shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
Deric C. 689e95817e
[DirectX] Add a GEP to scalar load/store on globals and remove incorrect assertion (#149191) 
Fixes #149180

This PR removes an assertion that triggered on valid IR. It has been
replaced with an if statement that returns early if the conditions are
not correct.

This PR also adds GEPs to scalar loads and stores from/to global
variables.
2025-07-17 14:46:45 -07:00

234 lines
17 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --tool llc --version 5
; RUN: llc %s -mtriple=dxil-pc-shadermodel6.3-library --filetype=asm -o - | FileCheck %s
; Make sure we can load groupshared, static vectors and arrays of vectors
@"arrayofVecData" = local_unnamed_addr addrspace(3) global [2 x <4 x i32>] zeroinitializer, align 16
@"vecData" = external addrspace(3) global <4 x i32>, align 4
@staticArrayOfVecData = internal global [3 x <4 x i32>] [<4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32> <i32 5, i32 6, i32 7, i32 8>, <4 x i32> <i32 9, i32 10, i32 11, i32 12>], align 4
@"groupshared2dArrayofVectors" = local_unnamed_addr addrspace(3) global [3 x [3 x <4 x i32>]] zeroinitializer, align 16
; CHECK: @arrayofVecData.scalarized.1dim = local_unnamed_addr addrspace(3) global [8 x i32] zeroinitializer, align 16
; CHECK: @vecData.scalarized = external addrspace(3) global [4 x i32], align 4
; CHECK: @staticArrayOfVecData.scalarized.1dim = internal global [12 x i32] [i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12], align 4
; CHECK: @groupshared2dArrayofVectors.scalarized.1dim = local_unnamed_addr addrspace(3) global [36 x i32] zeroinitializer, align 16
; CHECK-NOT: @arrayofVecData
; CHECK-NOT: @arrayofVecData.scalarized
; CHECK-NOT: @vecData
; CHECK-NOT: @staticArrayOfVecData
; CHECK-NOT: @staticArrayOfVecData.scalarized
; CHECK-NOT: @groupshared2dArrayofVectors
; CHECK-NOT: @groupshared2dArrayofVectors.scalarized
define <4 x i32> @load_array_vec_test() #0 {
; CHECK-LABEL: define <4 x i32> @load_array_vec_test(
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 0
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), align 4
; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 2), align 4
; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 3), align 4
; CHECK-NEXT: [[TMP10:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4
; CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4
; CHECK-NEXT: [[TMP14:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4
; CHECK-NEXT: [[TMP16:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4
; CHECK-NEXT: [[DOTI05:%.*]] = add i32 [[TMP2]], [[TMP10]]
; CHECK-NEXT: [[DOTI16:%.*]] = add i32 [[TMP4]], [[TMP12]]
; CHECK-NEXT: [[DOTI27:%.*]] = add i32 [[TMP6]], [[TMP14]]
; CHECK-NEXT: [[DOTI38:%.*]] = add i32 [[TMP8]], [[TMP16]]
; CHECK-NEXT: [[DOTUPTO01215:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI05]], i32 0
; CHECK-NEXT: [[DOTUPTO11316:%.*]] = insertelement <4 x i32> [[DOTUPTO01215]], i32 [[DOTI16]], i32 1
; CHECK-NEXT: [[DOTUPTO21417:%.*]] = insertelement <4 x i32> [[DOTUPTO11316]], i32 [[DOTI27]], i32 2
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <4 x i32> [[DOTUPTO21417]], i32 [[DOTI38]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP17]]
;
%1 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([2 x <4 x i32>], [2 x <4 x i32>] addrspace(3)* @"arrayofVecData", i32 0, i32 0), align 4
%2 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([2 x <4 x i32>], [2 x <4 x i32>] addrspace(3)* @"arrayofVecData", i32 0, i32 1), align 4
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @load_vec_test() #0 {
; CHECK-LABEL: define <4 x i32> @load_vec_test(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 0
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 1), align 4
; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 2), align 4
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 3), align 4
; CHECK-NEXT: [[DOTUPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP1]], i32 0
; CHECK-NEXT: [[DOTUPTO1:%.*]] = insertelement <4 x i32> [[DOTUPTO0]], i32 [[TMP2]], i32 1
; CHECK-NEXT: [[DOTUPTO2:%.*]] = insertelement <4 x i32> [[DOTUPTO1]], i32 [[TMP3]], i32 2
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> [[DOTUPTO2]], i32 [[TMP4]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP5]]
;
%1 = load <4 x i32>, <4 x i32> addrspace(3)* @"vecData", align 4
ret <4 x i32> %1
}
define <4 x i32> @load_vec_from_scalar_gep_test() #0 {
; CHECK-LABEL: define <4 x i32> @load_vec_from_scalar_gep_test(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[DOTI04:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds nuw ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4
