NOOPT-NEXT: v_mov_b32_e32 v8, v20
+; NOOPT-NEXT: s_waitcnt vmcnt(4)
; NOOPT-NEXT: v_mov_b32_e32 v13, v27
; NOOPT-NEXT: v_mov_b32_e32 v14, v26
; NOOPT-NEXT: v_mov_b32_e32 v15, v25
; NOOPT-NEXT: v_mov_b32_e32 v9, v24
+; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_mov_b32_e32 v10, v31
; NOOPT-NEXT: v_mov_b32_e32 v11, v30
; NOOPT-NEXT: v_mov_b32_e32 v12, v29
@@ -4576,7 +4574,6 @@ define amdgpu_kernel void @insert_neg_inline_offset_vgpr(ptr addrspace(1) %in, p
; NOOPT-NEXT: v_mov_b32_e32 v14, v18
; NOOPT-NEXT: v_mov_b32_e32 v15, v17
; NOOPT-NEXT: buffer_store_dword v0, off, s[20:23], 0 offset:72 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:76 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:80 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:84 ; 4-byte Folded Spill
@@ -4602,7 +4599,6 @@ define amdgpu_kernel void @insert_neg_inline_offset_vgpr(ptr addrspace(1) %in, p
; NOOPT-NEXT: s_mov_b64 exec, s[16:17]
; NOOPT-NEXT: s_waitcnt expcnt(2)
; NOOPT-NEXT: buffer_store_dword v0, off, s[20:23], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:12 ; 4-byte Folded Spill
@@ -4653,7 +4649,6 @@ define amdgpu_kernel void @insert_neg_inline_offset_vgpr(ptr addrspace(1) %in, p
; NOOPT-NEXT: s_add_i32 m0, s2, -16
; NOOPT-NEXT: v_movreld_b32_e32 v1, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 offset:140 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:144 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:148 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[20:23], 0 offset:152 ; 4-byte Folded Spill
@@ -4671,7 +4666,6 @@ define amdgpu_kernel void @insert_neg_inline_offset_vgpr(ptr addrspace(1) %in, p
; NOOPT-NEXT: buffer_store_dword v16, off, s[20:23], 0 offset:200 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[20:23], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[20:23], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[20:23], 0 offset:12 ; 4-byte Folded Spill
@@ -4729,19 +4723,22 @@ define amdgpu_kernel void @insert_neg_inline_offset_vgpr(ptr addrspace(1) %in, p
; NOOPT-NEXT: buffer_load_dword v29, off, s[20:23], 0 offset:192 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v30, off, s[20:23], 0 offset:196 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v31, off, s[20:23], 0 offset:200 ; 4-byte Folded Reload
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
+; NOOPT-NEXT: s_waitcnt vmcnt(12)
; NOOPT-NEXT: v_mov_b32_e32 v5, v19
; NOOPT-NEXT: v_mov_b32_e32 v6, v18
; NOOPT-NEXT: v_mov_b32_e32 v7, v17
; NOOPT-NEXT: v_mov_b32_e32 v1, v16
+; NOOPT-NEXT: s_waitcnt vmcnt(8)
; NOOPT-NEXT: v_mov_b32_e32 v2, v23
; NOOPT-NEXT: v_mov_b32_e32 v3, v22
; NOOPT-NEXT: v_mov_b32_e32 v4, v21
; NOOPT-NEXT: v_mov_b32_e32 v8, v20
+; NOOPT-NEXT: s_waitcnt vmcnt(4)
; NOOPT-NEXT: v_mov_b32_e32 v13, v27
; NOOPT-NEXT: v_mov_b32_e32 v14, v26
; NOOPT-NEXT: v_mov_b32_e32 v15, v25
; NOOPT-NEXT: v_mov_b32_e32 v9, v24
+; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_mov_b32_e32 v10, v31
; NOOPT-NEXT: v_mov_b32_e32 v11, v30
; NOOPT-NEXT: v_mov_b32_e32 v12, v29
@@ -5154,7 +5151,6 @@ define amdgpu_kernel void @extract_vgpr_offset_multiple_in_block(ptr addrspace(1
; NOOPT-NEXT: v_mov_b32_e32 v2, s1
; NOOPT-NEXT: v_mov_b32_e32 v1, s0
; NOOPT-NEXT: buffer_store_dword v1, off, s[36:39], 0 offset:4 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[36:39], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[36:39], 0 offset:12 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[36:39], 0 offset:16 ; 4-byte Folded Spill
@@ -5272,7 +5268,6 @@ define amdgpu_kernel void @extract_vgpr_offset_multiple_in_block(ptr addrspace(1
; NOOPT-NEXT: v_mov_b32_e32 v2, s1
; NOOPT-NEXT: v_mov_b32_e32 v1, s0
; NOOPT-NEXT: buffer_store_dword v1, off, s[36:39], 0 offset:88 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[36:39], 0 offset:92 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[36:39], 0 offset:96 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[36:39], 0 offset:100 ; 4-byte Folded Spill
@@ -5893,7 +5888,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: buffer_store_dword v16, off, s[28:31], 0 offset:64 ; 4-byte Folded Spill
; NOOPT-NEXT: s_mov_b64 exec, s[26:27]
; NOOPT-NEXT: buffer_store_dword v0, off, s[28:31], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:12 ; 4-byte Folded Spill
@@ -5944,7 +5938,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: s_mov_b32 m0, s2
; NOOPT-NEXT: v_movreld_b32_e32 v1, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 offset:88 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:92 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:96 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[28:31], 0 offset:100 ; 4-byte Folded Spill
@@ -5962,7 +5955,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: buffer_store_dword v16, off, s[28:31], 0 offset:148 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[28:31], 0 offset:12 ; 4-byte Folded Spill
@@ -6025,7 +6017,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: buffer_store_dword v16, off, s[28:31], 0 offset:64 ; 4-byte Folded Spill
; NOOPT-NEXT: s_mov_b64 exec, s[26:27]
; NOOPT-NEXT: buffer_store_dword v0, off, s[28:31], 0 offset:152 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 offset:156 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:160 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:164 ; 4-byte Folded Spill
@@ -6076,7 +6067,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: s_mov_b32 m0, s2
; NOOPT-NEXT: v_movreld_b32_e32 v1, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 offset:220 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:224 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:228 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[28:31], 0 offset:232 ; 4-byte Folded Spill
@@ -6094,7 +6084,6 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: buffer_store_dword v16, off, s[28:31], 0 offset:280 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[28:31], 0 offset:152 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[28:31], 0 offset:156 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[28:31], 0 offset:160 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[28:31], 0 offset:164 ; 4-byte Folded Spill
@@ -6154,19 +6143,22 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: buffer_load_dword v30, off, s[28:31], 0 offset:272 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v31, off, s[28:31], 0 offset:276 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v32, off, s[28:31], 0 offset:280 ; 4-byte Folded Reload
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
+; NOOPT-NEXT: s_waitcnt vmcnt(12)
; NOOPT-NEXT: v_mov_b32_e32 v6, v20
; NOOPT-NEXT: v_mov_b32_e32 v7, v19
; NOOPT-NEXT: v_mov_b32_e32 v8, v18
; NOOPT-NEXT: v_mov_b32_e32 v2, v17
+; NOOPT-NEXT: s_waitcnt vmcnt(8)
; NOOPT-NEXT: v_mov_b32_e32 v3, v24
; NOOPT-NEXT: v_mov_b32_e32 v4, v23
; NOOPT-NEXT: v_mov_b32_e32 v5, v22
; NOOPT-NEXT: v_mov_b32_e32 v9, v21
+; NOOPT-NEXT: s_waitcnt vmcnt(4)
; NOOPT-NEXT: v_mov_b32_e32 v14, v28
; NOOPT-NEXT: v_mov_b32_e32 v15, v27
; NOOPT-NEXT: v_mov_b32_e32 v16, v26
; NOOPT-NEXT: v_mov_b32_e32 v10, v25
+; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_mov_b32_e32 v11, v32
; NOOPT-NEXT: v_mov_b32_e32 v12, v31
; NOOPT-NEXT: v_mov_b32_e32 v13, v30
@@ -9158,7 +9150,6 @@ define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) {
; NOOPT-NEXT: buffer_store_dword v16, off, s[24:27], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: s_mov_b64 exec, s[20:21]
; NOOPT-NEXT: buffer_store_dword v0, off, s[24:27], 0 offset:12 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[24:27], 0 offset:16 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[24:27], 0 offset:20 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[24:27], 0 offset:24 ; 4-byte Folded Spill
@@ -9210,7 +9201,6 @@ define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) {
; NOOPT-NEXT: s_mov_b32 m0, s2
; NOOPT-NEXT: v_movreld_b32_e32 v1, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[24:27], 0 offset:84 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[24:27], 0 offset:88 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[24:27], 0 offset:92 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[24:27], 0 offset:96 ; 4-byte Folded Spill
@@ -9228,7 +9218,6 @@ define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) {
; NOOPT-NEXT: buffer_store_dword v16, off, s[24:27], 0 offset:144 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[24:27], 0 offset:12 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[24:27], 0 offset:16 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[24:27], 0 offset:20 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[24:27], 0 offset:24 ; 4-byte Folded Spill
@@ -9282,7 +9271,7 @@ define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) {
; NOOPT-NEXT: buffer_load_dword v15, off, s[24:27], 0 offset:140 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v16, off, s[24:27], 0 offset:144 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 s[0:1], 0
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
+; NOOPT-NEXT: s_waitcnt vmcnt(14)
; NOOPT-NEXT: buffer_store_dword v1, off, s[24:27], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: v_writelane_b32 v0, s0, 2
; NOOPT-NEXT: v_writelane_b32 v0, s1, 3
@@ -9576,7 +9565,6 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: ; kill: def $vgpr0 killed $vgpr0 def $vgpr0_vgpr1 killed $exec
; NOOPT-NEXT: v_mov_b32_e32 v1, v2
; NOOPT-NEXT: buffer_store_dword v0, off, s[16:19], 0 offset:136 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[16:19], 0 offset:140 ; 4-byte Folded Spill
; NOOPT-NEXT: s_mov_b32 s8, 0xf000
; NOOPT-NEXT: s_mov_b32 s0, 0
@@ -9632,7 +9620,6 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: v_mov_b32_e32 v14, v18
; NOOPT-NEXT: v_mov_b32_e32 v15, v17
; NOOPT-NEXT: buffer_store_dword v0, off, s[16:19], 0 offset:68 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[16:19], 0 offset:72 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[16:19], 0 offset:76 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[16:19], 0 offset:80 ; 4-byte Folded Spill
@@ -9656,7 +9643,6 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: s_mov_b64 exec, s[12:13]
; NOOPT-NEXT: s_waitcnt expcnt(1)
; NOOPT-NEXT: buffer_store_dword v0, off, s[16:19], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[16:19], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v2, off, s[16:19], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[16:19], 0 offset:12 ; 4-byte Folded Spill
@@ -9707,7 +9693,6 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: s_mov_b32 m0, s2
; NOOPT-NEXT: v_movreld_b32_e32 v2, v17
; NOOPT-NEXT: buffer_store_dword v1, off, s[16:19], 0 offset:148 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[16:19], 0 offset:152 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[16:19], 0 offset:156 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[16:19], 0 offset:160 ; 4-byte Folded Spill
@@ -9725,7 +9710,6 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: buffer_store_dword v16, off, s[16:19], 0 offset:208 ; 4-byte Folded Spill
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_store_dword v1, off, s[16:19], 0 ; 4-byte Folded Spill
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: buffer_store_dword v2, off, s[16:19], 0 offset:4 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v3, off, s[16:19], 0 offset:8 ; 4-byte Folded Spill
; NOOPT-NEXT: buffer_store_dword v4, off, s[16:19], 0 offset:12 ; 4-byte Folded Spill
@@ -9785,19 +9769,22 @@ define amdgpu_cs void @insert_or_disj_index(ptr addrspace(1) %out, ptr addrspace
; NOOPT-NEXT: buffer_load_dword v31, off, s[16:19], 0 offset:200 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v32, off, s[16:19], 0 offset:204 ; 4-byte Folded Reload
; NOOPT-NEXT: buffer_load_dword v33, off, s[16:19], 0 offset:208 ; 4-byte Folded Reload
-; NOOPT-NEXT: s_waitcnt vmcnt(0)
+; NOOPT-NEXT: s_waitcnt vmcnt(12)
; NOOPT-NEXT: v_mov_b32_e32 v7, v21
; NOOPT-NEXT: v_mov_b32_e32 v8, v20
; NOOPT-NEXT: v_mov_b32_e32 v9, v19
; NOOPT-NEXT: v_mov_b32_e32 v1, v18
+; NOOPT-NEXT: s_waitcnt vmcnt(8)
; NOOPT-NEXT: v_mov_b32_e32 v2, v25
; NOOPT-NEXT: v_mov_b32_e32 v3, v24
; NOOPT-NEXT: v_mov_b32_e32 v4, v23
; NOOPT-NEXT: v_mov_b32_e32 v10, v22
+; NOOPT-NEXT: s_waitcnt vmcnt(4)
; NOOPT-NEXT: v_mov_b32_e32 v15, v29
; NOOPT-NEXT: v_mov_b32_e32 v16, v28
; NOOPT-NEXT: v_mov_b32_e32 v17, v27
; NOOPT-NEXT: v_mov_b32_e32 v11, v26
+; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_mov_b32_e32 v12, v33
; NOOPT-NEXT: v_mov_b32_e32 v13, v32
; NOOPT-NEXT: v_mov_b32_e32 v14, v31
diff --git a/llvm/test/CodeGen/AMDGPU/load-global-i16.ll b/llvm/test/CodeGen/AMDGPU/load-global-i16.ll
index 4cc47b09d813d6..fe5427048e8cf1 100644
--- a/llvm/test/CodeGen/AMDGPU/load-global-i16.ll
+++ b/llvm/test/CodeGen/AMDGPU/load-global-i16.ll
@@ -3479,7 +3479,6 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v17, 0xffff, v15
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v15, 0xffff, v14
; GCN-NOHSA-SI-NEXT: buffer_store_dword v15, off, s[12:15], 0 ; 4-byte Folded Spill
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_store_dword v16, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v17, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v18, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -3487,7 +3486,6 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: s_waitcnt expcnt(0)
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v18, 0xffff, v12
; GCN-NOHSA-SI-NEXT: buffer_store_dword v18, off, s[12:15], 0 offset:16 ; 4-byte Folded Spill
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_store_dword v19, off, s[12:15], 0 offset:20 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v20, off, s[12:15], 0 offset:24 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v21, off, s[12:15], 0 offset:28 ; 4-byte Folded Spill
@@ -3498,6 +3496,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v23, 0xffff, v10
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v18, 0xffff, v9
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v16, 0xffff, v8
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(13)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v15, 16, v7
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v13, 16, v6
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v46, 16, v5
@@ -3506,6 +3505,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v12, 0xffff, v6
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v45, 0xffff, v5
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v43, 0xffff, v4
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(12)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v11, 16, v3
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v9, 16, v2
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v50, 16, v1
@@ -3514,6 +3514,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v8, 0xffff, v2
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v49, 0xffff, v1
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v47, 0xffff, v0
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(11)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v54, 16, v30
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v52, 16, v29
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v58, 16, v28
@@ -3522,6 +3523,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v51, 0xffff, v29
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v57, 0xffff, v28
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v55, 0xffff, v27
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(10)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v30, 16, v34
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v28, 16, v33
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v62, 16, v32
@@ -3530,6 +3532,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v27, 0xffff, v33
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v61, 0xffff, v32
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v59, 0xffff, v31
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(9)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v34, 16, v38
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v32, 16, v37
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v7, 16, v36
@@ -3538,6 +3541,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v31, 0xffff, v37
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v6, 0xffff, v36
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v4, 0xffff, v35
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(8)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v38, 16, v42
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v36, 16, v41
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v3, 16, v40
@@ -3563,7 +3567,6 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[16:19], off, s[0:3], 0 offset:32
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[23:26], off, s[0:3], 0 offset:48
; GCN-NOHSA-SI-NEXT: buffer_load_dword v0, off, s[12:15], 0 offset:16 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v1, off, s[12:15], 0 offset:20 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: buffer_load_dword v2, off, s[12:15], 0 offset:24 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
@@ -3572,7 +3575,6 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[0:3], off, s[0:3], 0
; GCN-NOHSA-SI-NEXT: s_waitcnt expcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v0, off, s[12:15], 0 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: buffer_load_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
@@ -3806,7 +3808,6 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v17, 0xffff, v15
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v15, 0xffff, v14
; GCN-NOHSA-VI-NEXT: buffer_store_dword v15, off, s[88:91], 0 ; 4-byte Folded Spill
-; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-VI-NEXT: buffer_store_dword v16, off, s[88:91], 0 offset:4 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v17, off, s[88:91], 0 offset:8 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v18, off, s[88:91], 0 offset:12 ; 4-byte Folded Spill
@@ -3815,10 +3816,10 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v20, 0xffff, v13
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v18, 0xffff, v12
; GCN-NOHSA-VI-NEXT: buffer_store_dword v18, off, s[88:91], 0 offset:16 ; 4-byte Folded Spill
-; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-VI-NEXT: buffer_store_dword v19, off, s[88:91], 0 offset:20 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v20, off, s[88:91], 0 offset:24 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v21, off, s[88:91], 0 offset:28 ; 4-byte Folded Spill
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(14)
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v26, 16, v11
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v24, 16, v10
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v19, 16, v9
@@ -3827,6 +3828,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v23, 0xffff, v10
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v18, 0xffff, v9
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v16, 0xffff, v8
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(12)
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v11, 16, v3
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v9, 16, v2
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v50, 16, v1
@@ -3835,6 +3837,7 @@ define amdgpu_kernel void @global_zextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v8, 0xffff, v2
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v49, 0xffff, v1
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v47, 0xffff, v0
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(8)
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v3, 16, v40
; GCN-NOHSA-VI-NEXT: v_lshrrev_b32_e32 v1, 16, v39
; GCN-NOHSA-VI-NEXT: v_and_b32_e32 v2, 0xffff, v40
@@ -4294,7 +4297,6 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v2, v11, 0, 16
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v0, v10, 0, 16
; GCN-NOHSA-SI-NEXT: buffer_store_dword v0, off, s[12:15], 0 ; 4-byte Folded Spill
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_store_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v3, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -4302,6 +4304,7 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v5, 16, v8
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v6, v9, 0, 16
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v4, v8, 0, 16
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(6)
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v11, 16, v35
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v9, 16, v34
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v10, v35, 0, 16
@@ -4310,6 +4313,7 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v13, 16, v32
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v14, v33, 0, 16
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v12, v32, 0, 16
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(5)
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v35, 16, v39
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v33, 16, v38
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v34, v39, 0, 16
@@ -4318,6 +4322,7 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v45, 16, v36
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v46, v37, 0, 16
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v44, v36, 0, 16
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(4)
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v39, 16, v43
; GCN-NOHSA-SI-NEXT: v_ashrrev_i32_e32 v37, 16, v42
; GCN-NOHSA-SI-NEXT: v_bfe_i32 v38, v43, 0, 16
@@ -4375,7 +4380,6 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[8:11], off, s[0:3], 0 offset:48
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[4:7], off, s[0:3], 0
; GCN-NOHSA-SI-NEXT: buffer_load_dword v0, off, s[12:15], 0 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: buffer_load_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
@@ -4609,7 +4613,6 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v17, v15, 0, 16
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v15, v14, 0, 16
; GCN-NOHSA-VI-NEXT: buffer_store_dword v15, off, s[88:91], 0 ; 4-byte Folded Spill
-; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-VI-NEXT: buffer_store_dword v16, off, s[88:91], 0 offset:4 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v17, off, s[88:91], 0 offset:8 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v18, off, s[88:91], 0 offset:12 ; 4-byte Folded Spill
@@ -4618,10 +4621,10 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v15, v13, 0, 16
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v13, v12, 0, 16
; GCN-NOHSA-VI-NEXT: buffer_store_dword v13, off, s[88:91], 0 offset:16 ; 4-byte Folded Spill
-; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-VI-NEXT: buffer_store_dword v14, off, s[88:91], 0 offset:20 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v15, off, s[88:91], 0 offset:24 ; 4-byte Folded Spill
; GCN-NOHSA-VI-NEXT: buffer_store_dword v16, off, s[88:91], 0 offset:28 ; 4-byte Folded Spill
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(14)
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v19, 16, v11
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v17, 16, v10
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v18, v11, 0, 16
@@ -4630,6 +4633,7 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v40, 16, v8
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v41, v9, 0, 16
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v39, v8, 0, 16
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(12)
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v11, 16, v3
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v9, 16, v2
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v10, v3, 0, 16
@@ -4638,6 +4642,7 @@ define amdgpu_kernel void @global_sextload_v64i16_to_v64i32(ptr addrspace(1) %ou
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v48, 16, v0
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v49, v1, 0, 16
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v47, v0, 0, 16
+; GCN-NOHSA-VI-NEXT: s_waitcnt vmcnt(8)
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v3, 16, v36
; GCN-NOHSA-VI-NEXT: v_ashrrev_i32_e32 v1, 16, v35
; GCN-NOHSA-VI-NEXT: v_bfe_i32 v2, v36, 0, 16
@@ -7277,7 +7282,6 @@ define amdgpu_kernel void @global_zextload_v32i16_to_v32i64(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v2, 16, v14
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v0, 0xffff, v14
; GCN-NOHSA-SI-NEXT: buffer_store_dword v0, off, s[12:15], 0 ; 4-byte Folded Spill
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_store_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v3, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -7293,6 +7297,7 @@ define amdgpu_kernel void @global_zextload_v32i16_to_v32i64(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v16, 0xffff, v19
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v44, 16, v21
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v42, 0xffff, v21
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(5)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v48, 16, v22
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v46, 0xffff, v22
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v22, 16, v24
@@ -7301,6 +7306,7 @@ define amdgpu_kernel void @global_zextload_v32i16_to_v32i64(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v50, 0xffff, v23
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v56, 16, v25
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v54, 0xffff, v25
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(4)
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v40, 16, v29
; GCN-NOHSA-SI-NEXT: v_lshrrev_b32_e32 v60, 16, v26
; GCN-NOHSA-SI-NEXT: v_and_b32_e32 v58, 0xffff, v26
@@ -7341,19 +7347,17 @@ define amdgpu_kernel void @global_zextload_v32i16_to_v32i64(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: v_mov_b32_e32 v13, v39
; GCN-NOHSA-SI-NEXT: v_mov_b32_e32 v15, v39
; GCN-NOHSA-SI-NEXT: buffer_store_dword v12, off, s[12:15], 0 offset:16 ; 4-byte Folded Spill
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_store_dword v13, off, s[12:15], 0 offset:20 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v14, off, s[12:15], 0 offset:24 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: buffer_store_dword v15, off, s[12:15], 0 offset:28 ; 4-byte Folded Spill
; GCN-NOHSA-SI-NEXT: s_waitcnt expcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v12, off, s[12:15], 0 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v13, off, s[12:15], 0 offset:4 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: buffer_load_dword v14, off, s[12:15], 0 offset:8 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v15, off, s[12:15], 0 offset:12 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: v_mov_b32_e32 v13, v39
+; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: v_mov_b32_e32 v15, v39
; GCN-NOHSA-SI-NEXT: s_mov_b32 s0, s4
; GCN-NOHSA-SI-NEXT: s_mov_b32 s1, s5
@@ -7372,7 +7376,6 @@ define amdgpu_kernel void @global_zextload_v32i16_to_v32i64(ptr addrspace(1) %ou
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[4:7], off, s[0:3], 0 offset:96
; GCN-NOHSA-SI-NEXT: buffer_store_dwordx4 v[8:11], off, s[0:3], 0 offset:64
; GCN-NOHSA-SI-NEXT: buffer_load_dword v0, off, s[12:15], 0 offset:16 ; 4-byte Folded Reload
-; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
; GCN-NOHSA-SI-NEXT: buffer_load_dword v1, off, s[12:15], 0 offset:20 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: buffer_load_dword v2, off, s[12:15], 0 offset:24 ; 4-byte Folded Reload
; GCN-NOHSA-SI-NEXT: s_waitcnt vmcnt(0)
diff --git a/llvm/test/CodeGen/AMDGPU/load-global-i32.ll b/llvm/test/CodeGen/AMDGPU/load-global-i32.ll
index 7cdf270810dea0..5ae2b91bdb3e7c 100644
--- a/llvm/test/CodeGen/AMDGPU/load-global-i32.ll
+++ b/llvm/test/CodeGen/AMDGPU/load-global-i32.ll
@@ -3032,10 +3032,10 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v44, v30
; SI-NOHSA-NEXT: v_mov_b32_e32 v46, v31
; SI-NOHSA-NEXT: buffer_store_dword v44, off, s[12:15], 0 ; 4-byte Folded Spill
-; SI-NOHSA-NEXT: s_waitcnt vmcnt(0)
; SI-NOHSA-NEXT: buffer_store_dword v45, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; SI-NOHSA-NEXT: buffer_store_dword v46, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; SI-NOHSA-NEXT: buffer_store_dword v47, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(9)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v15, 31, v7
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v13, 31, v6
; SI-NOHSA-NEXT: s_waitcnt expcnt(0)
@@ -3045,6 +3045,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v46, v5
; SI-NOHSA-NEXT: v_mov_b32_e32 v12, v6
; SI-NOHSA-NEXT: v_mov_b32_e32 v14, v7
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(8)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v7, 31, v3
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v5, 31, v2
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v51, 31, v1
@@ -3053,6 +3054,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v50, v1
; SI-NOHSA-NEXT: v_mov_b32_e32 v4, v2
; SI-NOHSA-NEXT: v_mov_b32_e32 v6, v3
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(7)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v3, 31, v19
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v1, 31, v18
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v55, 31, v17
@@ -3061,6 +3063,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v54, v17
; SI-NOHSA-NEXT: v_mov_b32_e32 v0, v18
; SI-NOHSA-NEXT: v_mov_b32_e32 v2, v19
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(6)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v19, 31, v23
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v17, 31, v22
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v59, 31, v21
@@ -3069,6 +3072,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v58, v21
; SI-NOHSA-NEXT: v_mov_b32_e32 v16, v22
; SI-NOHSA-NEXT: v_mov_b32_e32 v18, v23
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(5)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v23, 31, v27
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v21, 31, v26
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v63, 31, v25
@@ -3077,6 +3081,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: v_mov_b32_e32 v62, v25
; SI-NOHSA-NEXT: v_mov_b32_e32 v20, v26
; SI-NOHSA-NEXT: v_mov_b32_e32 v22, v27
+; SI-NOHSA-NEXT: s_waitcnt vmcnt(4)
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v27, 31, v11
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v25, 31, v10
; SI-NOHSA-NEXT: v_ashrrev_i32_e32 v31, 31, v9
@@ -3091,7 +3096,6 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; SI-NOHSA-NEXT: buffer_store_dwordx4 v[36:39], off, s[0:3], 0 offset:240
; SI-NOHSA-NEXT: buffer_store_dwordx4 v[32:35], off, s[0:3], 0 offset:192
; SI-NOHSA-NEXT: buffer_load_dword v8, off, s[12:15], 0 ; 4-byte Folded Reload
-; SI-NOHSA-NEXT: s_waitcnt vmcnt(0)
; SI-NOHSA-NEXT: buffer_load_dword v9, off, s[12:15], 0 offset:4 ; 4-byte Folded Reload
; SI-NOHSA-NEXT: buffer_load_dword v10, off, s[12:15], 0 offset:8 ; 4-byte Folded Reload
; SI-NOHSA-NEXT: s_waitcnt vmcnt(0)
@@ -3614,10 +3618,11 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v4, v0
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v6, v1
; GCN-GFX900-HSA-NEXT: buffer_store_dword v25, off, s[16:19], 0 ; 4-byte Folded Spill
-; GCN-GFX900-HSA-NEXT: s_waitcnt vmcnt(0)
+; GCN-GFX900-HSA-NEXT: s_nop 0
; GCN-GFX900-HSA-NEXT: buffer_store_dword v26, off, s[16:19], 0 offset:4 ; 4-byte Folded Spill
; GCN-GFX900-HSA-NEXT: buffer_store_dword v27, off, s[16:19], 0 offset:8 ; 4-byte Folded Spill
; GCN-GFX900-HSA-NEXT: buffer_store_dword v28, off, s[16:19], 0 offset:12 ; 4-byte Folded Spill
+; GCN-GFX900-HSA-NEXT: s_waitcnt vmcnt(7)
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v28, 31, v12
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v26, 31, v11
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v40, 31, v10
@@ -3626,6 +3631,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v39, v10
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v25, v11
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v27, v12
+; GCN-GFX900-HSA-NEXT: s_waitcnt vmcnt(6)
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v12, 31, v16
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v10, 31, v15
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v44, 31, v14
@@ -3634,6 +3640,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v43, v14
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v9, v15
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v11, v16
+; GCN-GFX900-HSA-NEXT: s_waitcnt vmcnt(5)
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v16, 31, v20
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v14, 31, v19
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v48, 31, v18
@@ -3643,6 +3650,7 @@ define amdgpu_kernel void @global_sextload_v32i32_to_v32i64(ptr addrspace(1) %ou
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v13, v19
; GCN-GFX900-HSA-NEXT: global_load_dwordx4 v[49:52], v8, s[2:3] offset:16
; GCN-GFX900-HSA-NEXT: v_mov_b32_e32 v15, v20
+; GCN-GFX900-HSA-NEXT: s_waitcnt vmcnt(5)
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v20, 31, v24
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v18, 31, v23
; GCN-GFX900-HSA-NEXT: v_ashrrev_i32_e32 v56, 31, v22
diff --git a/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands-non-ptr-intrinsics.ll b/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands-non-ptr-intrinsics.ll
index 06ebd86b795107..85d342bf303c08 100644
--- a/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands-non-ptr-intrinsics.ll
+++ b/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands-non-ptr-intrinsics.ll
@@ -162,12 +162,13 @@ define float @mubuf_vgpr(<4 x i32> %i, i32 %c) #0 {
; W64-O0-NEXT: v_mov_b32_e32 v3, v6
; W64-O0-NEXT: v_mov_b32_e32 v4, v5
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
; W64-O0-NEXT: s_mov_b32 s4, 0
+; W64-O0-NEXT: s_waitcnt vmcnt(4)
; W64-O0-NEXT: v_writelane_b32 v0, s4, 0
; W64-O0-NEXT: s_mov_b64 s[4:5], exec
; W64-O0-NEXT: v_writelane_b32 v0, s4, 1
@@ -183,13 +184,16 @@ define float @mubuf_vgpr(<4 x i32> %i, i32 %c) #0 {
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -524,7 +528,7 @@ define void @mubuf_vgpr_adjacent_in_block(<4 x i32> %i, <4 x i32> %j, i32 %c, pt
; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_mov_b32_e32 v16, v4
; W64-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
@@ -537,7 +541,7 @@ define void @mubuf_vgpr_adjacent_in_block(<4 x i32> %i, <4 x i32> %j, i32 %c, pt
; W64-O0-NEXT: v_mov_b32_e32 v5, v8
; W64-O0-NEXT: v_mov_b32_e32 v6, v7
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
@@ -545,21 +549,24 @@ define void @mubuf_vgpr_adjacent_in_block(<4 x i32> %i, <4 x i32> %j, i32 %c, pt
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v3, v12
+; W64-O0-NEXT: s_waitcnt vmcnt(10)
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr1 killed $vgpr1 def $vgpr1_vgpr2 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v2, v10
+; W64-O0-NEXT: s_waitcnt vmcnt(11)
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
; W64-O0-NEXT: s_mov_b32 s4, 0
+; W64-O0-NEXT: s_waitcnt vmcnt(12)
; W64-O0-NEXT: v_writelane_b32 v0, s4, 0
; W64-O0-NEXT: s_mov_b64 s[4:5], exec
; W64-O0-NEXT: v_writelane_b32 v0, s4, 1
@@ -575,13 +582,16 @@ define void @mubuf_vgpr_adjacent_in_block(<4 x i32> %i, <4 x i32> %j, i32 %c, pt
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:24 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:28 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -643,13 +653,16 @@ define void @mubuf_vgpr_adjacent_in_block(<4 x i32> %i, <4 x i32> %j, i32 %c, pt
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:44 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -1055,7 +1068,7 @@ define void @mubuf_vgpr_outside_entry(<4 x i32> %i, <4 x i32> %j, i32 %c, ptr ad
; W64-O0-NEXT: v_mov_b32_e32 v8, v11
; W64-O0-NEXT: v_mov_b32_e32 v9, v10
; W64-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
@@ -1063,11 +1076,13 @@ define void @mubuf_vgpr_outside_entry(<4 x i32> %i, <4 x i32> %j, i32 %c, ptr ad
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v6, v12
+; W64-O0-NEXT: s_waitcnt vmcnt(7)
; W64-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
+; W64-O0-NEXT: s_waitcnt vmcnt(7)
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
@@ -1076,6 +1091,7 @@ define void @mubuf_vgpr_outside_entry(<4 x i32> %i, <4 x i32> %j, i32 %c, ptr ad
; W64-O0-NEXT: s_mov_b32 s4, 17
; W64-O0-NEXT: ;;#ASMEND
; W64-O0-NEXT: s_mov_b32 s5, s4
+; W64-O0-NEXT: s_waitcnt vmcnt(10)
; W64-O0-NEXT: v_writelane_b32 v0, s5, 0
; W64-O0-NEXT: s_mov_b32 s5, 0
; W64-O0-NEXT: v_writelane_b32 v0, s5, 1
@@ -1095,13 +1111,16 @@ define void @mubuf_vgpr_outside_entry(<4 x i32> %i, <4 x i32> %j, i32 %c, ptr ad
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:44 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -1191,13 +1210,16 @@ define void @mubuf_vgpr_outside_entry(<4 x i32> %i, <4 x i32> %j, i32 %c, ptr ad
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:20 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
diff --git a/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands.ll b/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands.ll
index 2591ff4bd2538a..42ed4c1f2e63d4 100644
--- a/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands.ll
+++ b/llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands.ll
@@ -175,13 +175,14 @@ define float @mubuf_vgpr(ptr addrspace(8) %i, i32 %c) #0 {
; W64-O0-NEXT: v_mov_b32_e32 v3, v6
; W64-O0-NEXT: v_mov_b32_e32 v4, v5
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: s_mov_b32 s4, 0
+; W64-O0-NEXT: s_waitcnt vmcnt(4)
; W64-O0-NEXT: v_writelane_b32 v0, s4, 0
; W64-O0-NEXT: s_mov_b64 s[4:5], exec
; W64-O0-NEXT: v_writelane_b32 v0, s4, 1
@@ -197,13 +198,16 @@ define float @mubuf_vgpr(ptr addrspace(8) %i, i32 %c) #0 {
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -549,7 +553,7 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: v_mov_b32_e32 v15, v7
; W64-O0-NEXT: v_mov_b32_e32 v16, v6
; W64-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
@@ -574,7 +578,7 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: v_mov_b32_e32 v5, v8
; W64-O0-NEXT: v_mov_b32_e32 v6, v7
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
@@ -582,15 +586,17 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v3, v12
+; W64-O0-NEXT: s_waitcnt vmcnt(10)
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr1 killed $vgpr1 def $vgpr1_vgpr2 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v2, v10
+; W64-O0-NEXT: s_waitcnt vmcnt(11)
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
@@ -599,6 +605,7 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: s_mov_b32 s4, 0
+; W64-O0-NEXT: s_waitcnt vmcnt(12)
; W64-O0-NEXT: v_writelane_b32 v0, s4, 0
; W64-O0-NEXT: s_mov_b64 s[4:5], exec
; W64-O0-NEXT: v_writelane_b32 v0, s4, 1
@@ -614,13 +621,16 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:24 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:28 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -682,13 +692,16 @@ define void @mubuf_vgpr_adjacent_in_block(ptr addrspace(8) %i, ptr addrspace(8)
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:44 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -1101,7 +1114,7 @@ define void @mubuf_vgpr_outside_entry(ptr addrspace(8) %i, ptr addrspace(8) %j,
; W64-O0-NEXT: v_mov_b32_e32 v10, v6
; W64-O0-NEXT: v_mov_b32_e32 v11, v4
; W64-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
@@ -1112,26 +1125,29 @@ define void @mubuf_vgpr_outside_entry(ptr addrspace(8) %i, ptr addrspace(8) %j,
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr3 killed $vgpr3 def $vgpr3_vgpr4 killed $exec
+; W64-O0-NEXT: s_waitcnt vmcnt(6)
; W64-O0-NEXT: v_mov_b32_e32 v4, v2
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; implicit-def: $sgpr4
; W64-O0-NEXT: ; kill: def $vgpr1 killed $vgpr1 def $vgpr1_vgpr2 killed $exec
; W64-O0-NEXT: v_mov_b32_e32 v2, v12
; W64-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
; W64-O0-NEXT: ; implicit-def: $sgpr4_sgpr5
+; W64-O0-NEXT: s_waitcnt vmcnt(9)
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; W64-O0-NEXT: ;;#ASMSTART
; W64-O0-NEXT: s_mov_b32 s4, 17
; W64-O0-NEXT: ;;#ASMEND
; W64-O0-NEXT: s_mov_b32 s5, s4
+; W64-O0-NEXT: s_waitcnt vmcnt(10)
; W64-O0-NEXT: v_writelane_b32 v0, s5, 0
; W64-O0-NEXT: s_mov_b32 s5, 0
; W64-O0-NEXT: v_writelane_b32 v0, s5, 1
@@ -1151,13 +1167,16 @@ define void @mubuf_vgpr_outside_entry(ptr addrspace(8) %i, ptr addrspace(8) %j,
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:44 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
@@ -1246,7 +1265,7 @@ define void @mubuf_vgpr_outside_entry(ptr addrspace(8) %i, ptr addrspace(8) %j,
; W64-O0-NEXT: v_mov_b32_e32 v3, v6
; W64-O0-NEXT: v_mov_b32_e32 v4, v5
; W64-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_nop 0
; W64-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
; W64-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
@@ -1268,13 +1287,16 @@ define void @mubuf_vgpr_outside_entry(ptr addrspace(8) %i, ptr addrspace(8) %j,
; W64-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:84 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:88 ; 4-byte Folded Reload
; W64-O0-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:92 ; 4-byte Folded Reload
-; W64-O0-NEXT: s_waitcnt vmcnt(0)
+; W64-O0-NEXT: s_waitcnt vmcnt(3)
; W64-O0-NEXT: v_readfirstlane_b32 s8, v1
+; W64-O0-NEXT: s_waitcnt vmcnt(2)
; W64-O0-NEXT: v_readfirstlane_b32 s12, v2
; W64-O0-NEXT: s_mov_b32 s4, s8
; W64-O0-NEXT: s_mov_b32 s5, s12
; W64-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], s[4:5], v[1:2]
+; W64-O0-NEXT: s_waitcnt vmcnt(1)
; W64-O0-NEXT: v_readfirstlane_b32 s7, v3
+; W64-O0-NEXT: s_waitcnt vmcnt(0)
; W64-O0-NEXT: v_readfirstlane_b32 s6, v4
; W64-O0-NEXT: s_mov_b32 s10, s7
; W64-O0-NEXT: s_mov_b32 s11, s6
diff --git a/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll b/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
index fbe34a3a3970bd..bbeb2e1884a9ff 100644
--- a/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
+++ b/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
@@ -44,7 +44,7 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX906-NEXT: v_writelane_b32 v41, s31, 1
; GFX906-NEXT: v_mov_b32_e32 v32, v31
; GFX906-NEXT: buffer_store_dword v0, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v1, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
; GFX906-NEXT: v_writelane_b32 v2, s5, 11
; GFX906-NEXT: s_or_saveexec_b64 s[34:35], -1
@@ -54,7 +54,7 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX906-NEXT: ; def v[0:31]
; GFX906-NEXT: ;;#ASMEND
; GFX906-NEXT: buffer_store_dword v0, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v1, off, s[0:3], s33 offset:20 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:24 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:28 ; 4-byte Folded Spill
@@ -425,7 +425,7 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX908-NEXT: v_writelane_b32 v2, s4, 10
; GFX908-NEXT: v_mov_b32_e32 v32, v31
; GFX908-NEXT: buffer_store_dword v0, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
-; GFX908-NEXT: s_waitcnt vmcnt(0)
+; GFX908-NEXT: s_nop 0
; GFX908-NEXT: buffer_store_dword v1, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
; GFX908-NEXT: v_writelane_b32 v2, s5, 11
; GFX908-NEXT: s_or_saveexec_b64 s[34:35], -1
@@ -435,7 +435,7 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX908-NEXT: ; def v[0:31]
; GFX908-NEXT: ;;#ASMEND
; GFX908-NEXT: buffer_store_dword v0, off, s[0:3], s33 offset:20 ; 4-byte Folded Spill
-; GFX908-NEXT: s_waitcnt vmcnt(0)
+; GFX908-NEXT: s_nop 0
; GFX908-NEXT: buffer_store_dword v1, off, s[0:3], s33 offset:24 ; 4-byte Folded Spill
; GFX908-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:28 ; 4-byte Folded Spill
; GFX908-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:32 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/rem_i128.ll b/llvm/test/CodeGen/AMDGPU/rem_i128.ll
index fe093d4ac8515e..fd6e06afc67da9 100644
--- a/llvm/test/CodeGen/AMDGPU/rem_i128.ll
+++ b/llvm/test/CodeGen/AMDGPU/rem_i128.ll
@@ -282,16 +282,17 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v13
; GFX9-O0-NEXT: v_ashrrev_i64 v[3:4], s4, v[3:4]
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:100 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v1
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v2, v13
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
+; GFX9-O0-NEXT: s_waitcnt vmcnt(4)
; GFX9-O0-NEXT: v_writelane_b32 v0, s6, 0
; GFX9-O0-NEXT: v_writelane_b32 v0, s7, 1
; GFX9-O0-NEXT: s_mov_b32 s10, s6
@@ -371,42 +372,42 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v6
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v5
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v16
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v17
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v18
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v19
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v18
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v19
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v6
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v5
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v16
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v17
