diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
index 9426df399597..c9c932ef2f5f 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
@@ -567,6 +567,7 @@ int PI = 0x40490fdb;
 int TWO_PI_INV = 0x3e22f983;
 int FP_UINT_MAX_PLUS_1 = 0x4f800000;    // 1 << 32 in floating point encoding
 int FP16_ONE = 0x3C00;
+int FP16_NEG_ONE = 0xBC00;
 int V2FP16_ONE = 0x3C003C00;
 int FP32_ONE = 0x3f800000;
 int FP32_NEG_ONE = 0xbf800000;
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index c3f8bfb53ef4..5c10646161b3 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -1386,6 +1386,11 @@ def : GCNPat<
   (V_MUL_F16_e64 0, (i32 CONST.FP16_ONE), $src_mods, $src, 0, 0)
 >;
 
+def : GCNPat<
+  (fcanonicalize (f16 (fneg (VOP3Mods f16:$src, i32:$src_mods)))),
+  (V_MUL_F16_e64 0, (i32 CONST.FP16_NEG_ONE), $src_mods, $src, 0, 0)
+>;
+
 def : GCNPat<
   (fcanonicalize (v2f16 (VOP3PMods v2f16:$src, i32:$src_mods))),
   (V_PK_MUL_F16 0, (i32 CONST.V2FP16_ONE), $src_mods, $src, DSTCLAMP.NONE)
@@ -1411,6 +1416,11 @@ def : GCNPat<
   (fcanonicalize (f32 (VOP3Mods f32:$src, i32:$src_mods))),
   (V_MUL_F32_e64 0, (i32 CONST.FP32_ONE), $src_mods, $src, 0, 0)
 >;
+
+def : GCNPat<
+  (fcanonicalize (f32 (fneg (VOP3Mods f32:$src, i32:$src_mods)))),
+  (V_MUL_F32_e64 0, (i32 CONST.FP32_NEG_ONE), $src_mods, $src, 0, 0)
+>;
 }
 
 let OtherPredicates = [FP32Denormals] in {
diff --git a/llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll b/llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
index a4db46b47500..d72dbf9e6ec0 100644
--- a/llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
+++ b/llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
@@ -225,7 +225,7 @@ define amdgpu_kernel void @test_fold_canonicalize_fpround_value_v2f16_v2f32(<2 x
 }
 
 ; GCN-LABEL: test_no_fold_canonicalize_fneg_value_f32:
-; GCN-FLUSH:  v_mul_f32_e64 v{{[0-9]+}}, 1.0, -v{{[0-9]+}}
+; GCN-FLUSH:  v_mul_f32_e32 v{{[0-9]+}}, -1.0, v{{[0-9]+}}
 ; GCN-DENORM: v_max_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, -v{{[0-9]+}}
 define amdgpu_kernel void @test_no_fold_canonicalize_fneg_value_f32(float addrspace(1)* %arg) {
   %id = tail call i32 @llvm.amdgcn.workitem.id.x()
diff --git a/llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll b/llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll
index 7cc556ce168d..f251e30a134b 100644
--- a/llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll
@@ -1,5 +1,5 @@
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
 
 declare half @llvm.fabs.f16(half) #0
 declare half @llvm.canonicalize.f16(half) #0
@@ -10,7 +10,7 @@ declare i32 @llvm.amdgcn.workitem.id.x() #0
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_var_f16:
 ; GCN: v_max_f16_e32 [[REG:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_var_f16(half addrspace(1)* %out) #1 {
   %val = load half, half addrspace(1)* %out
   %canonicalized = call half @llvm.canonicalize.f16(half %val)
@@ -20,7 +20,7 @@ define amdgpu_kernel void @v_test_canonicalize_var_f16(half addrspace(1)* %out)
 
