[AMDGPU] add buffer_atomic_swap for float

The functionality is used when calling imageAtomicExhange() on float
type imageBuffer in Graphics shaders.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D85187

diff --git a/llvm/lib/Target/AMDGPU/BUFInstructions.td b/llvm/lib/Target/AMDGPU/BUFInstructions.td
index bf0177b..c0f2ab0 100644 (file)
--- a/llvm/lib/Target/AMDGPU/BUFInstructions.td
+++ b/llvm/lib/Target/AMDGPU/BUFInstructions.td
@@ -1368,6 +1368,7 @@ multiclass BufferAtomicPatterns<SDPatternOperator name, ValueType vt,
 }
 
 defm : BufferAtomicPatterns<SIbuffer_atomic_swap, i32, "BUFFER_ATOMIC_SWAP">;
+defm : BufferAtomicPatterns<SIbuffer_atomic_swap, f32, "BUFFER_ATOMIC_SWAP">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_add, i32, "BUFFER_ATOMIC_ADD">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_sub, i32, "BUFFER_ATOMIC_SUB">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_smin, i32, "BUFFER_ATOMIC_SMIN">;

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 3c53950..71999e2 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
@@ -13,6 +13,7 @@
 ;CHECK: buffer_atomic_swap v0, off, s[0:3], [[SOFS]] offset:4 glc
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, off, s[0:3], 0{{$}}
+;CHECK: buffer_atomic_swap v0, off, s[0:3], 0 glc
 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(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
@@ -21,7 +22,8 @@ main_body:
   %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
+  %o7 = bitcast i32 %o6 to float
+  %out = call float @llvm.amdgcn.raw.buffer.atomic.swap.f32(float %o7, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
   ret float %out
 }
 
@@ -107,6 +109,7 @@ main_body:
 }
 
 declare i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare float @llvm.amdgcn.raw.buffer.atomic.swap.f32(float, <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

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 822fd79..2d01a9a 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
@@ -17,6 +17,7 @@
 ;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], [[SOFS]] idxen offset:4 glc
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen{{$}}
+;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen glc
 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(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
@@ -27,7 +28,8 @@ main_body:
   %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
+  %o7 = bitcast i32 %o6 to float
+  %out = call float @llvm.amdgcn.struct.buffer.atomic.swap.f32(float %o7, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
   ret float %out
 }
 
@@ -119,6 +121,7 @@ main_body:
 }
 
 declare i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare float @llvm.amdgcn.struct.buffer.atomic.swap.f32(float, <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