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v14, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v19
@@ -521,14 +522,14 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v9
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; kill: def $vgpr8 killed $vgpr8 def $vgpr8_vgpr9 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v9, v7
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[8:9], v[8:9], s[6:7]
; GFX9-O0-NEXT: s_mov_b64 s[12:13], 0x7f
@@ -576,10 +577,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-O0-NEXT: s_and_b64 s[6:7], s[4:5], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], exec
; GFX9-O0-NEXT: v_writelane_b32 v0, s4, 4
@@ -610,16 +611,19 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:176 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_5
; GFX9-O0-NEXT: .LBB0_3: ; %Flow2
@@ -636,10 +640,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_9
; GFX9-O0-NEXT: .LBB0_4: ; %udiv-loop-exit
@@ -676,10 +680,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_3
; GFX9-O0-NEXT: .LBB0_5: ; %Flow1
@@ -700,16 +704,16 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:120 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_4
; GFX9-O0-NEXT: .LBB0_6: ; %udiv-do-while
@@ -794,11 +798,12 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v10, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v23
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v24
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v11, v14
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v15
; GFX9-O0-NEXT: v_sub_co_u32_e32 v13, vcc, v13, v6
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_subb_co_u32_e32 v12, vcc, v12, v10, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v11, vcc, v11, v4, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v7, vcc, v7, v5, vcc
@@ -884,22 +889,22 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v2
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v15
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v14
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], s[4:5]
; GFX9-O0-NEXT: v_writelane_b32 v16, s6, 6
@@ -911,28 +916,28 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[22:23]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-O0-NEXT: s_cbranch_execnz .LBB0_6
@@ -957,7 +962,7 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v20, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v21, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v22, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
-; GFX9-O0-NEXT: s_waitcnt vmcnt(9)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[6:7], v4, v[21:22]
@@ -1030,10 +1035,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v17
; GFX9-O0-NEXT: s_mov_b64 s[8:9], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:296 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:300 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:304 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], s[6:7]
; GFX9-O0-NEXT: v_mov_b32_e32 v15, s9
@@ -1046,28 +1051,28 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[22:23]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB0_6
; GFX9-O0-NEXT: .LBB0_8: ; %udiv-bb1
@@ -1084,7 +1089,7 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 1
; GFX9-O0-NEXT: s_mov_b32 s5, s6
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v1
; GFX9-O0-NEXT: s_mov_b32 s4, s7
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
@@ -1095,6 +1100,7 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s5
; GFX9-O0-NEXT: v_add_co_u32_e32 v9, vcc, v4, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s4
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_addc_co_u32_e32 v2, vcc, v2, v5, vcc
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s8
; GFX9-O0-NEXT: v_addc_co_u32_e32 v1, vcc, v1, v5, vcc
@@ -1111,12 +1117,12 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v1
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:324 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:328 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v10
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:332 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:336 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b32 s4, 0x7f
; GFX9-O0-NEXT: v_sub_u32_e64 v3, s4, v4
@@ -1164,10 +1170,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr7 killed $vgpr7 def $vgpr7_vgpr8 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v3
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:316 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:320 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:308 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:312 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v10
@@ -1184,16 +1190,16 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v1, s6
; GFX9-O0-NEXT: v_mov_b32_e32 v2, s7
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], exec
; GFX9-O0-NEXT: s_and_b64 s[4:5], s[6:7], s[4:5]
@@ -1230,9 +1236,10 @@ define i128 @v_srem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-O0-NEXT: v_lshrrev_b64 v[0:1], s4, v[5:6]
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v0
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v17
; GFX9-O0-NEXT: v_mul_lo_u32 v3, v1, v0
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[17:18], s4, v[17:18]
; GFX9-O0-NEXT: v_mov_b32_e32 v2, v17
; GFX9-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 killed $vgpr5_vgpr6 killed $exec
@@ -1756,42 +1763,43 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v14
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:92 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:96 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:84 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:88 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v12
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:80 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(7)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v1
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v12
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v1
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v14
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v12
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v2
@@ -1802,6 +1810,7 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr1 killed $vgpr1 def $vgpr1_vgpr2 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v2, v3
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
+; GFX9-O0-NEXT: s_waitcnt vmcnt(16)
; GFX9-O0-NEXT: v_writelane_b32 v0, s6, 0
; GFX9-O0-NEXT: v_writelane_b32 v0, s7, 1
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[4:5], v[1:2], s[6:7]
@@ -1911,14 +1920,14 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr5 killed $vgpr5 def $vgpr5_vgpr6 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v9
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; implicit-def: $sgpr8
; GFX9-O0-NEXT: ; kill: def $vgpr8 killed $vgpr8 def $vgpr8_vgpr9 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v9, v7
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_cmp_eq_u64_e64 s[8:9], v[8:9], s[6:7]
; GFX9-O0-NEXT: s_mov_b64 s[12:13], 0x7f
@@ -1966,10 +1975,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v5
; GFX9-O0-NEXT: s_and_b64 s[6:7], s[4:5], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], exec
; GFX9-O0-NEXT: v_writelane_b32 v0, s4, 2
@@ -2000,16 +2009,19 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:164 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
+; GFX9-O0-NEXT: s_waitcnt vmcnt(6)
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_5
; GFX9-O0-NEXT: .LBB1_3: ; %Flow2
@@ -2026,10 +2038,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:168 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:172 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_9
; GFX9-O0-NEXT: .LBB1_4: ; %udiv-loop-exit
@@ -2066,10 +2078,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v4
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_3
; GFX9-O0-NEXT: .LBB1_5: ; %Flow1
@@ -2090,16 +2102,16 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:108 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:192 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:196 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:208 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:212 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:200 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:204 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_4
; GFX9-O0-NEXT: .LBB1_6: ; %udiv-do-while
@@ -2184,11 +2196,12 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v10, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v23
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v24
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v11
; GFX9-O0-NEXT: v_mov_b32_e32 v11, v14
; GFX9-O0-NEXT: v_mov_b32_e32 v7, v15
; GFX9-O0-NEXT: v_sub_co_u32_e32 v13, vcc, v13, v6
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_subb_co_u32_e32 v12, vcc, v12, v10, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v11, vcc, v11, v4, vcc
; GFX9-O0-NEXT: v_subb_co_u32_e32 v7, vcc, v7, v5, vcc
@@ -2274,22 +2287,22 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v2
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:136 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:140 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v1
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v0
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:144 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:148 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v15
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v14
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:152 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:156 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v18, v13
; GFX9-O0-NEXT: v_mov_b32_e32 v17, v12
; GFX9-O0-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:160 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v18, off, s[0:3], s32 offset:164 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], s[4:5]
; GFX9-O0-NEXT: v_writelane_b32 v16, s6, 4
@@ -2301,28 +2314,28 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[18:19]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-O0-NEXT: s_cbranch_execnz .LBB1_6
@@ -2347,7 +2360,7 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v20, off, s[0:3], s32 offset:48 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v21, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
; GFX9-O0-NEXT: buffer_load_dword v22, off, s[0:3], s32 offset:40 ; 4-byte Folded Reload
-; GFX9-O0-NEXT: s_waitcnt vmcnt(9)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(10)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v10
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[6:7], v4, v[21:22]
@@ -2420,10 +2433,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v13, v17
; GFX9-O0-NEXT: s_mov_b64 s[8:9], s[6:7]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:280 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:284 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:288 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:292 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[4:5], s[6:7]
; GFX9-O0-NEXT: v_mov_b32_e32 v15, s9
@@ -2436,28 +2449,28 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_store_dword v16, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[18:19]
; GFX9-O0-NEXT: buffer_store_dword v14, off, s[0:3], s32 offset:272 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:276 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:264 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:268 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v10, off, s[0:3], s32 offset:256 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:260 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:248 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:252 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:240 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:244 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:232 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:236 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:224 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:228 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:216 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:220 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_branch .LBB1_6
; GFX9-O0-NEXT: .LBB1_8: ; %udiv-bb1
@@ -2474,7 +2487,7 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: buffer_load_dword v2, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 1
; GFX9-O0-NEXT: s_mov_b32 s5, s6
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v1
; GFX9-O0-NEXT: s_mov_b32 s4, s7
; GFX9-O0-NEXT: s_mov_b64 s[6:7], 0
@@ -2485,6 +2498,7 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s5
; GFX9-O0-NEXT: v_add_co_u32_e32 v9, vcc, v4, v5
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s4
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_addc_co_u32_e32 v2, vcc, v2, v5, vcc
; GFX9-O0-NEXT: v_mov_b32_e32 v5, s8
; GFX9-O0-NEXT: v_addc_co_u32_e32 v1, vcc, v1, v5, vcc
@@ -2501,12 +2515,12 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v1
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:312 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:316 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v5, v9
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v10
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:320 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:324 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b32 s4, 0x7f
; GFX9-O0-NEXT: v_sub_u32_e64 v3, s4, v4
@@ -2554,10 +2568,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: ; kill: def $vgpr7 killed $vgpr7 def $vgpr7_vgpr8 killed $exec
; GFX9-O0-NEXT: v_mov_b32_e32 v8, v3
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:304 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:308 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:296 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:300 ; 4-byte Folded Spill
; GFX9-O0-NEXT: v_mov_b32_e32 v4, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v10
@@ -2574,16 +2588,16 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: v_mov_b32_e32 v1, s6
; GFX9-O0-NEXT: v_mov_b32_e32 v2, s7
; GFX9-O0-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:128 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:132 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:120 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:124 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:112 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:116 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:104 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:108 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 s[6:7], exec
; GFX9-O0-NEXT: s_and_b64 s[4:5], s[6:7], s[4:5]
@@ -2616,9 +2630,10 @@ define i128 @v_urem_i128_vv(i128 %lhs, i128 %rhs) {
; GFX9-O0-NEXT: s_waitcnt vmcnt(2)
; GFX9-O0-NEXT: v_lshrrev_b64 v[2:3], s4, v[7:8]
; GFX9-O0-NEXT: v_mov_b32_e32 v6, v2
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_waitcnt vmcnt(1)
; GFX9-O0-NEXT: v_mov_b32_e32 v2, v13
; GFX9-O0-NEXT: v_mul_lo_u32 v5, v6, v2
+; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: v_lshrrev_b64 v[13:14], s4, v[13:14]
; GFX9-O0-NEXT: v_mov_b32_e32 v3, v13
; GFX9-O0-NEXT: ; kill: def $vgpr7 killed $vgpr7 killed $vgpr7_vgpr8 killed $exec
diff --git a/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll b/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
index f523b4a2495f19..b2f5b6aa7fe36a 100644
--- a/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
+++ b/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
@@ -1316,7 +1316,6 @@ define void @spill_sgpr_no_free_vgpr(ptr addrspace(1) %out, ptr addrspace(1) %in
; GCN-NEXT: flat_load_dwordx4 v[6:9], v[2:3]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:452 ; 4-byte Folded Spill
-; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:456 ; 4-byte Folded Spill
; GCN-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:460 ; 4-byte Folded Spill
; GCN-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:464 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/spill-offset-calculation.ll b/llvm/test/CodeGen/AMDGPU/spill-offset-calculation.ll
index 55238b284efce5..daf0a2d1baa88a 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-offset-calculation.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-offset-calculation.ll
@@ -282,7 +282,7 @@ define amdgpu_kernel void @test_sgpr_offset_subregs_kernel() {
; MUBUF-NEXT: buffer_load_dword v1, off, s[0:3], 0 offset:12 glc
; MUBUF-NEXT: s_waitcnt vmcnt(0)
; MUBUF-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4084 ; 4-byte Folded Spill
-; MUBUF-NEXT: s_waitcnt vmcnt(0)
+; MUBUF-NEXT: s_nop 0
; MUBUF-NEXT: buffer_store_dword v1, off, s[0:3], 0 offset:4088 ; 4-byte Folded Spill
; MUBUF-NEXT: ;;#ASMSTART
; MUBUF-NEXT: ;;#ASMEND
@@ -349,7 +349,7 @@ define amdgpu_kernel void @test_inst_offset_subregs_kernel() {
; MUBUF-NEXT: s_waitcnt vmcnt(0)
; MUBUF-NEXT: s_mov_b32 s4, 0x3ff00
; MUBUF-NEXT: buffer_store_dword v0, off, s[0:3], s4 ; 4-byte Folded Spill
-; MUBUF-NEXT: s_waitcnt vmcnt(0)
+; MUBUF-NEXT: s_nop 0
; MUBUF-NEXT: buffer_store_dword v1, off, s[0:3], s4 offset:4 ; 4-byte Folded Spill
; MUBUF-NEXT: ;;#ASMSTART
; MUBUF-NEXT: ;;#ASMEND
@@ -515,7 +515,7 @@ define void @test_sgpr_offset_subregs_function() {
; MUBUF-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:12 glc
; MUBUF-NEXT: s_waitcnt vmcnt(0)
; MUBUF-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:4084 ; 4-byte Folded Spill
-; MUBUF-NEXT: s_waitcnt vmcnt(0)
+; MUBUF-NEXT: s_nop 0
; MUBUF-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4088 ; 4-byte Folded Spill
; MUBUF-NEXT: ;;#ASMSTART
; MUBUF-NEXT: ;;#ASMEND
@@ -580,7 +580,7 @@ define void @test_inst_offset_subregs_function() {
; MUBUF-NEXT: s_waitcnt vmcnt(0)
; MUBUF-NEXT: s_add_i32 s4, s32, 0x3ff00
; MUBUF-NEXT: buffer_store_dword v0, off, s[0:3], s4 ; 4-byte Folded Spill
-; MUBUF-NEXT: s_waitcnt vmcnt(0)
+; MUBUF-NEXT: s_nop 0
; MUBUF-NEXT: buffer_store_dword v1, off, s[0:3], s4 offset:4 ; 4-byte Folded Spill
; MUBUF-NEXT: ;;#ASMSTART
; MUBUF-NEXT: ;;#ASMEND
diff --git a/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll b/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
index b9ad4615fcbcf1..0e68c306fb8b8e 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
@@ -53,7 +53,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s33, 0x4f900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:12 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:16 ; 4-byte Folded Spill
@@ -61,7 +60,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:16
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:20 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:24 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:28 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:32 ; 4-byte Folded Spill
@@ -69,7 +67,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:32
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:36 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:40 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:44 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:48 ; 4-byte Folded Spill
@@ -77,7 +74,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:48
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:52 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:56 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:60 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:64 ; 4-byte Folded Spill
@@ -85,7 +81,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:64
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:68 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:72 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:76 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:80 ; 4-byte Folded Spill
@@ -93,7 +88,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:80
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:84 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:88 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:92 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:96 ; 4-byte Folded Spill
@@ -101,7 +95,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:96
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:100 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:104 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:108 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:112 ; 4-byte Folded Spill
@@ -109,7 +102,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:112
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:116 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:120 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:124 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:128 ; 4-byte Folded Spill
@@ -117,7 +109,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:128
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:132 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:136 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:140 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:144 ; 4-byte Folded Spill
@@ -125,7 +116,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:144
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:148 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:152 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:156 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:160 ; 4-byte Folded Spill
@@ -133,7 +123,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:160
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:164 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:168 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:172 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:176 ; 4-byte Folded Spill
@@ -141,7 +130,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:176
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:180 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:184 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:188 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:192 ; 4-byte Folded Spill
@@ -149,7 +137,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:192
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:196 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:200 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:204 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:208 ; 4-byte Folded Spill
@@ -157,7 +144,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:208
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:212 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:216 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:220 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:224 ; 4-byte Folded Spill
