[AMDGPU] Add an AMDGPU specific atomic optimizer.

This commit adds a new IR level pass to the AMDGPU backend to perform
atomic optimizations. It works by:

- Running through a function and finding atomicrmw add/sub or uses of
  the atomic buffer intrinsics for add/sub.
- If all arguments except the value to be added/subtracted are uniform,
  record the value to be optimized.
- Run through the atomic operations we can optimize and, depending on
  whether the value is uniform/divergent use wavefront wide operations
  (DPP in the divergent case) to calculate the total amount to be
  atomically added/subtracted.
- Then let only a single lane of each wavefront perform the atomic
  operation, reducing the total number of atomic operations in flight.
- Lastly we recombine the result from the single lane to each lane of
  the wavefront, and calculate our individual lanes offset into the
  final result.

Differential Revision: https://reviews.llvm.org/D51969

llvm-svn: 343973

14 files changed, 822 insertions, 28 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/atomic_load_add.ll b/llvm/test/CodeGen/AMDGPU/atomic_load_add.ll
index 6b18fe0200d..76090b73bc3 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_load_add.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_load_add.ll
@@ -1,7 +1,7 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=R600,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false < %s | FileCheck -check-prefixes=R600,FUNC %s
 
 ; FUNC-LABEL: {{^}}atomic_add_local:
 ; SICIVI: s_mov_b32 m0
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_load_sub.ll b/llvm/test/CodeGen/AMDGPU/atomic_load_sub.ll
index 1d6fe169e10..b48ed36dfc2 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_load_sub.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_load_sub.ll
@@ -1,7 +1,7 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -enable-var-scope -check-prefixes=R600,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false < %s | FileCheck -enable-var-scope -check-prefixes=R600,FUNC %s
 
 ; FUNC-LABEL: {{^}}atomic_sub_local:
 ; SICIVI: s_mov_b32 m0
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
new file mode 100644
index 00000000000..c4b814041c8
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
@@ -0,0 +1,129 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.buffer.atomic.add(i32, <4 x i32>, i32, i32, i1)
+declare i32 @llvm.amdgcn.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i1)
+
+; Show that what the atomic optimization pass will do for raw buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
new file mode 100644
index 00000000000..2e51aba5f69
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
@@ -0,0 +1,189 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+
+; Show that what the atomic optimization pass will do for global pointers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+  %old = atomicrmw add i32 addrspace(1)* %inout, i32 5 acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %additive) {
+entry:
+  %old = atomicrmw add i32 addrspace(1)* %inout, i32 %additive acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = atomicrmw add i32 addrspace(1)* %inout, i32 %lane acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+  %old = atomicrmw add i64 addrspace(1)* %inout, i64 5 acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %additive) {
+entry:
+  %old = atomicrmw add i64 addrspace(1)* %inout, i64 %additive acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %zext = zext i32 %lane to i64
+  %old = atomicrmw add i64 addrspace(1)* %inout, i64 %zext acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+  %old = atomicrmw sub i32 addrspace(1)* %inout, i32 5 acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %subitive) {
+entry:
+  %old = atomicrmw sub i32 addrspace(1)* %inout, i32 %subitive acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = atomicrmw sub i32 addrspace(1)* %inout, i32 %lane acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+  %old = atomicrmw sub i64 addrspace(1)* %inout, i64 5 acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %subitive) {
+entry:
+  %old = atomicrmw sub i64 addrspace(1)* %inout, i64 %subitive acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %zext = zext i32 %lane to i64
+  %old = atomicrmw sub i64 addrspace(1)* %inout, i64 %zext acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
new file mode 100644
index 00000000000..849e2b61803
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
@@ -0,0 +1,192 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+
+@local_var32 = addrspace(3) global i32 undef, align 4
+@local_var64 = addrspace(3) global i64 undef, align 8
+
+; Show that what the atomic optimization pass will do for local pointers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out) {
+entry:
+  %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 5 acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 %additive) {
+entry:
+  %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %additive acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
+entry:
+  %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 5 acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 %additive) {
+entry:
+  %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %additive acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: ds_add_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %zext = zext i32 %lane to i64
+  %old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %zext acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out) {
+entry:
+  %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 5 acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 %subitive) {
+entry:
+  %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %subitive acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
+define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %lane acq_rel
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
+define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
+entry:
+  %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 5 acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 %subitive) {
+entry:
+  %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %subitive acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i64_varying:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: ds_sub_rtn_u64 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v{{[0-9]+}}, v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
+define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %zext = zext i32 %lane to i64
+  %old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %zext acq_rel
+  store i64 %old, i64 addrspace(1)* %out
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
new file mode 100644
index 00000000000..3e71e02ebfa
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
@@ -0,0 +1,129 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32)
+
+; Show that what the atomic optimization pass will do for raw buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
new file mode 100644
index 00000000000..dab6cbbe8a9
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
@@ -0,0 +1,155 @@
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare i32 @llvm.amdgcn.struct.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32, i32)
+declare i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32, i32)
+
+; Show that what the atomic optimization pass will do for struct buffers.
+
+; GCN-LABEL: add_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
+entry:
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_vindex:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: add_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_add v{{[0-9]+}}
+define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_constant:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_uniform:
+; GCN: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
+; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
+; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
+; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
+; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
+; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
+; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GCN: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
+entry:
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_sub v[[value]]
+define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_vindex:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_vindex(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: sub_i32_varying_offset:
+; GCN-NOT: v_mbcnt_lo_u32_b32
+; GCN-NOT: v_mbcnt_hi_u32_b32
+; GCN-NOT: s_bcnt1_i32_b64
+; GCN: buffer_atomic_sub v{{[0-9]+}}
+define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 0, i32 %lane, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics.ll b/llvm/test/CodeGen/AMDGPU/global_atomics.ll
index 1c22c375bc5..031f17f1385 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics.ll
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
 