 ; GCN-LABEL: {{^}}s_test_canonicalize_var_f16:
 ; GCN: v_max_f16_e64 [[REG:v[0-9]+]], {{s[0-9]+}}, {{s[0-9]+}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @s_test_canonicalize_var_f16(half addrspace(1)* %out, i16 zeroext %val.arg) #1 {
   %val = bitcast i16 %val.arg to half
   %canonicalized = call half @llvm.canonicalize.f16(half %val)
@@ -30,7 +30,7 @@ define amdgpu_kernel void @s_test_canonicalize_var_f16(half addrspace(1)* %out,
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_fabs_var_f16:
 ; GCN: v_max_f16_e64 [[REG:v[0-9]+]], |{{v[0-9]+}}|, |{{v[0-9]+}}|
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fabs_var_f16(half addrspace(1)* %out) #1 {
   %val = load half, half addrspace(1)* %out
   %val.fabs = call half @llvm.fabs.f16(half %val)
@@ -41,7 +41,7 @@ define amdgpu_kernel void @v_test_canonicalize_fabs_var_f16(half addrspace(1)* %
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_fneg_fabs_var_f16:
 ; GCN: v_max_f16_e64 [[REG:v[0-9]+]], -|{{v[0-9]+}}|, -|{{v[0-9]+}}|
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_f16(half addrspace(1)* %out) #1 {
   %val = load half, half addrspace(1)* %out
   %val.fabs = call half @llvm.fabs.f16(half %val)
@@ -53,7 +53,7 @@ define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_f16(half addrspace(
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_fneg_var_f16:
 ; GCN: v_max_f16_e64 [[REG:v[0-9]+]], -{{v[0-9]+}}, -{{v[0-9]+}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fneg_var_f16(half addrspace(1)* %out) #1 {
   %val = load half, half addrspace(1)* %out
   %val.fneg = fsub half -0.0, %val
@@ -62,9 +62,32 @@ define amdgpu_kernel void @v_test_canonicalize_fneg_var_f16(half addrspace(1)* %
   ret void
 }
 
+; GCN-LABEL: {{^}}v_test_no_denormals_canonicalize_fneg_var_f16:
+; GCN: v_mul_f16_e32 [[REG:v[0-9]+]], -1.0, v{{[0-9]+}}
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
+define amdgpu_kernel void @v_test_no_denormals_canonicalize_fneg_var_f16(half addrspace(1)* %out) #2 {
+  %val = load half, half addrspace(1)* %out
+  %val.fneg = fsub half -0.0, %val
+  %canonicalized = call half @llvm.canonicalize.f16(half %val.fneg)
+  store half %canonicalized, half addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_test_no_denormals_canonicalize_fneg_fabs_var_f16:
+; GCN: v_mul_f16_e64 [[REG:v[0-9]+]], -1.0, |v{{[0-9]+}}|
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
+define amdgpu_kernel void @v_test_no_denormals_canonicalize_fneg_fabs_var_f16(half addrspace(1)* %out) #2 {
+  %val = load half, half addrspace(1)* %out
+  %val.fabs = call half @llvm.fabs.f16(half %val)
+  %val.fabs.fneg = fsub half -0.0, %val.fabs
+  %canonicalized = call half @llvm.canonicalize.f16(half %val.fabs.fneg)
+  store half %canonicalized, half addrspace(1)* %out
+  ret void
+}
+
 ; GCN-LABEL: {{^}}test_fold_canonicalize_p0_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_p0_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0.0)
   store half %canonicalized, half addrspace(1)* %out
@@ -73,7 +96,7 @@ define amdgpu_kernel void @test_fold_canonicalize_p0_f16(half addrspace(1)* %out
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_n0_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0xffff8000{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_n0_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half -0.0)
   store half %canonicalized, half addrspace(1)* %out
@@ -82,7 +105,7 @@ define amdgpu_kernel void @test_fold_canonicalize_n0_f16(half addrspace(1)* %out
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_p1_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3c00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_p1_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 1.0)
   store half %canonicalized, half addrspace(1)* %out
@@ -91,7 +114,7 @@ define amdgpu_kernel void @test_fold_canonicalize_p1_f16(half addrspace(1)* %out
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_n1_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0xffffbc00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_n1_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half -1.0)
   store half %canonicalized, half addrspace(1)* %out
@@ -100,7 +123,7 @@ define amdgpu_kernel void @test_fold_canonicalize_n1_f16(half addrspace(1)* %out
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_literal_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x4c00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_literal_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 16.0)
   store half %canonicalized, half addrspace(1)* %out
@@ -109,7 +132,7 @@ define amdgpu_kernel void @test_fold_canonicalize_literal_f16(half addrspace(1)*
 