@@ -165,7 +151,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:224
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:228 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:232 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:236 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:240 ; 4-byte Folded Spill
@@ -173,7 +158,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:240
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:244 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:248 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:252 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:256 ; 4-byte Folded Spill
@@ -181,7 +165,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:256
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:260 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:264 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:268 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:272 ; 4-byte Folded Spill
@@ -189,7 +172,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:272
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:276 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:280 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:284 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:288 ; 4-byte Folded Spill
@@ -197,7 +179,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:288
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:292 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:296 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:300 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:304 ; 4-byte Folded Spill
@@ -205,7 +186,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:304
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:308 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:312 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:316 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:320 ; 4-byte Folded Spill
@@ -213,7 +193,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:320
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:324 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:328 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:332 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:336 ; 4-byte Folded Spill
@@ -221,7 +200,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:336
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:340 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:344 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:348 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:352 ; 4-byte Folded Spill
@@ -229,7 +207,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:352
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:356 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:360 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:364 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:368 ; 4-byte Folded Spill
@@ -237,7 +214,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:368
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:372 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:376 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:380 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:384 ; 4-byte Folded Spill
@@ -245,7 +221,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:384
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:388 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:392 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:396 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:400 ; 4-byte Folded Spill
@@ -253,7 +228,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:400
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:404 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:408 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:412 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:416 ; 4-byte Folded Spill
@@ -261,7 +235,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:416
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:420 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:424 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:428 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:432 ; 4-byte Folded Spill
@@ -269,7 +242,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:432
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:436 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:440 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:444 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:448 ; 4-byte Folded Spill
@@ -277,7 +249,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:448
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:452 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:456 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:460 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:464 ; 4-byte Folded Spill
@@ -285,7 +256,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:464
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:468 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:472 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:476 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:480 ; 4-byte Folded Spill
@@ -293,7 +263,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:480
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:484 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:488 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:492 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:496 ; 4-byte Folded Spill
@@ -301,7 +270,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:496
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:500 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:504 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:508 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:512 ; 4-byte Folded Spill
@@ -309,7 +277,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:512
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:516 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:520 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:524 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:528 ; 4-byte Folded Spill
@@ -317,7 +284,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:528
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:532 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:536 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:540 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:544 ; 4-byte Folded Spill
@@ -325,7 +291,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:544
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:548 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:552 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:556 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:560 ; 4-byte Folded Spill
@@ -333,7 +298,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:560
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:564 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:568 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:572 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:576 ; 4-byte Folded Spill
@@ -341,7 +305,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:576
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:580 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:584 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:588 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:592 ; 4-byte Folded Spill
@@ -349,7 +312,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:592
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:596 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:600 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:604 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:608 ; 4-byte Folded Spill
@@ -357,7 +319,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:608
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:612 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:616 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:620 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:624 ; 4-byte Folded Spill
@@ -365,7 +326,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:624
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:628 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:632 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:636 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:640 ; 4-byte Folded Spill
@@ -373,7 +333,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:640
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:644 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:648 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:652 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:656 ; 4-byte Folded Spill
@@ -381,7 +340,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:656
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:660 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:664 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:668 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:672 ; 4-byte Folded Spill
@@ -389,7 +347,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:672
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:676 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:680 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:684 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:688 ; 4-byte Folded Spill
@@ -397,7 +354,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:688
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:692 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:696 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:700 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:704 ; 4-byte Folded Spill
@@ -405,7 +361,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:704
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:708 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:712 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:716 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:720 ; 4-byte Folded Spill
@@ -413,7 +368,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:720
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:724 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:728 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:732 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:736 ; 4-byte Folded Spill
@@ -421,7 +375,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:736
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:740 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:744 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:748 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:752 ; 4-byte Folded Spill
@@ -429,7 +382,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:752
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:756 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:760 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:764 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:768 ; 4-byte Folded Spill
@@ -437,7 +389,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:768
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:772 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:776 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:780 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:784 ; 4-byte Folded Spill
@@ -445,7 +396,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:784
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:788 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:792 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:796 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:800 ; 4-byte Folded Spill
@@ -453,7 +403,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:800
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:804 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:808 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:812 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:816 ; 4-byte Folded Spill
@@ -461,7 +410,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:816
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:820 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:824 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:828 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:832 ; 4-byte Folded Spill
@@ -469,7 +417,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:832
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:836 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:840 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:844 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:848 ; 4-byte Folded Spill
@@ -477,7 +424,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:848
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:852 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:856 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:860 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:864 ; 4-byte Folded Spill
@@ -485,7 +431,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:864
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:868 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:872 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:876 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:880 ; 4-byte Folded Spill
@@ -493,7 +438,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:880
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:884 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:888 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:892 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:896 ; 4-byte Folded Spill
@@ -501,7 +445,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:896
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:900 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:904 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:908 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:912 ; 4-byte Folded Spill
@@ -509,7 +452,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:912
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:916 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:920 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:924 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:928 ; 4-byte Folded Spill
@@ -517,7 +459,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:928
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:932 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:936 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:940 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:944 ; 4-byte Folded Spill
@@ -525,7 +466,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:944
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:948 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:952 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:956 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:960 ; 4-byte Folded Spill
@@ -533,7 +473,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:960
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:964 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:968 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:972 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:976 ; 4-byte Folded Spill
@@ -541,7 +480,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:976
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:980 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:984 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:988 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:992 ; 4-byte Folded Spill
@@ -549,7 +487,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:992
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:996 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1000 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1004 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1008 ; 4-byte Folded Spill
@@ -557,7 +494,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1008
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1012 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1016 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1020 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1024 ; 4-byte Folded Spill
@@ -565,7 +501,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1024
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1028 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1032 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1036 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1040 ; 4-byte Folded Spill
@@ -573,7 +508,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1040
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1044 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1048 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1052 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1056 ; 4-byte Folded Spill
@@ -581,7 +515,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1056
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1060 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1064 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1068 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1072 ; 4-byte Folded Spill
@@ -589,7 +522,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1072
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1076 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1080 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1084 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1088 ; 4-byte Folded Spill
@@ -597,7 +529,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1088
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1092 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1096 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1100 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1104 ; 4-byte Folded Spill
@@ -605,7 +536,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1104
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1108 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1112 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1116 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1120 ; 4-byte Folded Spill
@@ -613,7 +543,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1120
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1124 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1128 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1132 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1136 ; 4-byte Folded Spill
@@ -621,7 +550,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1136
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1140 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1144 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1148 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1152 ; 4-byte Folded Spill
@@ -629,7 +557,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1152
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1156 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1160 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1164 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1168 ; 4-byte Folded Spill
@@ -637,7 +564,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1168
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1172 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1176 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1180 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1184 ; 4-byte Folded Spill
@@ -645,7 +571,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1184
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1188 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1192 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1196 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1200 ; 4-byte Folded Spill
@@ -653,7 +578,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1200
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1204 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1208 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1212 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1216 ; 4-byte Folded Spill
@@ -661,7 +585,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1216
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1220 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1224 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1228 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1232 ; 4-byte Folded Spill
@@ -669,7 +592,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1232
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1236 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1240 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1244 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1248 ; 4-byte Folded Spill
@@ -677,7 +599,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1248
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1252 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1256 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1260 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1264 ; 4-byte Folded Spill
@@ -685,7 +606,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1264
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1268 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1272 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1276 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1280 ; 4-byte Folded Spill
@@ -693,7 +613,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1280
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1284 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1288 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1292 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1296 ; 4-byte Folded Spill
@@ -701,7 +620,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1296
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1300 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1304 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1308 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1312 ; 4-byte Folded Spill
@@ -709,7 +627,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1312
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1316 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1320 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1324 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1328 ; 4-byte Folded Spill
@@ -717,7 +634,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1328
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1332 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1336 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1340 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1344 ; 4-byte Folded Spill