 ; GCN-LABEL: {{^}}atomic_add_i32_offset:
 ; SIVI: buffer_atomic_add v{{[0-9]+}}, off, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:16{{$}}
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll
index e63b5a9de22..3a26b84c223 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
 
 ; GCN-LABEL: {{^}}atomic_add_i64_offset:
 ; CIVI: buffer_atomic_add_x2 v{{\[[0-9]+:[0-9]+\]}}, off, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:32{{$}}
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
index 0ce7d3efe45..b8700b00cc4 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
 
 ;CHECK-LABEL: {{^}}test1:
 ;CHECK-NOT: s_waitcnt
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
index 03def71d591..cb29e5a6ec6 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
 
 ;CHECK-LABEL: {{^}}test1:
 ;CHECK-NOT: s_waitcnt
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
index 271e8681b38..dd9f6457df0 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
@@ -1,5 +1,5 @@
-;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
-;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
+;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
 
 ;CHECK-LABEL: {{^}}test1:
 ;CHECK-NOT: s_waitcnt
diff --git a/llvm/test/CodeGen/AMDGPU/local-atomics.ll b/llvm/test/CodeGen/AMDGPU/local-atomics.ll
index d2167f5a730..9cf4e6a131e 100644
--- a/llvm/test/CodeGen/AMDGPU/local-atomics.ll
+++ b/llvm/test/CodeGen/AMDGPU/local-atomics.ll
@@ -1,8 +1,8 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,SICIVI,FUNC %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=EG,FUNC %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,SICIVI,FUNC %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,FUNC %s
+; RUN: llc -march=r600 -mcpu=redwood -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=EG,FUNC %s
 
 ; FUNC-LABEL: {{^}}lds_atomic_xchg_ret_i32:
 ; EG: LDS_WRXCHG_RET *
diff --git a/llvm/test/CodeGen/AMDGPU/local-atomics64.ll b/llvm/test/CodeGen/AMDGPU/local-atomics64.ll
index 6155bfcf1ae..fc7f9f7615a 100644
--- a/llvm/test/CodeGen/AMDGPU/local-atomics64.ll
+++ b/llvm/test/CodeGen/AMDGPU/local-atomics64.ll
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,VI,SICIVI,GFX89 %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s
+; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,VI,SICIVI,GFX89 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s
 
 ; GCN-LABEL: {{^}}lds_atomic_xchg_ret_i64:
 ; SICIVI: s_mov_b32 m0