 ; GCN-LABEL: {{^}}test_default_denormals_fold_canonicalize_denormal0_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3ff{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_default_denormals_fold_canonicalize_denormal0_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH03FF)
   store half %canonicalized, half addrspace(1)* %out
@@ -118,7 +141,7 @@ define amdgpu_kernel void @test_default_denormals_fold_canonicalize_denormal0_f1
 
 ; GCN-LABEL: {{^}}test_denormals_fold_canonicalize_denormal0_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3ff{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal0_f16(half addrspace(1)* %out) #3 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH03FF)
   store half %canonicalized, half addrspace(1)* %out
@@ -127,7 +150,7 @@ define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal0_f16(half a
 
 ; GCN-LABEL: {{^}}test_default_denormals_fold_canonicalize_denormal1_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0xffff83ff{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_default_denormals_fold_canonicalize_denormal1_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH83FF)
   store half %canonicalized, half addrspace(1)* %out
@@ -136,7 +159,7 @@ define amdgpu_kernel void @test_default_denormals_fold_canonicalize_denormal1_f1
 
 ; GCN-LABEL: {{^}}test_denormals_fold_canonicalize_denormal1_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0xffff83ff{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal1_f16(half addrspace(1)* %out) #3 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH83FF)
   store half %canonicalized, half addrspace(1)* %out
@@ -145,7 +168,7 @@ define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal1_f16(half a
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7c00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH7C00)
   store half %canonicalized, half addrspace(1)* %out
@@ -154,7 +177,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_f16(half addrspace(1)* %o
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_value_neg1_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg1_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half bitcast (i16 -1 to half))
   store half %canonicalized, half addrspace(1)* %out
@@ -163,7 +186,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg1_f16(half addrs
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_value_neg2_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg2_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half bitcast (i16 -2 to half))
   store half %canonicalized, half addrspace(1)* %out
@@ -172,7 +195,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg2_f16(half addrs
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan0_value_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan0_value_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH7C01)
   store half %canonicalized, half addrspace(1)* %out
@@ -181,7 +204,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan0_value_f16(half addrspace
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan1_value_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan1_value_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xH7DFF)
   store half %canonicalized, half addrspace(1)* %out
@@ -190,7 +213,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan1_value_f16(half addrspace
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan2_value_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan2_value_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xHFDFF)
   store half %canonicalized, half addrspace(1)* %out
@@ -199,7 +222,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan2_value_f16(half addrspace
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan3_value_f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e00{{$}}
-; GCN: buffer_store_short [[REG]]
+; GCN: {{flat|global}}_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan3_value_f16(half addrspace(1)* %out) #1 {
   %canonicalized = call half @llvm.canonicalize.f16(half 0xHFC01)
   store half %canonicalized, half addrspace(1)* %out
@@ -212,7 +235,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan3_value_f16(half addrspace
 ; VI-NOT: v_and_b32
 
 ; GFX9: v_pk_max_f16 [[REG:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+$}}
-; GFX9: buffer_store_dword [[REG]]
+; GFX9: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_var_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
@@ -230,7 +253,7 @@ define amdgpu_kernel void @v_test_canonicalize_var_v2f16(<2 x half> addrspace(1)
 
 ; GFX9: v_and_b32_e32 [[ABS:v[0-9]+]], 0x7fff7fff, v{{[0-9]+}}
 ; GFX9: v_pk_max_f16 [[REG:v[0-9]+]], [[ABS]], [[ABS]]{{$}}
-; GCN: buffer_store_dword
+; GCN: {{flat|global}}_store_dword
 define amdgpu_kernel void @v_test_canonicalize_fabs_var_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
@@ -248,7 +271,7 @@ define amdgpu_kernel void @v_test_canonicalize_fabs_var_v2f16(<2 x half> addrspa
 