; CHECK-NEXT: [[DOTI116:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4
; CHECK-NEXT: [[DOTI228:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4
; CHECK-NEXT: [[DOTI3310:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4
; CHECK-NEXT: [[DOTUPTO011:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI04]], i32 0
; CHECK-NEXT: [[DOTUPTO112:%.*]] = insertelement <4 x i32> [[DOTUPTO011]], i32 [[DOTI116]], i32 1
; CHECK-NEXT: [[DOTUPTO213:%.*]] = insertelement <4 x i32> [[DOTUPTO112]], i32 [[DOTI228]], i32 2
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO213]], i32 [[DOTI3310]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
;
%1 = getelementptr inbounds nuw i32, ptr addrspace(3) @"arrayofVecData", i32 4
%2 = load <4 x i32>, ptr addrspace(3) %1, align 4
ret <4 x i32> %2
}
define <4 x i32> @load_vec_from_i8_gep_test() #0 {
; CHECK-LABEL: define <4 x i32> @load_vec_from_i8_gep_test(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[DOTI04:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds nuw ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 4), align 4
; CHECK-NEXT: [[DOTI116:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 5), align 4
; CHECK-NEXT: [[DOTI228:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 6), align 4
; CHECK-NEXT: [[DOTI3310:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 7), align 4
; CHECK-NEXT: [[DOTUPTO011:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI04]], i32 0
; CHECK-NEXT: [[DOTUPTO112:%.*]] = insertelement <4 x i32> [[DOTUPTO011]], i32 [[DOTI116]], i32 1
; CHECK-NEXT: [[DOTUPTO213:%.*]] = insertelement <4 x i32> [[DOTUPTO112]], i32 [[DOTI228]], i32 2
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO213]], i32 [[DOTI3310]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
;
%1 = getelementptr inbounds nuw i8, ptr addrspace(3) @"arrayofVecData", i32 16
%2 = load <4 x i32>, ptr addrspace(3) %1, align 4
ret <4 x i32> %2
}
define <4 x i32> @load_static_array_of_vec_test(i32 %index) #0 {
; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_test(
; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[TMP3]]
; CHECK-NEXT: [[DOTFLAT:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP2]]
; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[DOTFLAT]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = mul i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP5:%.*]] = add i32 1, [[TMP4]]
; CHECK-NEXT: [[DOTFLAT_I1:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP5]]
; CHECK-NEXT: [[DOTI1:%.*]] = load i32, ptr [[DOTFLAT_I1]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP7:%.*]] = add i32 2, [[TMP6]]
; CHECK-NEXT: [[DOTFLAT_I2:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP7]]
; CHECK-NEXT: [[DOTI2:%.*]] = load i32, ptr [[DOTFLAT_I2]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = mul i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP9:%.*]] = add i32 3, [[TMP8]]
; CHECK-NEXT: [[DOTFLAT_I3:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP9]]
; CHECK-NEXT: [[DOTI3:%.*]] = load i32, ptr [[DOTFLAT_I3]], align 4
; CHECK-NEXT: [[DOTUPTO01:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0
; CHECK-NEXT: [[DOTUPTO12:%.*]] = insertelement <4 x i32> [[DOTUPTO01]], i32 [[DOTI1]], i32 1
; CHECK-NEXT: [[DOTUPTO23:%.*]] = insertelement <4 x i32> [[DOTUPTO12]], i32 [[DOTI2]], i32 2
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[DOTUPTO23]], i32 [[DOTI3]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
;
%3 = getelementptr inbounds [3 x <4 x i32>], [3 x <4 x i32>]* @staticArrayOfVecData, i32 0, i32 %index
%4 = load <4 x i32>, <4 x i32>* %3, align 4
ret <4 x i32> %4
}
define <4 x i32> @load_static_array_of_vec_from_scalar_gep_test(i32 %index) #0 {
; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_from_scalar_gep_test(
; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP3:%.*]] = add i32 0, [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP3]]
; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[TMP4]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP6:%.*]] = add i32 1, [[TMP5]]
; CHECK-NEXT: [[DOTI14:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP6]]
; CHECK-NEXT: [[DOTI11:%.*]] = load i32, ptr [[DOTI14]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP8:%.*]] = add i32 2, [[TMP7]]
; CHECK-NEXT: [[DOTI25:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP8]]
; CHECK-NEXT: [[DOTI22:%.*]] = load i32, ptr [[DOTI25]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP10:%.*]] = add i32 3, [[TMP9]]
