AMDGPU: Future-proof {raw,struct}.buffer.atomic intrinsics

Summary:
The ISA is really supposed to support 64-bit atomics as well,
so the data type should be an overload.

Mesa doesn't use these atomics yet, in fact I noticed this
issue while trying to use the atomics from Mesa.

Change-Id: I77f58317a085a0d3eb933cc7e99308c48a19f83e

Reviewers: tpr

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, jfb, llvm-commits

Differential Revision: https://reviews.llvm.org/D52291

llvm-svn: 343978

3 files changed, 76 insertions, 76 deletions

diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index e12d7cd83d9..ccf43a61c3d 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -879,8 +879,8 @@ def int_amdgcn_struct_buffer_store_format : AMDGPUStructBufferStore;
 def int_amdgcn_struct_buffer_store : AMDGPUStructBufferStore;
 
 class AMDGPURawBufferAtomic : Intrinsic <
-  [llvm_i32_ty],
-  [llvm_i32_ty,       // vdata(VGPR)
+  [llvm_anyint_ty],
+  [LLVMMatchType<0>,  // vdata(VGPR)
    llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)
    llvm_i32_ty,       // soffset(SGPR/imm, excluded from bounds checking and swizzling)
@@ -898,9 +898,9 @@ def int_amdgcn_raw_buffer_atomic_and : AMDGPURawBufferAtomic;
 def int_amdgcn_raw_buffer_atomic_or : AMDGPURawBufferAtomic;
 def int_amdgcn_raw_buffer_atomic_xor : AMDGPURawBufferAtomic;
 def int_amdgcn_raw_buffer_atomic_cmpswap : Intrinsic<
-  [llvm_i32_ty],
-  [llvm_i32_ty,       // src(VGPR)
-   llvm_i32_ty,       // cmp(VGPR)
+  [llvm_anyint_ty],
+  [LLVMMatchType<0>,  // src(VGPR)
+   LLVMMatchType<0>,  // cmp(VGPR)
    llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)
    llvm_i32_ty,       // soffset(SGPR/imm, excluded from bounds checking and swizzling)
@@ -909,8 +909,8 @@ def int_amdgcn_raw_buffer_atomic_cmpswap : Intrinsic<
   AMDGPURsrcIntrinsic<2, 0>;
 