@@ -725,7 +641,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1344
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1348 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1352 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1356 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1360 ; 4-byte Folded Spill
@@ -733,7 +648,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1360
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1364 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1368 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1372 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1376 ; 4-byte Folded Spill
@@ -741,7 +655,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1376
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1380 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1384 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1388 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1392 ; 4-byte Folded Spill
@@ -749,7 +662,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1392
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1396 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1400 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1404 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1408 ; 4-byte Folded Spill
@@ -757,7 +669,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1408
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1412 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1416 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1420 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1424 ; 4-byte Folded Spill
@@ -765,7 +676,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1424
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1428 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1432 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1436 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1440 ; 4-byte Folded Spill
@@ -773,7 +683,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1440
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1444 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1448 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1452 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1456 ; 4-byte Folded Spill
@@ -781,7 +690,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1456
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1460 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1464 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1468 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1472 ; 4-byte Folded Spill
@@ -789,7 +697,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1472
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1476 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1480 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1484 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1488 ; 4-byte Folded Spill
@@ -797,7 +704,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1488
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1492 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1496 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1500 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1504 ; 4-byte Folded Spill
@@ -805,7 +711,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1504
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1508 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1512 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1516 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1520 ; 4-byte Folded Spill
@@ -813,7 +718,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1520
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1524 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1528 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1532 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1536 ; 4-byte Folded Spill
@@ -821,7 +725,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1536
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1540 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1544 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1548 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1552 ; 4-byte Folded Spill
@@ -829,7 +732,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1552
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1556 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1560 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1564 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1568 ; 4-byte Folded Spill
@@ -837,7 +739,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1568
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1572 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1576 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1580 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1584 ; 4-byte Folded Spill
@@ -845,7 +746,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1584
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1588 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1592 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1596 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1600 ; 4-byte Folded Spill
@@ -853,7 +753,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1600
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1604 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1608 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1612 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1616 ; 4-byte Folded Spill
@@ -861,7 +760,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1616
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1620 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1624 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1628 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1632 ; 4-byte Folded Spill
@@ -869,7 +767,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1632
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1636 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1640 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1644 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1648 ; 4-byte Folded Spill
@@ -877,7 +774,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1648
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1652 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1656 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1660 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1664 ; 4-byte Folded Spill
@@ -885,7 +781,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1664
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1668 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1672 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1676 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1680 ; 4-byte Folded Spill
@@ -893,7 +788,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1680
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1684 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1688 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1692 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1696 ; 4-byte Folded Spill
@@ -901,7 +795,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1696
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1700 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1704 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1708 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1712 ; 4-byte Folded Spill
@@ -909,7 +802,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1712
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1716 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1720 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1724 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1728 ; 4-byte Folded Spill
@@ -917,7 +809,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1728
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1732 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1736 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1740 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1744 ; 4-byte Folded Spill
@@ -925,7 +816,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1744
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1748 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1752 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1756 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1760 ; 4-byte Folded Spill
@@ -933,7 +823,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1760
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1764 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1768 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1772 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1776 ; 4-byte Folded Spill
@@ -941,7 +830,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1776
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1780 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1784 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1788 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1792 ; 4-byte Folded Spill
@@ -949,7 +837,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1792
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1796 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1800 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1804 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1808 ; 4-byte Folded Spill
@@ -957,7 +844,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1808
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1812 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1816 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1820 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1824 ; 4-byte Folded Spill
@@ -965,7 +851,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1824
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1828 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1832 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1836 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1840 ; 4-byte Folded Spill
@@ -973,7 +858,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1840
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1844 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1848 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1852 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1856 ; 4-byte Folded Spill
@@ -981,7 +865,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1856
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1860 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1864 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1868 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1872 ; 4-byte Folded Spill
@@ -989,7 +872,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1872
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1876 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1880 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1884 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1888 ; 4-byte Folded Spill
@@ -997,7 +879,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1888
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1892 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1896 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1900 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1904 ; 4-byte Folded Spill
@@ -1005,7 +886,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1904
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1908 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1912 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1916 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1920 ; 4-byte Folded Spill
@@ -1013,7 +893,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1920
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1924 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1928 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1932 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1936 ; 4-byte Folded Spill
@@ -1021,7 +900,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1936
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1940 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1944 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1948 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1952 ; 4-byte Folded Spill
@@ -1029,7 +907,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1952
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1956 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1960 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1964 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1968 ; 4-byte Folded Spill
@@ -1037,7 +914,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1968
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1972 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1976 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1980 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:1984 ; 4-byte Folded Spill
@@ -1045,7 +921,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:1984
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:1988 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:1992 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:1996 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2000 ; 4-byte Folded Spill
@@ -1053,7 +928,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2004 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2008 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2012 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2016 ; 4-byte Folded Spill
@@ -1061,7 +935,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2016
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2020 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2024 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2028 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2032 ; 4-byte Folded Spill
@@ -1069,7 +942,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2032
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2036 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2040 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2044 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2048 ; 4-byte Folded Spill
@@ -1077,7 +949,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2048
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2052 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2056 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2060 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2064 ; 4-byte Folded Spill
@@ -1085,7 +956,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2064
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2068 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2072 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2076 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2080 ; 4-byte Folded Spill
@@ -1093,7 +963,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2080
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2084 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2088 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2092 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2096 ; 4-byte Folded Spill
@@ -1101,7 +970,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2096
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2100 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2104 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2108 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2112 ; 4-byte Folded Spill
@@ -1109,7 +977,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2112
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2116 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2120 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2124 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2128 ; 4-byte Folded Spill
@@ -1117,7 +984,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2128
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2132 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2136 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2140 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2144 ; 4-byte Folded Spill
@@ -1125,7 +991,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2144
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2148 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2152 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2156 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2160 ; 4-byte Folded Spill
@@ -1133,7 +998,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2160
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2164 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2168 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2172 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2176 ; 4-byte Folded Spill
@@ -1141,7 +1005,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2176
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2180 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2184 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2188 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2192 ; 4-byte Folded Spill
@@ -1149,7 +1012,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2192
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2196 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2200 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2204 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2208 ; 4-byte Folded Spill
@@ -1157,7 +1019,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2208
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2212 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2216 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2220 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2224 ; 4-byte Folded Spill
@@ -1165,7 +1026,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2224
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2228 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2232 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2236 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2240 ; 4-byte Folded Spill
@@ -1173,7 +1033,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2240
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2244 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2248 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2252 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2256 ; 4-byte Folded Spill
@@ -1181,7 +1040,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2256
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2260 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2264 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2268 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2272 ; 4-byte Folded Spill
@@ -1189,7 +1047,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2272
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2276 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2280 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2284 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2288 ; 4-byte Folded Spill
@@ -1197,7 +1054,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2288
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2292 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2296 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2300 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2304 ; 4-byte Folded Spill
@@ -1205,7 +1061,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2304
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2308 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2312 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2316 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2320 ; 4-byte Folded Spill
@@ -1213,7 +1068,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2320
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2324 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2328 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2332 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2336 ; 4-byte Folded Spill
@@ -1221,7 +1075,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2336
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2340 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2344 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2348 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2352 ; 4-byte Folded Spill
@@ -1229,7 +1082,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2352
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2356 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2360 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2364 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2368 ; 4-byte Folded Spill
@@ -1237,7 +1089,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2368
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2372 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2376 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2380 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2384 ; 4-byte Folded Spill
@@ -1245,7 +1096,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2384
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2388 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2392 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2396 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2400 ; 4-byte Folded Spill
@@ -1253,7 +1103,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2400
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2404 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2408 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2412 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2416 ; 4-byte Folded Spill
@@ -1261,7 +1110,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2416
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2420 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2424 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2428 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2432 ; 4-byte Folded Spill
@@ -1269,7 +1117,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2432
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2436 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2440 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2444 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2448 ; 4-byte Folded Spill
@@ -1277,7 +1124,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2448
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2452 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2456 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2460 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2464 ; 4-byte Folded Spill
