forked from OSchip/llvm-project
831 lines
63 KiB
LLVM
831 lines
63 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -stop-after=legalizer -o - %s | FileCheck -check-prefix=GFX10 %s
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, float %s) {
|
|
; GFX10-LABEL: name: sample_d_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY15]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.d.1d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY14]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f16.f32(i32 15, half %dsdh, half %dsdv, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t) {
|
|
; GFX10-LABEL: name: sample_d_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY18]](s32), [[COPY19]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY20]](s32), [[COPY21]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.d.2d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY16]](s32), [[COPY17]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f16.f32(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_3d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %drdh, half %dsdv, half %dtdv, half %drdv, float %s, float %t, float %r) {
|
|
; GFX10-LABEL: name: sample_d_3d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY $vgpr7
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[COPY23:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY23]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY24:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[COPY25:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC2:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY24]](s32), [[COPY25]](s32)
|
|
; GFX10: [[COPY26:%[0-9]+]]:_(s32) = COPY [[COPY17]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC3:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY26]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.d.3d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[BUILD_VECTOR_TRUNC2]](<2 x s16>), [[BUILD_VECTOR_TRUNC3]](<2 x s16>), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.3d.v4f32.f16.f32(i32 15, half %dsdh, half %dtdh, half %drdh, half %dsdv, half %dtdv, half %drdv, float %s, float %t, float %r, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, float %s) {
|
|
; GFX10-LABEL: name: sample_c_d_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.1d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY15]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dsdv, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t) {
|
|
; GFX10-LABEL: name: sample_c_d_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY19]](s32), [[COPY20]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.2d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY17]](s32), [[COPY18]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, float %s, float %clamp) {
|
|
; GFX10-LABEL: name: sample_d_cl_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.d.cl.1d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY14]](s32), [[COPY15]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f16.f32(i32 15, half %dsdh, half %dsdv, float %s, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp) {
|
|
; GFX10-LABEL: name: sample_d_cl_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY19]](s32), [[COPY20]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.d.cl.2d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f16.f32(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, float %s, float %clamp) {
|
|
; GFX10-LABEL: name: sample_c_d_cl_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY18]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.cl.1d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY15]](s32), [[COPY16]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dsdv, float %s, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp) {
|
|
; GFX10-LABEL: name: sample_c_d_cl_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY $vgpr7
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY20]](s32), [[COPY21]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[COPY23:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY22]](s32), [[COPY23]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.cl.2d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, float %s) {
|
|
; GFX10-LABEL: name: sample_cd_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY15]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.cd.1d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY14]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f16.f32(i32 15, half %dsdh, half %dsdv, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t) {
|
|
; GFX10-LABEL: name: sample_cd_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY18]](s32), [[COPY19]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY20]](s32), [[COPY21]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.cd.2d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY16]](s32), [[COPY17]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f16.f32(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, float %s) {
|
|
; GFX10-LABEL: name: sample_c_cd_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.cd.1d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY15]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dsdv, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t) {
|
|
; GFX10-LABEL: name: sample_c_cd_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY19]](s32), [[COPY20]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.cd.2d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY17]](s32), [[COPY18]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, float %s, float %clamp) {
|
|
; GFX10-LABEL: name: sample_cd_cl_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY16]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.cd.cl.1d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY14]](s32), [[COPY15]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f16.f32(i32 15, half %dsdh, half %dsdv, float %s, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp) {
|
|
; GFX10-LABEL: name: sample_cd_cl_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY12]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY19]](s32), [[COPY20]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.cd.cl.2d), 15, [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f16.f32(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, float %s, float %clamp) {
|
|
; GFX10-LABEL: name: sample_c_cd_cl_1d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY17]](s32), [[DEF]](s32)
