[AMDGPU] Allow int types for MUBUF vdata

Summary:
Previously the new llvm.amdgcn.raw/struct.buffer.load/store intrinsics
only allowed float types for the data to be loaded or stored, which
sometimes meant the frontend needed to generate a bitcast. In this, the
new intrinsics copied the old buffer intrinsics.

This commit extends the new intrinsics to allow int types as well.

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D50315

Change-Id: I8202af2d036455553681dcbb3d7d32ae273f8f85
llvm-svn: 340270

llvm/include/llvm/IR/IntrinsicsAMDGPU.td

@@ -823,7 +823,7 @@ def int_amdgcn_buffer_store : AMDGPUBufferStore;
 // These new instrinsics also keep the offset and soffset arguments separate as
 // they behave differently in bounds checking and swizzling.
 class AMDGPURawBufferLoad : Intrinsic <
-  [llvm_anyfloat_ty],
+  [llvm_any_ty],
   [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)
@@ -834,7 +834,7 @@ def int_amdgcn_raw_buffer_load_format : AMDGPURawBufferLoad;
 def int_amdgcn_raw_buffer_load : AMDGPURawBufferLoad;
 
 class AMDGPUStructBufferLoad : Intrinsic <
-  [llvm_anyfloat_ty],
+  [llvm_any_ty],
   [llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // vindex(VGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)
@@ -847,7 +847,7 @@ def int_amdgcn_struct_buffer_load : AMDGPUStructBufferLoad;
 
 class AMDGPURawBufferStore : Intrinsic <
   [],
-  [llvm_anyfloat_ty,  // vdata(VGPR) -- can currently only select f32, v2f32, v4f32
+  [llvm_any_ty,       // 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)
@@ -859,7 +859,7 @@ def int_amdgcn_raw_buffer_store : AMDGPURawBufferStore;
 
 class AMDGPUStructBufferStore : Intrinsic <
   [],
-  [llvm_anyfloat_ty,  // vdata(VGPR) -- can currently only select f32, v2f32, v4f32
+  [llvm_any_ty,       // vdata(VGPR)
    llvm_v4i32_ty,     // rsrc(SGPR)
    llvm_i32_ty,       // vindex(VGPR)
    llvm_i32_ty,       // offset(VGPR/imm, included in bounds checking and swizzling)

llvm/lib/Target/AMDGPU/BUFInstructions.td

@@ -1074,24 +1074,34 @@ multiclass MUBUF_LoadIntrinsicPat<SDPatternOperator name, ValueType vt,
 }
 
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, f32, "BUFFER_LOAD_FORMAT_X">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, i32, "BUFFER_LOAD_FORMAT_X">;
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v2f32, "BUFFER_LOAD_FORMAT_XY">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v2i32, "BUFFER_LOAD_FORMAT_XY">;
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v4f32, "BUFFER_LOAD_FORMAT_XYZW">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v4i32, "BUFFER_LOAD_FORMAT_XYZW">;
 
 let SubtargetPredicate = HasUnpackedD16VMem in {
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, f16, "BUFFER_LOAD_FORMAT_D16_X_gfx80">;
+  defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, i16, "BUFFER_LOAD_FORMAT_D16_X_gfx80">;
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v2i32, "BUFFER_LOAD_FORMAT_D16_XY_gfx80">;
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v4i32, "BUFFER_LOAD_FORMAT_D16_XYZW_gfx80">;
 } // End HasUnpackedD16VMem.
 
 let SubtargetPredicate = HasPackedD16VMem in {
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, f16, "BUFFER_LOAD_FORMAT_D16_X">;
+  defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, i16, "BUFFER_LOAD_FORMAT_D16_X">;
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v2f16, "BUFFER_LOAD_FORMAT_D16_XY">;
+  defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v2i16, "BUFFER_LOAD_FORMAT_D16_XY">;
   defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v4f16, "BUFFER_LOAD_FORMAT_D16_XYZW">;
+  defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format_d16, v4i16, "BUFFER_LOAD_FORMAT_D16_XYZW">;
 } // End HasPackedD16VMem.
 
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, f32, "BUFFER_LOAD_DWORD">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, i32, "BUFFER_LOAD_DWORD">;
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v2f32, "BUFFER_LOAD_DWORDX2">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v2i32, "BUFFER_LOAD_DWORDX2">;
 defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v4f32, "BUFFER_LOAD_DWORDX4">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v4i32, "BUFFER_LOAD_DWORDX4">;
 
 multiclass MUBUF_StoreIntrinsicPat<SDPatternOperator name, ValueType vt,
                                    string opcode> {
@@ -1128,24 +1138,34 @@ multiclass MUBUF_StoreIntrinsicPat<SDPatternOperator name, ValueType vt,
 }
 