 class AMDGPUStructBufferAtomic : Intrinsic <
-  [llvm_i32_ty],
-  [llvm_i32_ty,       // vdata(VGPR)
+  [llvm_anyint_ty],
+  [LLVMMatchType<0>,  // vdata(VGPR)
    llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // vindex(VGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)
@@ -929,9 +929,9 @@ def int_amdgcn_struct_buffer_atomic_and : AMDGPUStructBufferAtomic;
 def int_amdgcn_struct_buffer_atomic_or : AMDGPUStructBufferAtomic;
 def int_amdgcn_struct_buffer_atomic_xor : AMDGPUStructBufferAtomic;
 def int_amdgcn_struct_buffer_atomic_cmpswap : Intrinsic<
-  [llvm_i32_ty],
-  [llvm_i32_ty,       // src(VGPR)
-   llvm_i32_ty,       // cmp(VGPR)
+  [llvm_anyint_ty],
+  [LLVMMatchType<0>,  // src(VGPR)
+   LLVMMatchType<0>,  // cmp(VGPR)
    llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // vindex(VGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)
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 cb29e5a6ec6..08edaf98927 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
@@ -15,12 +15,12 @@
 ;CHECK: buffer_atomic_swap v0, off, s[0:3], 0{{$}}
 define amdgpu_ps float @test1(<4 x i32> inreg %rsrc, i32 %data, i32 %voffset) {
 main_body:
-  %o1 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
-  %o3 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32 %o1, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %o1 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
+  %o3 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %o1, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
   %off5 = add i32 %voffset, 42
-  %o5 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32 %o3, <4 x i32> %rsrc, i32 %off5, i32 0, i32 0)
-  %o6 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32 %o5, <4 x i32> %rsrc, i32 4, i32 8188, i32 0)
-  %unused = call i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32 %o6, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
+  %o5 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %o3, <4 x i32> %rsrc, i32 %off5, i32 0, i32 0)
+  %o6 = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %o5, <4 x i32> %rsrc, i32 4, i32 8188, i32 0)
+  %unused = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %o6, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
   %out = bitcast i32 %o6 to float
   ret float %out
 }
@@ -46,15 +46,15 @@ main_body:
 ;CHECK: buffer_atomic_xor v0, v1, s[0:3], 0 offen glc
 define amdgpu_ps float @test2(<4 x i32> inreg %rsrc, i32 %data, i32 %voffset) {
 main_body:
-  %t1 = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %data, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
-  %t2 = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %t1, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
-  %t3 = call i32 @llvm.amdgcn.raw.buffer.atomic.smin(i32 %t2, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
-  %t4 = call i32 @llvm.amdgcn.raw.buffer.atomic.umin(i32 %t3, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
-  %t5 = call i32 @llvm.amdgcn.raw.buffer.atomic.smax(i32 %t4, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
-  %t6 = call i32 @llvm.amdgcn.raw.buffer.atomic.umax(i32 %t5, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
-  %t7 = call i32 @llvm.amdgcn.raw.buffer.atomic.and(i32 %t6, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
-  %t8 = call i32 @llvm.amdgcn.raw.buffer.atomic.or(i32 %t7, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
-  %t9 = call i32 @llvm.amdgcn.raw.buffer.atomic.xor(i32 %t8, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %t1 = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %data, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %t2 = call i32 @llvm.amdgcn.raw.buffer.atomic.sub.i32(i32 %t1, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
+  %t3 = call i32 @llvm.amdgcn.raw.buffer.atomic.smin.i32(i32 %t2, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %t4 = call i32 @llvm.amdgcn.raw.buffer.atomic.umin.i32(i32 %t3, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
+  %t5 = call i32 @llvm.amdgcn.raw.buffer.atomic.smax.i32(i32 %t4, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %t6 = call i32 @llvm.amdgcn.raw.buffer.atomic.umax.i32(i32 %t5, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
+  %t7 = call i32 @llvm.amdgcn.raw.buffer.atomic.and.i32(i32 %t6, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %t8 = call i32 @llvm.amdgcn.raw.buffer.atomic.or.i32(i32 %t7, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 2)
+  %t9 = call i32 @llvm.amdgcn.raw.buffer.atomic.xor.i32(i32 %t8, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
   %out = bitcast i32 %t9 to float
   ret float %out
 }
@@ -75,18 +75,18 @@ main_body:
 ;CHECK: buffer_atomic_cmpswap {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], [[SOFS]] offset:4 glc
 define amdgpu_ps float @test3(<4 x i32> inreg %rsrc, i32 %data, i32 %cmp, i32 %vindex, i32 %voffset) {
 main_body:
-  %o1 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
-  %o3 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32 %o1, i32 %cmp, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
+  %o1 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
+  %o3 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %o1, i32 %cmp, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
   %ofs.5 = add i32 %voffset, 44
-  %o5 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32 %o3, i32 %cmp, <4 x i32> %rsrc, i32 %ofs.5, i32 0, i32 0)
-  %o6 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32 %o5, i32 %cmp, <4 x i32> %rsrc, i32 4, i32 8188, i32 0)
+  %o5 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %o3, i32 %cmp, <4 x i32> %rsrc, i32 %ofs.5, i32 0, i32 0)
+  %o6 = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %o5, i32 %cmp, <4 x i32> %rsrc, i32 4, i32 8188, i32 0)
 
 ; Detecting the no-return variant doesn't work right now because of how the
 ; intrinsic is replaced by an instruction that feeds into an EXTRACT_SUBREG.
 ; Since there probably isn't a reasonable use-case of cmpswap that discards
 ; the return value, that seems okay.
 ;
-;  %unused = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32 %o6, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
+;  %unused = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %o6, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
   %out = bitcast i32 %o6 to float
   ret float %out
 }
@@ -95,21 +95,21 @@ main_body:
 ;CHECK: buffer_atomic_add v0,
 define amdgpu_ps float @test4() {
 main_body:
-  %v = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> undef, i32 4, i32 0, i32 0)
+  %v = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 1, <4 x i32> undef, i32 4, i32 0, i32 0)
   %v.float = bitcast i32 %v to float
   ret float %v.float
 }
 
-declare i32 @llvm.amdgcn.raw.buffer.atomic.swap(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.smin(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.umin(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.smax(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.umax(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.and(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.or(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.xor(i32, <4 x i32>, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap(i32, i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.sub.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.smin.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.umin.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.smax.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.umax.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.and.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.or.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.xor.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32, i32, <4 x i32>, i32, i32, i32) #0
 