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY18]](s32), [[DEF]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.cd.cl.1d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY15]](s32), [[COPY16]](s32), [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dsdv, float %s, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp) {
|
|
; GFX10-LABEL: name: sample_c_cd_cl_2d
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY $vgpr7
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY13]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY20]](s32), [[COPY21]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[COPY23:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY22]](s32), [[COPY23]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.cd.cl.2d), 15, [[BITCAST]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 16 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<4 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: $vgpr2 = COPY [[UV2]](s32)
|
|
; GFX10: $vgpr3 = COPY [[UV3]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f16.f32(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps float @sample_c_d_o_2darray_V1(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %slice) {
|
|
; GFX10-LABEL: name: sample_c_d_o_2darray_V1
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY $vgpr7
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY13]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[COPY23:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[COPY24:%[0-9]+]]:_(s32) = COPY [[COPY17]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY23]](s32), [[COPY24]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(s32) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.o.2darray), 4, [[BITCAST]](<2 x s16>), [[BITCAST1]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 4 from custom "TargetCustom8")
|
|
; GFX10: $vgpr0 = COPY [[AMDGPU_INTRIN_IMAGE_LOAD]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0
|
|
main_body:
|
|
%v = call float @llvm.amdgcn.image.sample.c.d.o.2darray.f16.f32.f32(i32 4, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret float %v
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_c_d_o_2darray_V2(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %slice) {
|
|
; GFX10-LABEL: name: sample_c_d_o_2darray_V2
|
|
; GFX10: bb.1.main_body:
|
|
; GFX10: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
|
|
; GFX10: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
|
|
; GFX10: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr5
|
|
; GFX10: [[COPY4:%[0-9]+]]:_(s32) = COPY $sgpr6
|
|
; GFX10: [[COPY5:%[0-9]+]]:_(s32) = COPY $sgpr7
|
|
; GFX10: [[COPY6:%[0-9]+]]:_(s32) = COPY $sgpr8
|
|
; GFX10: [[COPY7:%[0-9]+]]:_(s32) = COPY $sgpr9
|
|
; GFX10: [[COPY8:%[0-9]+]]:_(s32) = COPY $sgpr10
|
|
; GFX10: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr11
|
|
; GFX10: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr12
|
|
; GFX10: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr13
|
|
; GFX10: [[COPY12:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY13:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[COPY14:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; GFX10: [[COPY15:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; GFX10: [[COPY16:%[0-9]+]]:_(s32) = COPY $vgpr4
|
|
; GFX10: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr5
|
|
; GFX10: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr6
|
|
; GFX10: [[COPY19:%[0-9]+]]:_(s32) = COPY $vgpr7
|
|
; GFX10: [[COPY20:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
|
|
; GFX10: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY12]](s32)
|
|
; GFX10: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY13]](s32)
|
|
; GFX10: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY14]](s32)
|
|
; GFX10: [[COPY22:%[0-9]+]]:_(s32) = COPY [[COPY15]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY21]](s32), [[COPY22]](s32)
|
|
; GFX10: [[COPY23:%[0-9]+]]:_(s32) = COPY [[COPY16]](s32)
|
|
; GFX10: [[COPY24:%[0-9]+]]:_(s32) = COPY [[COPY17]](s32)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY23]](s32), [[COPY24]](s32)
|
|
; GFX10: [[AMDGPU_INTRIN_IMAGE_LOAD:%[0-9]+]]:_(<2 x s32>) = G_AMDGPU_INTRIN_IMAGE_LOAD intrinsic(@llvm.amdgcn.image.sample.c.d.o.2darray), 6, [[BITCAST]](<2 x s16>), [[BITCAST1]](<2 x s16>), [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), $noreg, $noreg, [[BUILD_VECTOR]](<8 x s32>), [[BUILD_VECTOR1]](<4 x s32>), 0, 0, 0, 2 :: (dereferenceable load 8 from custom "TargetCustom8")
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[AMDGPU_INTRIN_IMAGE_LOAD]](<2 x s32>)
|
|
; GFX10: $vgpr0 = COPY [[UV]](s32)
|
|
; GFX10: $vgpr1 = COPY [[UV1]](s32)
|
|
; GFX10: SI_RETURN_TO_EPILOG implicit $vgpr0, implicit $vgpr1
|
|
main_body:
|
|
%v = call <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f16.f32(i32 6, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f16.f32(i32, half, half, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f16.f32(i32, half, half, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.3d.v4f32.f16.f32(i32, half, half, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f16.f32(i32, float, half, half, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f16.f32(i32, float, half, half, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f16.f32(i32, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f16.f32(i32, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f16.f32(i32, float, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f16.f32(i32, float, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f16.f32(i32, half, half, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f16.f32(i32, half, half, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f16.f32(i32, float, half, half, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f16.f32(i32, float, half, half, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f16.f32(i32, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f16.f32(i32, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f16.f32(i32, float, half, half, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f16.f32(i32, float, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare float @llvm.amdgcn.image.sample.c.d.o.2darray.f16.f32.f32(i32, i32, float, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f16.f32(i32, i32, float, half, half, half, half, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|
|
attributes #2 = { nounwind readnone }
|