@@ -1285,7 +1131,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2464
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2468 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2472 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2476 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2480 ; 4-byte Folded Spill
@@ -1293,7 +1138,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2480
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2484 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2488 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2492 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2496 ; 4-byte Folded Spill
@@ -1301,7 +1145,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2496
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2500 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2504 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2508 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2512 ; 4-byte Folded Spill
@@ -1309,7 +1152,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2512
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2516 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2520 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2524 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2528 ; 4-byte Folded Spill
@@ -1317,7 +1159,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2528
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2532 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2536 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2540 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2544 ; 4-byte Folded Spill
@@ -1325,7 +1166,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2544
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2548 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2552 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2556 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2560 ; 4-byte Folded Spill
@@ -1333,7 +1173,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2560
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2564 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2568 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2572 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2576 ; 4-byte Folded Spill
@@ -1341,7 +1180,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2576
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2580 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2584 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2588 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2592 ; 4-byte Folded Spill
@@ -1349,7 +1187,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2592
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2596 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2600 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2604 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2608 ; 4-byte Folded Spill
@@ -1357,7 +1194,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2608
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2612 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2616 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2620 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2624 ; 4-byte Folded Spill
@@ -1365,7 +1201,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2624
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2628 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2632 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2636 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2640 ; 4-byte Folded Spill
@@ -1373,7 +1208,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2640
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2644 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2648 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2652 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2656 ; 4-byte Folded Spill
@@ -1381,7 +1215,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2656
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2660 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2664 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2668 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2672 ; 4-byte Folded Spill
@@ -1389,7 +1222,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2672
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2676 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2680 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2684 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2688 ; 4-byte Folded Spill
@@ -1397,7 +1229,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2688
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2692 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2696 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2700 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2704 ; 4-byte Folded Spill
@@ -1405,7 +1236,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2704
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2708 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2712 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2716 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2720 ; 4-byte Folded Spill
@@ -1413,7 +1243,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2720
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2724 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2728 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2732 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2736 ; 4-byte Folded Spill
@@ -1421,7 +1250,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2736
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2740 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2744 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2748 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2752 ; 4-byte Folded Spill
@@ -1429,7 +1257,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2752
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2756 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2760 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2764 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2768 ; 4-byte Folded Spill
@@ -1437,7 +1264,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2768
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2772 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2776 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2780 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2784 ; 4-byte Folded Spill
@@ -1445,7 +1271,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2784
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2788 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2792 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2796 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2800 ; 4-byte Folded Spill
@@ -1453,7 +1278,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2800
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2804 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2808 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2812 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2816 ; 4-byte Folded Spill
@@ -1461,7 +1285,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2816
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2820 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2824 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2828 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2832 ; 4-byte Folded Spill
@@ -1469,7 +1292,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2832
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2836 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2840 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2844 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2848 ; 4-byte Folded Spill
@@ -1477,7 +1299,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2848
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2852 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2856 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2860 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2864 ; 4-byte Folded Spill
@@ -1485,7 +1306,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2864
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2868 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2872 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2876 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2880 ; 4-byte Folded Spill
@@ -1493,7 +1313,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2880
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2884 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2888 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2892 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2896 ; 4-byte Folded Spill
@@ -1501,7 +1320,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2896
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2900 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2904 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2908 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2912 ; 4-byte Folded Spill
@@ -1509,7 +1327,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2912
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2916 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2920 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2924 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2928 ; 4-byte Folded Spill
@@ -1517,7 +1334,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2928
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2932 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2936 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2940 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2944 ; 4-byte Folded Spill
@@ -1525,7 +1341,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2944
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2948 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2952 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2956 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2960 ; 4-byte Folded Spill
@@ -1533,7 +1348,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2960
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2964 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2968 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2972 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2976 ; 4-byte Folded Spill
@@ -1541,7 +1355,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2976
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2980 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:2984 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:2988 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:2992 ; 4-byte Folded Spill
@@ -1549,7 +1362,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:2992
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:2996 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3000 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3004 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3008 ; 4-byte Folded Spill
@@ -1557,7 +1369,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3008
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3012 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3016 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3020 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3024 ; 4-byte Folded Spill
@@ -1565,7 +1376,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3024
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3028 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3032 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3036 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3040 ; 4-byte Folded Spill
@@ -1573,7 +1383,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3040
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3044 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3048 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3052 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3056 ; 4-byte Folded Spill
@@ -1581,7 +1390,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3056
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3060 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3064 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3068 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3072 ; 4-byte Folded Spill
@@ -1589,7 +1397,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3072
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3076 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3080 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3084 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3088 ; 4-byte Folded Spill
@@ -1597,7 +1404,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3088
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3092 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3096 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3100 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3104 ; 4-byte Folded Spill
@@ -1605,7 +1411,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3104
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3108 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3112 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3116 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3120 ; 4-byte Folded Spill
@@ -1613,7 +1418,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3120
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3124 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3128 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3132 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3136 ; 4-byte Folded Spill
@@ -1621,7 +1425,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3136
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3140 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3144 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3148 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3152 ; 4-byte Folded Spill
@@ -1629,7 +1432,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3152
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3156 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3160 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3164 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3168 ; 4-byte Folded Spill
@@ -1637,7 +1439,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3168
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3172 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3176 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3180 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3184 ; 4-byte Folded Spill
@@ -1645,7 +1446,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3184
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3188 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3192 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3196 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3200 ; 4-byte Folded Spill
@@ -1653,7 +1453,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3200
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3204 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3208 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3212 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3216 ; 4-byte Folded Spill
@@ -1661,7 +1460,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3216
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3220 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3224 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3228 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3232 ; 4-byte Folded Spill
@@ -1669,7 +1467,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3232
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3236 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3240 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3244 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3248 ; 4-byte Folded Spill
@@ -1677,7 +1474,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3248
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3252 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3256 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3260 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3264 ; 4-byte Folded Spill
@@ -1685,7 +1481,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3264
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3268 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3272 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3276 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3280 ; 4-byte Folded Spill
@@ -1693,7 +1488,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3280
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3284 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3288 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3292 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3296 ; 4-byte Folded Spill
@@ -1701,7 +1495,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3296
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3300 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3304 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3308 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3312 ; 4-byte Folded Spill
@@ -1709,7 +1502,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3312
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3316 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3320 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3324 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3328 ; 4-byte Folded Spill
@@ -1717,7 +1509,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3328
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3332 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3336 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3340 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3344 ; 4-byte Folded Spill
@@ -1725,7 +1516,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3344
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3348 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3352 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3356 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3360 ; 4-byte Folded Spill
@@ -1733,7 +1523,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3360
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3364 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3368 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3372 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3376 ; 4-byte Folded Spill
@@ -1741,7 +1530,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3376
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3380 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3384 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3388 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3392 ; 4-byte Folded Spill
@@ -1749,7 +1537,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3392
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3396 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3400 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3404 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3408 ; 4-byte Folded Spill
@@ -1757,7 +1544,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3408
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3412 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3416 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3420 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3424 ; 4-byte Folded Spill
@@ -1765,7 +1551,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3424
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3428 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3432 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3436 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3440 ; 4-byte Folded Spill
@@ -1773,7 +1558,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3440
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3444 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3448 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3452 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3456 ; 4-byte Folded Spill
@@ -1781,7 +1565,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3456
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3460 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3464 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3468 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3472 ; 4-byte Folded Spill
@@ -1789,7 +1572,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3472
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3476 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3480 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3484 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3488 ; 4-byte Folded Spill
@@ -1797,7 +1579,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3488
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3492 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3496 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3500 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3504 ; 4-byte Folded Spill
@@ -1805,7 +1586,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3504
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3508 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3512 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3516 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3520 ; 4-byte Folded Spill
@@ -1813,7 +1593,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3520
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3524 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3528 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3532 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3536 ; 4-byte Folded Spill
@@ -1821,7 +1600,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3536
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3540 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3544 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3548 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3552 ; 4-byte Folded Spill
@@ -1829,7 +1607,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3552
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3556 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3560 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3564 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3568 ; 4-byte Folded Spill
@@ -1837,7 +1614,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3568
