[AMDGPU] add buffer_atomic_swap for float

[ruiling]

Summary

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

[arsenm]

Can you also add a test for the .raw version test

[ruiling]

also add test for .raw version

[arsenm]

Should probably broaden this to all the legal 32-bit types at some point, including <2 x i16> and <2 x half>

llvm/lib/Target/AMDGPU/BUFInstructions.td

(!cast<MUBUF_Pseudo>(opcode # _BOTHEN_RTN)
       getVregSrcForVT<vt>.ret:$vdata_in,
       (REG_SEQUENCE VReg_64, VGPR_32:$vindex, sub0, VGPR_32:$voffset, sub1),
         SReg_128:$rsrc, SCSrc_b32:$soffset, (as_i16timm $offset),
         (extract_slc $cachepolicy))
   >;
 }
 
 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">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_umin, i32, "BUFFER_ATOMIC_UMIN">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_smax, i32, "BUFFER_ATOMIC_SMAX">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_umax, i32, "BUFFER_ATOMIC_UMAX">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_and, i32, "BUFFER_ATOMIC_AND">;
 defm : BufferAtomicPatterns<SIbuffer_atomic_or, i32, "BUFFER_ATOMIC_OR">;

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll

 ;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
 ;CHECK: buffer_atomic_swap v0, off, s[0:3], 0 glc
 ;CHECK: s_movk_i32 [[SOFS:s[0-9]+]], 0x1ffc
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, v1, s[0:3], 0 offen glc
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, v1, s[0:3], 0 offen offset:42 glc
 ;CHECK-DAG: s_waitcnt vmcnt(0)
 ;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)
   %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(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
 }
 
 ;CHECK-LABEL: {{^}}test2:
 ;CHECK-NOT: s_waitcnt
 ;CHECK: buffer_atomic_add v0, v1, s[0:3], 0 offen glc{{$}}
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_sub v0, v1, s[0:3], 0 offen glc slc

 define amdgpu_ps float @test4() {
 main_body:
   %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(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
 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.inc.i32(i32, <4 x i32>, i32, i32, i32) #0
 declare i32 @llvm.amdgcn.raw.buffer.atomic.dec.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 }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll

 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, {{v\[[0-9]+:[0-9]+\]}}, s[0:3], 0 idxen offen glc
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_swap v0, v[1:2], s[0:3], 0 idxen offen offset:42 glc
 ;CHECK-DAG: s_waitcnt vmcnt(0)
 ;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)
   %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(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
 }
 
 ;CHECK-LABEL: {{^}}test2:
 ;CHECK-NOT: s_waitcnt
 ;CHECK: buffer_atomic_add v0, v1, s[0:3], 0 idxen glc{{$}}
 ;CHECK: s_waitcnt vmcnt(0)
 ;CHECK: buffer_atomic_sub v0, v1, s[0:3], 0 idxen glc slc

 define amdgpu_ps float @test4() {
 main_body:
   %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(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
 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.inc.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
 declare i32 @llvm.amdgcn.struct.buffer.atomic.dec.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 }