 attributes #0 = { nounwind }
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 dd9f6457df0..6c9ca9b17d2 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
@@ -19,14 +19,14 @@
 ;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen{{$}}
 define amdgpu_ps float @test1(<4 x i32> inreg %rsrc, i32 %data, i32 %vindex, i32 %voffset) {
 main_body:
-  %o1 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
-  %o2 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o1, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %o3 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o2, <4 x i32> %rsrc, i32 0, i32 %voffset, i32 0, i32 0)
-  %o4 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o3, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 0, i32 0)
+  %o1 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
+  %o2 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o1, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %o3 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o2, <4 x i32> %rsrc, i32 0, i32 %voffset, i32 0, i32 0)
+  %o4 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o3, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 0, i32 0)
   %ofs.5 = add i32 %voffset, 42
-  %o5 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o4, <4 x i32> %rsrc, i32 0, i32 %ofs.5, i32 0, i32 0)
-  %o6 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o5, <4 x i32> %rsrc, i32 0, i32 4, i32 8188, i32 0)
-  %unused = call i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32 %o6, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
+  %o5 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o4, <4 x i32> %rsrc, i32 0, i32 %ofs.5, i32 0, i32 0)
+  %o6 = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o5, <4 x i32> %rsrc, i32 0, i32 4, i32 8188, i32 0)
+  %unused = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %o6, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
   %out = bitcast i32 %o6 to float
   ret float %out
 }
@@ -52,15 +52,15 @@ main_body:
 ;CHECK: buffer_atomic_xor v0, v1, s[0:3], 0 idxen glc
 define amdgpu_ps float @test2(<4 x i32> inreg %rsrc, i32 %data, i32 %vindex) {
 main_body:
-  %t1 = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %t2 = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %t1, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
-  %t3 = call i32 @llvm.amdgcn.struct.buffer.atomic.smin(i32 %t2, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %t4 = call i32 @llvm.amdgcn.struct.buffer.atomic.umin(i32 %t3, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
-  %t5 = call i32 @llvm.amdgcn.struct.buffer.atomic.smax(i32 %t4, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %t6 = call i32 @llvm.amdgcn.struct.buffer.atomic.umax(i32 %t5, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
-  %t7 = call i32 @llvm.amdgcn.struct.buffer.atomic.and(i32 %t6, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %t8 = call i32 @llvm.amdgcn.struct.buffer.atomic.or(i32 %t7, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
-  %t9 = call i32 @llvm.amdgcn.struct.buffer.atomic.xor(i32 %t8, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %t1 = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %t2 = call i32 @llvm.amdgcn.struct.buffer.atomic.sub.i32(i32 %t1, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
+  %t3 = call i32 @llvm.amdgcn.struct.buffer.atomic.smin.i32(i32 %t2, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %t4 = call i32 @llvm.amdgcn.struct.buffer.atomic.umin.i32(i32 %t3, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
+  %t5 = call i32 @llvm.amdgcn.struct.buffer.atomic.smax.i32(i32 %t4, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %t6 = call i32 @llvm.amdgcn.struct.buffer.atomic.umax.i32(i32 %t5, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
+  %t7 = call i32 @llvm.amdgcn.struct.buffer.atomic.and.i32(i32 %t6, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %t8 = call i32 @llvm.amdgcn.struct.buffer.atomic.or.i32(i32 %t7, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 2)
+  %t9 = call i32 @llvm.amdgcn.struct.buffer.atomic.xor.i32(i32 %t8, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
   %out = bitcast i32 %t9 to float
   ret float %out
 }
@@ -85,20 +85,20 @@ main_body:
 ;CHECK: buffer_atomic_cmpswap {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, s[0:3], [[SOFS]] idxen offset:4 glc
 define amdgpu_ps float @test3(<4 x i32> inreg %rsrc, i32 %data, i32 %cmp, i32 %vindex, i32 %voffset) {
 main_body:
-  %o1 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
-  %o2 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o1, i32 %cmp, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
-  %o3 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o2, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 %voffset, i32 0, i32 0)
-  %o4 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o3, i32 %cmp, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 0, i32 0)
+  %o1 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
+  %o2 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o1, i32 %cmp, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
+  %o3 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o2, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 %voffset, i32 0, i32 0)
+  %o4 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o3, i32 %cmp, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 0, i32 0)
   %offs.5 = add i32 %voffset, 44
-  %o5 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o4, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 %offs.5, i32 0, i32 0)
-  %o6 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o5, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 4, i32 8188, i32 0)
+  %o5 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o4, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 %offs.5, i32 0, i32 0)
+  %o6 = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o5, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 4, i32 8188, i32 0)
 
 ; Detecting the no-return variant doesn't work right now because of how the
 ; intrinsic is replaced by an instruction that feeds into an EXTRACT_SUBREG.
 ; Since there probably isn't a reasonable use-case of cmpswap that discards
 ; the return value, that seems okay.
 ;
-;  %unused = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32 %o6, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
+;  %unused = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %o6, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
   %out = bitcast i32 %o6 to float
   ret float %out
 }
@@ -107,21 +107,21 @@ main_body:
 ;CHECK: buffer_atomic_add v0,
 define amdgpu_ps float @test4() {
 main_body:
-  %v = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 1, <4 x i32> undef, i32 0, i32 4, i32 0, i32 0)
+  %v = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 1, <4 x i32> undef, i32 0, i32 4, i32 0, i32 0)
   %v.float = bitcast i32 %v to float
   ret float %v.float
 }
 
-declare i32 @llvm.amdgcn.struct.buffer.atomic.swap(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.smin(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.umin(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.smax(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.umax(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.and(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.or(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.xor(i32, <4 x i32>, i32, i32, i32, i32) #0
-declare i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap(i32, i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.sub.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.smin.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.umin.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.smax.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.umax.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.and.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.or.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.xor.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32, i32, <4 x i32>, i32, i32, i32, i32) #0
 
 attributes #0 = { nounwind }