; CHECK-NEXT: [[DOTI36:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP10]]
; CHECK-NEXT: [[DOTI33:%.*]] = load i32, ptr [[DOTI36]], align 4
; CHECK-NEXT: [[DOTUPTO07:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0
; CHECK-NEXT: [[DOTUPTO18:%.*]] = insertelement <4 x i32> [[DOTUPTO07]], i32 [[DOTI11]], i32 1
; CHECK-NEXT: [[DOTUPTO29:%.*]] = insertelement <4 x i32> [[DOTUPTO18]], i32 [[DOTI22]], i32 2
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[DOTUPTO29]], i32 [[DOTI33]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP11]]
;
%2 = mul i32 %index, 4
%3 = getelementptr inbounds i32, ptr @staticArrayOfVecData, i32 %2
%4 = load <4 x i32>, <4 x i32>* %3, align 4
ret <4 x i32> %4
}
define <4 x i32> @load_static_array_of_vec_from_i8_gep_test(i32 %index) #0 {
; CHECK-LABEL: define <4 x i32> @load_static_array_of_vec_from_i8_gep_test(
; CHECK-SAME: i32 [[INDEX:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[INDEX]], 12
; CHECK-NEXT: [[TMP2:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP12:%.*]] = lshr i32 [[TMP2]], 2
; CHECK-NEXT: [[TMP3:%.*]] = add i32 0, [[TMP12]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP3]]
; CHECK-NEXT: [[DOTI0:%.*]] = load i32, ptr [[TMP4]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP14:%.*]] = lshr i32 [[TMP5]], 2
; CHECK-NEXT: [[TMP6:%.*]] = add i32 1, [[TMP14]]
; CHECK-NEXT: [[DOTI14:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP6]]
; CHECK-NEXT: [[DOTI11:%.*]] = load i32, ptr [[DOTI14]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP15:%.*]] = lshr i32 [[TMP7]], 2
; CHECK-NEXT: [[TMP8:%.*]] = add i32 2, [[TMP15]]
; CHECK-NEXT: [[DOTI25:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP8]]
; CHECK-NEXT: [[DOTI22:%.*]] = load i32, ptr [[DOTI25]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[TMP1]], 1
; CHECK-NEXT: [[TMP13:%.*]] = lshr i32 [[TMP9]], 2
; CHECK-NEXT: [[TMP10:%.*]] = add i32 3, [[TMP13]]
; CHECK-NEXT: [[DOTI36:%.*]] = getelementptr [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[TMP10]]
; CHECK-NEXT: [[DOTI33:%.*]] = load i32, ptr [[DOTI36]], align 4
; CHECK-NEXT: [[DOTUPTO07:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI0]], i32 0
; CHECK-NEXT: [[DOTUPTO18:%.*]] = insertelement <4 x i32> [[DOTUPTO07]], i32 [[DOTI11]], i32 1
; CHECK-NEXT: [[DOTUPTO29:%.*]] = insertelement <4 x i32> [[DOTUPTO18]], i32 [[DOTI22]], i32 2
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[DOTUPTO29]], i32 [[DOTI33]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP11]]
;
%2 = mul i32 %index, 12
%3 = getelementptr inbounds i8, ptr @staticArrayOfVecData, i32 %2
%4 = load <4 x i32>, <4 x i32>* %3, align 4
ret <4 x i32> %4
}
define <4 x i32> @multid_load_test() #0 {
; CHECK-LABEL: define <4 x i32> @multid_load_test(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 0
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), align 4
; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 2), align 4
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 3), align 4
; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 16), align 4
; CHECK-NEXT: [[DOTI13:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 17), align 4
; CHECK-NEXT: [[DOTI25:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 18), align 4
; CHECK-NEXT: [[DOTI37:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 19), align 4
; CHECK-NEXT: [[DOTI08:%.*]] = add i32 [[TMP1]], [[TMP5]]
; CHECK-NEXT: [[DOTI19:%.*]] = add i32 [[TMP2]], [[DOTI13]]
; CHECK-NEXT: [[DOTI210:%.*]] = add i32 [[TMP3]], [[DOTI25]]
; CHECK-NEXT: [[DOTI311:%.*]] = add i32 [[TMP4]], [[DOTI37]]
; CHECK-NEXT: [[DOTUPTO015:%.*]] = insertelement <4 x i32> poison, i32 [[DOTI08]], i32 0
; CHECK-NEXT: [[DOTUPTO116:%.*]] = insertelement <4 x i32> [[DOTUPTO015]], i32 [[DOTI19]], i32 1
; CHECK-NEXT: [[DOTUPTO217:%.*]] = insertelement <4 x i32> [[DOTUPTO116]], i32 [[DOTI210]], i32 2
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3
; CHECK-NEXT: ret <4 x i32> [[TMP6]]
;
%1 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([3 x [3 x <4 x i32>]], [3 x [3 x <4 x i32>]] addrspace(3)* @"groupshared2dArrayofVectors", i32 0, i32 0, i32 0), align 4
%2 = load <4 x i32>, <4 x i32> addrspace(3)* getelementptr inbounds ([3 x [3 x <4 x i32>]], [3 x [3 x <4 x i32>]] addrspace(3)* @"groupshared2dArrayofVectors", i32 0, i32 1, i32 1), align 4
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
attributes #0 = { convergent norecurse nounwind "hlsl.export"}
Reference in New Issue View Git Blame Copy Permalink