 ; GFX9: v_and_b32_e32 [[ABS:v[0-9]+]], 0x7fff7fff, v{{[0-9]+}}
 ; GFX9: v_pk_max_f16 [[REG:v[0-9]+]], [[ABS]], [[ABS]] neg_lo:[1,1] neg_hi:[1,1]{{$}}
-; GCN: buffer_store_dword
+; GCN: {{flat|global}}_store_dword
 define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
@@ -266,7 +289,7 @@ define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_v2f16(<2 x half> ad
 ; VI-NOT: 0xffff
 
 ; GFX9: v_pk_max_f16 [[REG:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}} neg_lo:[1,1] neg_hi:[1,1]{{$}}
-; GFX9: buffer_store_dword [[REG]]
+; GFX9: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fneg_var_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
@@ -283,7 +306,7 @@ define amdgpu_kernel void @v_test_canonicalize_fneg_var_v2f16(<2 x half> addrspa
 ; VI-NOT: v_and_b32
 
 ; GFX9: v_pk_max_f16 [[REG:v[0-9]+]], {{s[0-9]+}}, {{s[0-9]+$}}
-; GFX9: buffer_store_dword [[REG]]
+; GFX9: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @s_test_canonicalize_var_v2f16(<2 x half> addrspace(1)* %out, i32 zeroext %val.arg) #1 {
   %val = bitcast i32 %val.arg to <2 x half>
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> %val)
@@ -293,7 +316,7 @@ define amdgpu_kernel void @s_test_canonicalize_var_v2f16(<2 x half> addrspace(1)
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_p0_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_p0_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> zeroinitializer)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -302,7 +325,7 @@ define amdgpu_kernel void @test_fold_canonicalize_p0_v2f16(<2 x half> addrspace(
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_n0_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80008000{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_n0_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half -0.0, half -0.0>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -311,7 +334,7 @@ define amdgpu_kernel void @test_fold_canonicalize_n0_v2f16(<2 x half> addrspace(
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_p1_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3c003c00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_p1_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 1.0, half 1.0>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -320,7 +343,7 @@ define amdgpu_kernel void @test_fold_canonicalize_p1_v2f16(<2 x half> addrspace(
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_n1_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0xbc00bc00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_n1_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half -1.0, half -1.0>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -329,7 +352,7 @@ define amdgpu_kernel void @test_fold_canonicalize_n1_v2f16(<2 x half> addrspace(
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_literal_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x4c004c00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_literal_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 16.0, half 16.0>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -338,7 +361,7 @@ define amdgpu_kernel void @test_fold_canonicalize_literal_v2f16(<2 x half> addrs
 
 ; GCN-LABEL: {{^}}test_no_denormals_fold_canonicalize_denormal0_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3ff03ff{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_no_denormals_fold_canonicalize_denormal0_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH03FF, half 0xH03FF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -347,7 +370,7 @@ define amdgpu_kernel void @test_no_denormals_fold_canonicalize_denormal0_v2f16(<
 
 ; GCN-LABEL: {{^}}test_denormals_fold_canonicalize_denormal0_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x3ff03ff{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal0_v2f16(<2 x half> addrspace(1)* %out) #3 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH03FF, half 0xH03FF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -356,7 +379,7 @@ define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal0_v2f16(<2 x
 
 ; GCN-LABEL: {{^}}test_no_denormals_fold_canonicalize_denormal1_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x83ff83ff{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_no_denormals_fold_canonicalize_denormal1_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH83FF, half 0xH83FF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -365,7 +388,7 @@ define amdgpu_kernel void @test_no_denormals_fold_canonicalize_denormal1_v2f16(<
 
