[llvm] a0e258d - [AMDGPU] Add tests for future commit

Konstantina Mitropoulou via llvm-commits llvm-commits at lists.llvm.org
Mon Feb 20 21:39:17 PST 2023


Author: Konstantina Mitropoulou
Date: 2023-02-20T21:36:25-08:00
New Revision: a0e258da1944d9a1aa4bce40f692d5de488f908b

URL: https://github.com/llvm/llvm-project/commit/a0e258da1944d9a1aa4bce40f692d5de488f908b
DIFF: https://github.com/llvm/llvm-project/commit/a0e258da1944d9a1aa4bce40f692d5de488f908b.diff

LOG: [AMDGPU] Add tests for future commit

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D144312

Added: 
    

Modified: 
    llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll
index 3add36b7016d9..8d5dcc1db5717 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll
@@ -452,6 +452,49 @@ define amdgpu_ps float @raw_buffer_load_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffse
   ret float %cast
 }
 
+define amdgpu_ps float @raw_buffer_load_i16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_zext(<4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
+  ; CHECK-LABEL: name: raw_buffer_load_i16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_zext
+  ; CHECK: bb.1 (%ir-block.0):
+  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr2
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr3
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr4
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr5
+  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
+  ; CHECK-NEXT:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 7)
+  ; CHECK-NEXT:   $vgpr0 = COPY [[BUFFER_LOAD_USHORT_OFFEN]]
+  ; CHECK-NEXT:   SI_RETURN_TO_EPILOG implicit $vgpr0
+  %val = call i16 @llvm.amdgcn.raw.buffer.load.i16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
+  %zext = zext i16 %val to i32
+  %cast = bitcast i32 %zext to float
+  ret float %cast
+}
+
+define amdgpu_ps float @raw_buffer_load_i16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_sext(<4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
+  ; CHECK-LABEL: name: raw_buffer_load_i16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_sext
+  ; CHECK: bb.1 (%ir-block.0):
+  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr2
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr3
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr4
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr5
+  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
+  ; CHECK-NEXT:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 7)
+  ; CHECK-NEXT:   [[V_BFE_I32_e64_:%[0-9]+]]:vgpr_32 = V_BFE_I32_e64 [[BUFFER_LOAD_USHORT_OFFEN]], 0, 16, implicit $exec
+  ; CHECK-NEXT:   $vgpr0 = COPY [[V_BFE_I32_e64_]]
+  ; CHECK-NEXT:   SI_RETURN_TO_EPILOG implicit $vgpr0
+  %val = call i16 @llvm.amdgcn.raw.buffer.load.i16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
+  %sext = sext i16 %val to i32
+  %cast = bitcast i32 %sext to float
+  ret float %cast
+}
+
 ; Waterfall for rsrc
 define amdgpu_ps half @raw_buffer_load_f16__vgpr_rsrc__vgpr_voffset__sgpr_soffset(<4 x i32> %rsrc, i32 %voffset, i32 inreg %soffset) {
   ; CHECK-LABEL: name: raw_buffer_load_f16__vgpr_rsrc__vgpr_voffset__sgpr_soffset
@@ -903,3 +946,4 @@ declare <3 x half> @llvm.amdgcn.raw.buffer.load.v3f16(<4 x i32>, i32, i32, i32 i
 declare <4 x half> @llvm.amdgcn.raw.buffer.load.v4f16(<4 x i32>, i32, i32, i32 immarg)
 
 declare i8 @llvm.amdgcn.raw.buffer.load.i8(<4 x i32>, i32, i32, i32 immarg)
+declare i16 @llvm.amdgcn.raw.buffer.load.i16(<4 x i32>, i32, i32, i32 immarg)


        


More information about the llvm-commits mailing list