[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

4 files changed, 76 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.load.ll
index 797700e5b4f..76695077f00 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.load.ll
+++ b/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 }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.store.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.store.ll
index 64865115966..afb2ef803f0 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.store.ll
+++ b/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 }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.ll
index cd373e0796b..71fbdaa71b2 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.ll
+++ b/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 }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.store.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.store.ll
index 8e05c43889a..738bb16e7d6 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.store.ll
+++ b/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 }