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, f32, "BUFFER_STORE_FORMAT_X">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, i32, "BUFFER_STORE_FORMAT_X">;
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, v2f32, "BUFFER_STORE_FORMAT_XY">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, v2i32, "BUFFER_STORE_FORMAT_XY">;
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, v4f32, "BUFFER_STORE_FORMAT_XYZW">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format, v4i32, "BUFFER_STORE_FORMAT_XYZW">;
 
 let SubtargetPredicate = HasUnpackedD16VMem in {
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, f16, "BUFFER_STORE_FORMAT_D16_X_gfx80">;
+  defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, i16, "BUFFER_STORE_FORMAT_D16_X_gfx80">;
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v2i32, "BUFFER_STORE_FORMAT_D16_XY_gfx80">;
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v4i32, "BUFFER_STORE_FORMAT_D16_XYZW_gfx80">;
 } // End HasUnpackedD16VMem.
 
 let SubtargetPredicate = HasPackedD16VMem in {
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, f16, "BUFFER_STORE_FORMAT_D16_X">;
+  defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, i16, "BUFFER_STORE_FORMAT_D16_X">;
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v2f16, "BUFFER_STORE_FORMAT_D16_XY">;
+  defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v2i16, "BUFFER_STORE_FORMAT_D16_XY">;
   defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v4f16, "BUFFER_STORE_FORMAT_D16_XYZW">;
+  defm : MUBUF_StoreIntrinsicPat<SIbuffer_store_format_d16, v4i16, "BUFFER_STORE_FORMAT_D16_XYZW">;
 } // End HasPackedD16VMem.
 
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, f32, "BUFFER_STORE_DWORD">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, i32, "BUFFER_STORE_DWORD">;
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, v2f32, "BUFFER_STORE_DWORDX2">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, v2i32, "BUFFER_STORE_DWORDX2">;
 defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, v4f32, "BUFFER_STORE_DWORDX4">;
+defm : MUBUF_StoreIntrinsicPat<SIbuffer_store, v4i32, "BUFFER_STORE_DWORDX4">;
 
 //===----------------------------------------------------------------------===//
 // buffer_atomic patterns

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

@@ -198,9 +198,31 @@ main_body:
   ret void
 }
 
+;CHECK-LABEL: {{^}}buffer_load_int:
+;CHECK: buffer_load_dwordx4 v[0:3], off, s[0:3], 0
+;CHECK: buffer_load_dwordx2 v[4:5], off, s[0:3], 0 glc
+;CHECK: buffer_load_dword v6, off, s[0:3], 0 slc
+;CHECK: s_waitcnt
+define amdgpu_ps {<4 x float>, <2 x float>, float} @buffer_load_int(<4 x i32> inreg) {
+main_body:
+  %data = call <4 x i32> @llvm.amdgcn.raw.buffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0)
+  %data_glc = call <2 x i32> @llvm.amdgcn.raw.buffer.load.v2i32(<4 x i32> %0, i32 0, i32 0, i32 1)
+  %data_slc = call i32 @llvm.amdgcn.raw.buffer.load.i32(<4 x i32> %0, i32 0, i32 0, i32 2)
+  %fdata = bitcast <4 x i32> %data to <4 x float>
+  %fdata_glc = bitcast <2 x i32> %data_glc to <2 x float>
+  %fdata_slc = bitcast i32 %data_slc to float
+  %r0 = insertvalue {<4 x float>, <2 x float>, float} undef, <4 x float> %fdata, 0
+  %r1 = insertvalue {<4 x float>, <2 x float>, float} %r0, <2 x float> %fdata_glc, 1
+  %r2 = insertvalue {<4 x float>, <2 x float>, float} %r1, float %fdata_slc, 2
+  ret {<4 x float>, <2 x float>, float} %r2
+}
+
 declare float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32>, i32, i32, i32) #0
 declare <2 x float> @llvm.amdgcn.raw.buffer.load.v2f32(<4 x i32>, i32, i32, i32) #0
 declare <4 x float> @llvm.amdgcn.raw.buffer.load.v4f32(<4 x i32>, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.raw.buffer.load.i32(<4 x i32>, i32, i32, i32) #0
+declare <2 x i32> @llvm.amdgcn.raw.buffer.load.v2i32(<4 x i32>, i32, i32, i32) #0
+declare <4 x i32> @llvm.amdgcn.raw.buffer.load.v4i32(<4 x i32>, i32, i32, i32) #0
 declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
 
 attributes #0 = { nounwind readonly }

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

@@ -142,9 +142,25 @@ define amdgpu_ps void @buffer_store_x2_offset_merged(<4 x i32> inreg %rsrc, <2 x
   ret void
 }
 