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3572 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3576 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3580 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3584 ; 4-byte Folded Spill
@@ -1845,7 +1621,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3584
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3588 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3592 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3596 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3600 ; 4-byte Folded Spill
@@ -1853,7 +1628,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3600
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3604 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3608 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3612 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3616 ; 4-byte Folded Spill
@@ -1861,7 +1635,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3616
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3620 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3624 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3628 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3632 ; 4-byte Folded Spill
@@ -1869,7 +1642,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3632
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3636 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3640 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3644 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3648 ; 4-byte Folded Spill
@@ -1877,7 +1649,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3648
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3652 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3656 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3660 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3664 ; 4-byte Folded Spill
@@ -1885,7 +1656,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3664
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3668 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3672 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3676 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3680 ; 4-byte Folded Spill
@@ -1893,7 +1663,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3680
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3684 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3688 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3692 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3696 ; 4-byte Folded Spill
@@ -1901,7 +1670,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3696
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3700 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3704 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3708 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3712 ; 4-byte Folded Spill
@@ -1909,7 +1677,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3712
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3716 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3720 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3724 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3728 ; 4-byte Folded Spill
@@ -1917,7 +1684,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3728
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3732 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3736 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3740 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3744 ; 4-byte Folded Spill
@@ -1925,7 +1691,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3744
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3748 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3752 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3756 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3760 ; 4-byte Folded Spill
@@ -1933,7 +1698,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3760
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3764 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3768 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3772 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3776 ; 4-byte Folded Spill
@@ -1941,7 +1705,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3776
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3780 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3784 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3788 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3792 ; 4-byte Folded Spill
@@ -1949,7 +1712,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3792
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3796 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3800 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3804 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3808 ; 4-byte Folded Spill
@@ -1957,7 +1719,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3808
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3812 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3816 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3820 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3824 ; 4-byte Folded Spill
@@ -1965,7 +1726,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3824
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3828 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3832 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3836 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3840 ; 4-byte Folded Spill
@@ -1973,7 +1733,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3840
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3844 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3848 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3852 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3856 ; 4-byte Folded Spill
@@ -1981,7 +1740,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3856
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3860 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3864 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3868 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3872 ; 4-byte Folded Spill
@@ -1989,7 +1747,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3872
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3876 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3880 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3884 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3888 ; 4-byte Folded Spill
@@ -1997,7 +1754,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3888
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3892 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3896 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3900 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3904 ; 4-byte Folded Spill
@@ -2005,7 +1761,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3904
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3908 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3912 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3916 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3920 ; 4-byte Folded Spill
@@ -2013,7 +1768,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3920
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3924 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3928 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3932 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3936 ; 4-byte Folded Spill
@@ -2021,7 +1775,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3936
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3940 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3944 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3948 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3952 ; 4-byte Folded Spill
@@ -2029,7 +1782,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3952
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3956 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3960 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3964 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3968 ; 4-byte Folded Spill
@@ -2037,7 +1789,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3968
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3972 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3976 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3980 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:3984 ; 4-byte Folded Spill
@@ -2045,7 +1796,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:3984
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:3988 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:3992 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:3996 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4000 ; 4-byte Folded Spill
@@ -2053,7 +1803,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:4000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4004 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:4008 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:4012 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4016 ; 4-byte Folded Spill
@@ -2061,7 +1810,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:4016
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4020 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:4024 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:4028 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4032 ; 4-byte Folded Spill
@@ -2069,7 +1817,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:4032
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4036 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:4040 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:4044 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4048 ; 4-byte Folded Spill
@@ -2077,7 +1824,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:4048
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4052 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:4056 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:4060 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4064 ; 4-byte Folded Spill
@@ -2085,7 +1831,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:4064
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], 0 offset:4068 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], 0 offset:4072 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], 0 offset:4076 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], 0 offset:4080 ; 4-byte Folded Spill
@@ -2094,7 +1839,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b64 s[4:5], 0x80
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2103,7 +1847,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x40100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2112,7 +1855,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x40500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2121,7 +1863,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x40900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2130,7 +1871,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x40d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2139,7 +1879,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x41100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2148,7 +1887,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x41500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2157,7 +1895,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x41900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2166,7 +1903,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x41d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2175,7 +1911,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x42100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2184,7 +1919,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x42500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2193,7 +1927,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x42900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2202,7 +1935,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x42d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2211,7 +1943,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x43100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2220,7 +1951,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x43500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2229,7 +1959,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x43900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2238,7 +1967,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x43d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2247,7 +1975,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x44100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2256,7 +1983,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x44500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2265,7 +1991,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x44900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2274,7 +1999,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x44d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2283,7 +2007,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x45100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2292,7 +2015,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x45500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2301,7 +2023,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x45900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2310,7 +2031,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x45d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2319,7 +2039,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x46100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2328,7 +2047,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x46500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2337,7 +2055,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x46900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2346,7 +2063,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x46d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2355,7 +2071,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x47100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2364,7 +2079,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x47500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2373,7 +2087,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x47900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2382,7 +2095,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x47d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2391,7 +2103,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x48100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2400,7 +2111,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x48500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2409,7 +2119,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x48900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2418,7 +2127,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x48d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2427,7 +2135,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x49100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2436,7 +2143,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x49500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2445,7 +2151,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x49900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2454,7 +2159,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x49d00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2463,7 +2167,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4a100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2472,7 +2175,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4a500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2481,7 +2183,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4a900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2490,7 +2191,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4ad00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2499,7 +2199,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4b100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2508,7 +2207,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4b500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2517,7 +2215,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4b900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2526,7 +2223,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4bd00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2535,7 +2231,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4c100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2544,7 +2239,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4c500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2553,7 +2247,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4c900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2562,7 +2255,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4cd00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2571,7 +2263,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4d100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2580,7 +2271,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4d500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2589,7 +2279,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4d900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2598,7 +2287,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4dd00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2607,7 +2295,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4e100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2616,7 +2303,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4e500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2625,7 +2311,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4e900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2634,7 +2319,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4ed00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2643,7 +2327,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4f100
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2652,7 +2335,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4f500
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -2661,7 +2343,6 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, ptr addrspace(1) %in) {
; GFX6-NEXT: s_mov_b32 s2, 0x4f900
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10102,7 +9783,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b64 s[8:9], exec
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10111,7 +9791,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x84000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10120,7 +9799,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x83c00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10129,7 +9807,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x83800
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10138,7 +9815,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x83400
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10147,7 +9823,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x83000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10156,7 +9831,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x82c00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10165,7 +9839,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x82800
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10174,7 +9847,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x82400
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10183,7 +9855,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x82000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10192,7 +9863,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x81c00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10201,7 +9871,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x81400
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v1, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v2, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10211,7 +9880,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x80c00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v7, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v8, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v9, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v10, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10220,7 +9888,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b32 s2, 0x81000
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v7, off, s[40:43], s2 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v8, off, s[40:43], s2 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v9, off, s[40:43], s2 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v10, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
@@ -10244,7 +9911,6 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: v_add_i32_e32 v4, vcc, 16, v4
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v7, off, s[40:43], s0 ; 4-byte Folded Spill
-; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v8, off, s[40:43], s0 offset:4 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v9, off, s[40:43], s0 offset:8 ; 4-byte Folded Spill
; GFX6-NEXT: buffer_store_dword v10, off, s[40:43], s0 offset:12 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/spill-wait.mir b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
new file mode 100644
index 00000000000000..8b8fbd1b3f06f9
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
@@ -0,0 +1,25 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx90a -run-pass si-insert-waitcnts %s -o - | FileCheck -check-prefix=GCN %s
+
+# There shall be no S_WAITCNT between two stores.
+
+---
+name: spill_vgpr_tuple
+
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1, $sgpr76_sgpr77_sgpr78_sgpr79
+
+ ; GCN-LABEL: name: spill_vgpr_tuple
+ ; GCN: liveins: $vgpr0_vgpr1, $sgpr76_sgpr77_sgpr78_sgpr79
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: $vgpr64_vgpr65 = V_MOV_B64_e32 $vgpr0_vgpr1, implicit $exec
+ ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr64, $sgpr76_sgpr77_sgpr78_sgpr79, 0, 672, 0, 0, implicit $exec, implicit-def $vgpr64_vgpr65, implicit $vgpr64_vgpr65
+ ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET $vgpr65, $sgpr76_sgpr77_sgpr78_sgpr79, 0, 676, 0, 0, implicit $exec, implicit $vgpr64_vgpr65
+ ; GCN-NEXT: S_ENDPGM 0
+ $vgpr64_vgpr65 = V_MOV_B64_e32 $vgpr0_vgpr1, implicit $exec
+ BUFFER_STORE_DWORD_OFFSET killed $vgpr64, $sgpr76_sgpr77_sgpr78_sgpr79, 0, 672, 0, 0, implicit $exec, implicit-def $vgpr64_vgpr65, implicit $vgpr64_vgpr65
+ BUFFER_STORE_DWORD_OFFSET $vgpr65, $sgpr76_sgpr77_sgpr78_sgpr79, 0, 676, 0, 0, implicit $exec, implicit $vgpr64_vgpr65
+ S_ENDPGM 0
+...