 ; GCN-LABEL: {{^}}test_denormals_fold_canonicalize_denormal1_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x83ff83ff{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal1_v2f16(<2 x half> addrspace(1)* %out) #3 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH83FF, half 0xH83FF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -374,7 +397,7 @@ define amdgpu_kernel void @test_denormals_fold_canonicalize_denormal1_v2f16(<2 x
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7c007c00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH7C00, half 0xH7C00>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -383,7 +406,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_v2f16(<2 x half> addrspac
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_value_neg1_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg1_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> bitcast (i32 -1 to <2 x half>))
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -392,7 +415,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg1_v2f16(<2 x hal
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_qnan_value_neg2_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg2_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half bitcast (i16 -2 to half), half bitcast (i16 -2 to half)>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -401,7 +424,7 @@ define amdgpu_kernel void @test_fold_canonicalize_qnan_value_neg2_v2f16(<2 x hal
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan0_value_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan0_value_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH7C01, half 0xH7C01>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -410,7 +433,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan0_value_v2f16(<2 x half> a
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan1_value_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan1_value_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xH7DFF, half 0xH7DFF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -419,7 +442,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan1_value_v2f16(<2 x half> a
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan2_value_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan2_value_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xHFDFF, half 0xHFDFF>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
@@ -428,7 +451,7 @@ define amdgpu_kernel void @test_fold_canonicalize_snan2_value_v2f16(<2 x half> a
 
 ; GCN-LABEL: {{^}}test_fold_canonicalize_snan3_value_v2f16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7e007e00{{$}}
-; GCN: buffer_store_dword [[REG]]
+; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[REG]]
 define amdgpu_kernel void @test_fold_canonicalize_snan3_value_v2f16(<2 x half> addrspace(1)* %out) #1 {
   %canonicalized = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> <half 0xHFC01, half 0xHFC01>)
   store <2 x half> %canonicalized, <2 x half> addrspace(1)* %out
diff --git a/llvm/test/CodeGen/AMDGPU/fcanonicalize.ll b/llvm/test/CodeGen/AMDGPU/fcanonicalize.ll
index 1c6d176c6762..7c4698b8cfaf 100644
--- a/llvm/test/CodeGen/AMDGPU/fcanonicalize.ll
+++ b/llvm/test/CodeGen/AMDGPU/fcanonicalize.ll
@@ -40,7 +40,7 @@ define amdgpu_kernel void @v_test_canonicalize_fabs_var_f32(float addrspace(1)*
 }
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_fneg_fabs_var_f32:
-; GCN: v_mul_f32_e64 [[REG:v[0-9]+]], 1.0, -|{{v[0-9]+}}|
+; GCN: v_mul_f32_e64 [[REG:v[0-9]+]], -1.0, |{{v[0-9]+}}|
 ; GCN: buffer_store_dword [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_f32(float addrspace(1)* %out) #1 {
   %val = load float, float addrspace(1)* %out
@@ -52,7 +52,7 @@ define amdgpu_kernel void @v_test_canonicalize_fneg_fabs_var_f32(float addrspace
 }
 
 ; GCN-LABEL: {{^}}v_test_canonicalize_fneg_var_f32:
-; GCN: v_mul_f32_e64 [[REG:v[0-9]+]], 1.0, -{{v[0-9]+}}
+; GCN: v_mul_f32_e32 [[REG:v[0-9]+]], -1.0, {{v[0-9]+}}
 ; GCN: buffer_store_dword [[REG]]
 define amdgpu_kernel void @v_test_canonicalize_fneg_var_f32(float addrspace(1)* %out) #1 {
   %val = load float, float addrspace(1)* %out
diff --git a/llvm/test/CodeGen/AMDGPU/fneg-combines.ll b/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
index 520309e0a9fd..c065227012f6 100644
--- a/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
+++ b/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
@@ -1730,7 +1730,7 @@ define amdgpu_kernel void @v_fneg_nearbyint_f32(float addrspace(1)* %out, float
 
 ; GCN-LABEL: {{^}}v_fneg_canonicalize_f32:
 ; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
-; GCN: v_mul_f32_e64 [[RESULT:v[0-9]+]], 1.0, -[[A]]
+; GCN: v_mul_f32_e32 [[RESULT:v[0-9]+]], -1.0, [[A]]
 ; GCN: buffer_store_dword [[RESULT]]
 define amdgpu_kernel void @v_fneg_canonicalize_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()