+;CHECK-LABEL: {{^}}buffer_store_int:
+;CHECK-NOT: s_waitcnt
+;CHECK: buffer_store_dwordx4 v[0:3], off, s[0:3], 0
+;CHECK: buffer_store_dwordx2 v[4:5], off, s[0:3], 0 glc
+;CHECK: buffer_store_dword v6, off, s[0:3], 0 slc
+define amdgpu_ps void @buffer_store_int(<4 x i32> inreg, <4 x i32>, <2 x i32>, i32) {
+main_body:
+  call void @llvm.amdgcn.raw.buffer.store.v4i32(<4 x i32> %1, <4 x i32> %0, i32 0, i32 0, i32 0)
+  call void @llvm.amdgcn.raw.buffer.store.v2i32(<2 x i32> %2, <4 x i32> %0, i32 0, i32 0, i32 1)
+  call void @llvm.amdgcn.raw.buffer.store.i32(i32 %3, <4 x i32> %0, i32 0, i32 0, i32 2)
+  ret void
+}
+
 declare void @llvm.amdgcn.raw.buffer.store.f32(float, <4 x i32>, i32, i32, i32) #0
 declare void @llvm.amdgcn.raw.buffer.store.v2f32(<2 x float>, <4 x i32>, i32, i32, i32) #0
 declare void @llvm.amdgcn.raw.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32) #0
+declare void @llvm.amdgcn.raw.buffer.store.i32(i32, <4 x i32>, i32, i32, i32) #0
+declare void @llvm.amdgcn.raw.buffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32) #0
+declare void @llvm.amdgcn.raw.buffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32) #0
 declare <4 x float> @llvm.amdgcn.raw.buffer.load.v4f32(<4 x i32>, i32, i32, i32) #1
 
 attributes #0 = { nounwind }

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

@@ -125,9 +125,31 @@ entry:
   ret float %val
 }
 
+;CHECK-LABEL: {{^}}buffer_load_int:
+;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
+;CHECK: buffer_load_dwordx2 v[4:5], {{v[0-9]+}}, s[0:3], 0 idxen glc
+;CHECK: buffer_load_dword v6, {{v[0-9]+}}, s[0:3], 0 idxen slc
+;CHECK: s_waitcnt
+define amdgpu_ps {<4 x float>, <2 x float>, float} @buffer_load_int(<4 x i32> inreg) {
+main_body:
+  %data = call <4 x i32> @llvm.amdgcn.struct.buffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0)
+  %data_glc = call <2 x i32> @llvm.amdgcn.struct.buffer.load.v2i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 1)
+  %data_slc = call i32 @llvm.amdgcn.struct.buffer.load.i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 2)
+  %fdata = bitcast <4 x i32> %data to <4 x float>
+  %fdata_glc = bitcast <2 x i32> %data_glc to <2 x float>
+  %fdata_slc = bitcast i32 %data_slc to float
+  %r0 = insertvalue {<4 x float>, <2 x float>, float} undef, <4 x float> %fdata, 0
+  %r1 = insertvalue {<4 x float>, <2 x float>, float} %r0, <2 x float> %fdata_glc, 1
+  %r2 = insertvalue {<4 x float>, <2 x float>, float} %r1, float %fdata_slc, 2
+  ret {<4 x float>, <2 x float>, float} %r2
+}
+
 declare float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32>, i32, i32, i32, i32) #0
 declare <2 x float> @llvm.amdgcn.struct.buffer.load.v2f32(<4 x i32>, i32, i32, i32, i32) #0
 declare <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32>, i32, i32, i32, i32) #0
+declare i32 @llvm.amdgcn.struct.buffer.load.i32(<4 x i32>, i32, i32, i32, i32) #0
+declare <2 x i32> @llvm.amdgcn.struct.buffer.load.v2i32(<4 x i32>, i32, i32, i32, i32) #0
+declare <4 x i32> @llvm.amdgcn.struct.buffer.load.v4i32(<4 x i32>, i32, i32, i32, i32) #0
 declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
 
 attributes #0 = { nounwind readonly }

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

@@ -95,9 +95,25 @@ main_body:
   ret void
 }
 
+;CHECK-LABEL: {{^}}buffer_store_int:
+;CHECK-NOT: s_waitcnt
+;CHECK: buffer_store_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
+;CHECK: buffer_store_dwordx2 v[4:5], {{v[0-9]+}}, s[0:3], 0 idxen glc
+;CHECK: buffer_store_dword v6, {{v[0-9]+}}, s[0:3], 0 idxen slc
+define amdgpu_ps void @buffer_store_int(<4 x i32> inreg, <4 x i32>, <2 x i32>, i32) {
+main_body:
+  call void @llvm.amdgcn.struct.buffer.store.v4i32(<4 x i32> %1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0)
+  call void @llvm.amdgcn.struct.buffer.store.v2i32(<2 x i32> %2, <4 x i32> %0, i32 0, i32 0, i32 0, i32 1)
+  call void @llvm.amdgcn.struct.buffer.store.i32(i32 %3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 2)
+  ret void
+}
+
 declare void @llvm.amdgcn.struct.buffer.store.f32(float, <4 x i32>, i32, i32, i32, i32) #0
 declare void @llvm.amdgcn.struct.buffer.store.v2f32(<2 x float>, <4 x i32>, i32, i32, i32, i32) #0
 declare void @llvm.amdgcn.struct.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32, i32) #0
+declare void @llvm.amdgcn.struct.buffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
+declare void @llvm.amdgcn.struct.buffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32, i32) #0
+declare void @llvm.amdgcn.struct.buffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32) #0
 declare <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32>, i32, i32, i32, i32) #1
 
 attributes #0 = { nounwind }