diff --git a/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll b/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
index 33c06e5d1e3a5e..2d5e5a9160fdf7 100644
--- a/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
+++ b/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
@@ -255,7 +255,7 @@ define amdgpu_kernel void @v256i8_liveout(ptr addrspace(1) %src1, ptr addrspace(
; GFX906-NEXT: v_mov_b32_e32 v4, 0
; GFX906-NEXT: s_waitcnt vmcnt(0)
; GFX906-NEXT: buffer_store_dword v5, off, s[12:15], 0 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v6, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v7, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v8, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
@@ -281,7 +281,7 @@ define amdgpu_kernel void @v256i8_liveout(ptr addrspace(1) %src1, ptr addrspace(
; GFX906-NEXT: global_load_dwordx4 v[0:3], v61, s[6:7] offset:240
; GFX906-NEXT: s_waitcnt vmcnt(0)
; GFX906-NEXT: buffer_store_dword v0, off, s[12:15], 0 ; 4-byte Folded Spill
-; GFX906-NEXT: s_waitcnt vmcnt(0)
+; GFX906-NEXT: s_nop 0
; GFX906-NEXT: buffer_store_dword v1, off, s[12:15], 0 offset:4 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v2, off, s[12:15], 0 offset:8 ; 4-byte Folded Spill
; GFX906-NEXT: buffer_store_dword v3, off, s[12:15], 0 offset:12 ; 4-byte Folded Spill
diff --git a/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll b/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
index b35ef6497f14ac..c295a056eb9e74 100644
--- a/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
+++ b/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
@@ -167,7 +167,7 @@ define amdgpu_gfx void @strict_wwm_cfg(ptr addrspace(8) inreg %tmp14, i32 %arg)
; GFX9-O0-NEXT: buffer_load_dwordx2 v[4:5], off, s[36:39], s34
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr36_sgpr37
; GFX9-O0-NEXT: ; implicit-def: $sgpr36_sgpr37
@@ -548,13 +548,13 @@ define amdgpu_gfx void @strict_wwm_call_i64(ptr addrspace(8) inreg %tmp14, i64 i
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:20 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v8, off, s[0:3], s33 offset:24 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v9, off, s[0:3], s33 offset:28 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s33 offset:32 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s33 offset:36 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:40 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:44 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[0:3], s33 offset:48 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[0:3], s33 offset:52 ; 4-byte Folded Spill
@@ -686,7 +686,7 @@ define amdgpu_gfx void @strict_wwm_call_i64(ptr addrspace(8) inreg %tmp14, i64 i
; GFX9-O3-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
; GFX9-O3-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
; GFX9-O3-NEXT: buffer_store_dword v2, off, s[0:3], s33 offset:20 ; 4-byte Folded Spill
-; GFX9-O3-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O3-NEXT: s_nop 0
; GFX9-O3-NEXT: buffer_store_dword v3, off, s[0:3], s33 offset:24 ; 4-byte Folded Spill
; GFX9-O3-NEXT: s_mov_b64 exec, s[34:35]
; GFX9-O3-NEXT: v_writelane_b32 v8, s30, 0
@@ -747,7 +747,7 @@ define amdgpu_gfx void @strict_wwm_amdgpu_cs_main(<4 x i32> inreg %desc, i32 %in
; GFX9-O0-NEXT: buffer_store_dword v1, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, s[34:35]
; GFX9-O0-NEXT: s_mov_b32 s36, s4
@@ -845,13 +845,13 @@ define amdgpu_gfx void @strict_wwm_amdgpu_cs_main(<4 x i32> inreg %desc, i32 %in
; GFX9-O3-NEXT: s_xor_saveexec_b64 s[34:35], -1
; GFX9-O3-NEXT: buffer_store_dword v1, off, s[0:3], s32 ; 4-byte Folded Spill
; GFX9-O3-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GFX9-O3-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O3-NEXT: s_nop 0
; GFX9-O3-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GFX9-O3-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GFX9-O3-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O3-NEXT: s_nop 0
; GFX9-O3-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
; GFX9-O3-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
-; GFX9-O3-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O3-NEXT: s_nop 0
; GFX9-O3-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
; GFX9-O3-NEXT: s_mov_b64 exec, s[34:35]
; GFX9-O3-NEXT: v_lshlrev_b32_e32 v0, 5, v0
@@ -921,7 +921,7 @@ define amdgpu_gfx <32 x i32> @strict_wwm_callee_saves(<32 x i32> inreg %keep, pt
; GFX9-O0-NEXT: buffer_store_dword v32, off, s[0:3], s32 offset:176 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v33, off, s[0:3], s32 offset:180 ; 4-byte Folded Spill
; GFX9-O0-NEXT: buffer_store_dword v33, off, s[0:3], s32 offset:184 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v34, off, s[0:3], s32 offset:188 ; 4-byte Folded Spill
; GFX9-O0-NEXT: s_mov_b64 exec, -1
; GFX9-O0-NEXT: buffer_store_dword v47, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
@@ -1286,7 +1286,7 @@ define amdgpu_gfx <32 x i32> @strict_wwm_callee_saves(<32 x i32> inreg %keep, pt
; GFX9-O3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-O3-NEXT: s_xor_saveexec_b64 s[34:35], -1
; GFX9-O3-NEXT: buffer_store_dword v32, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
-; GFX9-O3-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O3-NEXT: s_nop 0
; GFX9-O3-NEXT: buffer_store_dword v33, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
; GFX9-O3-NEXT: s_mov_b64 exec, s[34:35]
; GFX9-O3-NEXT: buffer_load_dword v26, off, s[0:3], s32
diff --git a/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll b/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
index 7fecab068396e0..ee9174822a9602 100644
--- a/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
+++ b/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
@@ -144,7 +144,7 @@ define amdgpu_cs void @cfg(ptr addrspace(8) inreg %tmp14, i32 %arg) {
; GFX9-O0-NEXT: buffer_load_dwordx2 v[4:5], off, s[4:7], s0
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[16:19], 0 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[16:19], 0 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr2_sgpr3
; GFX9-O0-NEXT: ; implicit-def: $sgpr2_sgpr3
@@ -1037,7 +1037,7 @@ define amdgpu_cs void @strict_wwm_cfg(ptr addrspace(8) inreg %tmp14, i32 %arg) {
; GFX9-O0-NEXT: buffer_load_dwordx2 v[4:5], off, s[4:7], s0
; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
; GFX9-O0-NEXT: buffer_store_dword v4, off, s[16:19], 0 offset:12 ; 4-byte Folded Spill
-; GFX9-O0-NEXT: s_waitcnt vmcnt(0)
+; GFX9-O0-NEXT: s_nop 0
; GFX9-O0-NEXT: buffer_store_dword v5, off, s[16:19], 0 offset:16 ; 4-byte Folded Spill
; GFX9-O0-NEXT: ; implicit-def: $sgpr2_sgpr3
; GFX9-O0-NEXT: ; implicit-def: $sgpr2_sgpr3
>From 8bb64cff788f1fef2f355d07ec3b2d8a86a3f89e Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Thu, 12 Sep 2024 01:42:17 -0700
Subject: [PATCH 2/5] Added comment
---
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index ced1d0c508ebc8..b702481e7fe395 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -901,6 +901,13 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
}
} else /* LGKM_CNT || EXP_CNT || VS_CNT || NUM_INST_CNTS */ {
// Match the score to the destination registers.
+ // Check only explicit operands. Stores, especially spill stores, include
+ // implicit uses and defs of their super registers which would create an
+ // artificial dependency, while these are there only for register liveness
+ // accounting purposes.
+ // Special cases where implicit register defs and uses exists, such as
+ // M0, FLAT_SCR or VCC, but there is no way to load these registers from
+ // memory, so these do not need tracking.
for (unsigned I = 0, E = Inst.getNumExplicitOperands(); I != E; ++I) {
auto &Op = Inst.getOperand(I);
if (!Op.isReg() || !Op.isDef())
>From 7dc5435f287d5ed50680d3a144d42cfa2e00c2c8 Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Thu, 12 Sep 2024 12:50:01 -0700
Subject: [PATCH 3/5] Added test with vcc load and updated comment.
---
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 6 +++++-
llvm/test/CodeGen/AMDGPU/spill-wait.mir | 22 +++++++++++++++++++++
2 files changed, 27 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index b702481e7fe395..61414361d54dbd 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -901,13 +901,17 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
}
} else /* LGKM_CNT || EXP_CNT || VS_CNT || NUM_INST_CNTS */ {
// Match the score to the destination registers.
+ //
// Check only explicit operands. Stores, especially spill stores, include
// implicit uses and defs of their super registers which would create an
// artificial dependency, while these are there only for register liveness
// accounting purposes.
+ //
// Special cases where implicit register defs and uses exists, such as
// M0, FLAT_SCR or VCC, but there is no way to load these registers from
- // memory, so these do not need tracking.
+ // memory except VCC, and no VALU instructions implicetly useing VCC may
+ // come to this place, so these do not need tracking. Memory instructions
+ // also do not implicetly define any of these registers.
for (unsigned I = 0, E = Inst.getNumExplicitOperands(); I != E; ++I) {
auto &Op = Inst.getOperand(I);
if (!Op.isReg() || !Op.isDef())
diff --git a/llvm/test/CodeGen/AMDGPU/spill-wait.mir b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
index 8b8fbd1b3f06f9..acb51876f60f8e 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-wait.mir
+++ b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
@@ -23,3 +23,25 @@ body: |
BUFFER_STORE_DWORD_OFFSET $vgpr65, $sgpr76_sgpr77_sgpr78_sgpr79, 0, 676, 0, 0, implicit $exec, implicit $vgpr64_vgpr65
S_ENDPGM 0
...
+
+# Make sure that while ignoring implicit operands we will not ignore implicit $vcc on VALU
+
+---
+name: load_vcc_wait
+
+body: |
+ bb.0:
+ liveins: $vgpr0, $sgpr10_sgpr11
+
+ ; GCN-LABEL: name: load_vcc_wait
+ ; GCN: liveins: $vgpr0, $sgpr10_sgpr11
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: $vcc_lo = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ ; GCN-NEXT: S_WAITCNT 49279
+ ; GCN-NEXT: $vgpr1 = V_ADDC_U32_e32 0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+ ; GCN-NEXT: S_ENDPGM 0
+ $vcc_lo = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ $vgpr1 = V_ADDC_U32_e32 0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+ S_ENDPGM 0
+...
>From 8f207390c34a72ecdc1248fe3327106fe4c7012a Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Thu, 12 Sep 2024 12:56:27 -0700
Subject: [PATCH 4/5] Fix comment spelling.
---
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 61414361d54dbd..5e7d23a0db2235 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -909,9 +909,9 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
//
// Special cases where implicit register defs and uses exists, such as
// M0, FLAT_SCR or VCC, but there is no way to load these registers from
- // memory except VCC, and no VALU instructions implicetly useing VCC may
+ // memory except VCC, and no VALU instructions implicitly using VCC may
// come to this place, so these do not need tracking. Memory instructions
- // also do not implicetly define any of these registers.
+ // also do not implicitly define any of these registers.
for (unsigned I = 0, E = Inst.getNumExplicitOperands(); I != E; ++I) {
auto &Op = Inst.getOperand(I);
if (!Op.isReg() || !Op.isDef())
>From e26f5e829c3b738b3946a6f981e88a27d1df3212 Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Fri, 13 Sep 2024 12:42:17 -0700
Subject: [PATCH 5/5] Added test with loading flat_scr
Simplified and updated comment.
---
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 6 +--
llvm/test/CodeGen/AMDGPU/spill-wait.mir | 42 +++++++++++++++++++++
2 files changed, 44 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 5e7d23a0db2235..b855b6b3107029 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -908,10 +908,8 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
// accounting purposes.
//
// Special cases where implicit register defs and uses exists, such as
- // M0, FLAT_SCR or VCC, but there is no way to load these registers from
- // memory except VCC, and no VALU instructions implicitly using VCC may
- // come to this place, so these do not need tracking. Memory instructions
- // also do not implicitly define any of these registers.
+ // M0, FLAT_SCR or VCC, but the wait will be generated earlier in the
+ // generateWaitcntInstBefore() if that was loaded from memory.
for (unsigned I = 0, E = Inst.getNumExplicitOperands(); I != E; ++I) {
auto &Op = Inst.getOperand(I);
if (!Op.isReg() || !Op.isDef())
diff --git a/llvm/test/CodeGen/AMDGPU/spill-wait.mir b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
index acb51876f60f8e..8e896252af89b4 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-wait.mir
+++ b/llvm/test/CodeGen/AMDGPU/spill-wait.mir
@@ -45,3 +45,45 @@ body: |
$vgpr1 = V_ADDC_U32_e32 0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
S_ENDPGM 0
...
+
+# Make sure that while ignoring implicit operands we will not ignore implicit $flat_src on FLAT
+
+---
+name: load_flat_scr_lo_flat_load_wait
+
+body: |
+ bb.0:
+ liveins: $sgpr10_sgpr11, $vgpr0_vgpr1
+
+ ; GCN-LABEL: name: load_flat_scr_lo_flat_load_wait
+ ; GCN: liveins: $sgpr10_sgpr11, $vgpr0_vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: $flat_scr_lo = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ ; GCN-NEXT: S_WAITCNT 49279
+ ; GCN-NEXT: $vgpr2 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GCN-NEXT: S_ENDPGM 0
+ $flat_scr_lo = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ $vgpr2 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ S_ENDPGM 0
+...
+
+---
+name: load_flat_scr_lo_scratch_store_wait
+
+body: |
+ bb.0:
+ liveins: $sgpr10_sgpr11, $vgpr0, $sgpr32
+
+ ; GCN-LABEL: name: load_flat_scr_lo_scratch_store_wait
+ ; GCN: liveins: $sgpr10_sgpr11, $vgpr0, $sgpr32
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: $flat_scr_hi = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ ; GCN-NEXT: S_WAITCNT 49279
+ ; GCN-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr
+ ; GCN-NEXT: S_ENDPGM 0
+ $flat_scr_hi = S_LOAD_DWORD_IMM $sgpr10_sgpr11, 0, 0
+ SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr
+ S_ENDPGM 0
+...
More information about the llvm-commits
mailing list