Skip to content

Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" #143043

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
Jun 6, 2025
Merged

Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" #143043

merged 2 commits into from
Jun 6, 2025

Conversation

farzonl
Copy link
Member

@farzonl farzonl commented Jun 5, 2025 •
edited
Loading

Noticed a really weird behavior where release and debug builds have different codegen for loads with geps after this PR. This is going to take a minute to debug and figure out why so revert seems to make the most sense.

diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50cf018..efa9efeff13a 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
@b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 6
+  ; CHECK-NEXT: %2 = load i32, ptr %1, align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @a, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
}
define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 0, i32 13
+  ; CHECK-NEXT: store i32 1, ptr %1, align 4
   ; CHECK-NEXT:    ret void

@llvmbot
Copy link
Member

llvmbot commented Jun 5, 2025

@llvm/pr-subscribers-backend-directx

Author: Farzon Lotfi (farzonl)

Changes

This reverts commit 9ab4c16.

Noticed a really weird behavior where release and debug builds have different codegen for loads with geps after this PR. This is going to take a minute to debug and figure out why so revert seems to make the most sense.

diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50cf018..efa9efeff13a 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -123,7 +123,8 @@ define void @<!-- -->gep_4d_test ()  {
@<!-- -->b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
define void @<!-- -->global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @<!-- -->a.1dim, i32 0, i32 6), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @<!-- -->a.1dim, i32 0, i32 6
+  ; CHECK-NEXT: %2 = load i32, ptr %1, align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @<!-- -->a, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -176,7 +177,8 @@ define void @<!-- -->global_incomplete_gep_chain(i32 %row, i32 %col) {
}
define void @<!-- -->global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @<!-- -->b.1dim, i32 0, i32 13), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @<!-- -->b.1dim, i32 0, i32 13
+  ; CHECK-NEXT: store i32 1, ptr %1, align 4
   ; CHECK-NEXT:    ret void

Full diff: https://github.com/llvm/llvm-project/pull/143043.diff

5 Files Affected:

  • (modified) llvm/lib/Target/DirectX/DXILFlattenArrays.cpp (+2-3)
  • (modified) llvm/test/CodeGen/DirectX/flatten-array.ll (+9-7)
  • (modified) llvm/test/CodeGen/DirectX/flatten-bug-117273.ll (+2-2)
  • (modified) llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll (+46-42)
  • (modified) llvm/test/CodeGen/DirectX/scalar-bug-117273.ll (+2-2)
diff --git a/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp b/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp
index a98ec01d9fd4b..a3163a8969642 100644
--- a/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp
+++ b/llvm/lib/Target/DirectX/DXILFlattenArrays.cpp
@@ -272,9 +272,8 @@ bool DXILFlattenArraysVisitor::visitGetElementPtrInstInGEPChainBase(
 
   ArrayType *FlattenedArrayType = GEPInfo.ParentArrayType;
   Value *FlatGEP =
-      Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand,
-                        {Builder.getInt32(0), FlatIndex},
-                        GEP.getName() + ".flat", GEP.getNoWrapFlags());
+      Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand, FlatIndex,
+                        GEP.getName() + ".flat", GEP.isInBounds());
 
   GEP.replaceAllUsesWith(FlatGEP);
   GEP.eraseFromParent();
diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50cf0186..754d5a25ca905 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -31,7 +31,7 @@ define void @alloca_4d_test ()  {
 ; CHECK-LABEL: gep_2d_test
 define void @gep_2d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [9 x i32], align 4
-    ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 0, i32 {{[0-8]}}
+    ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 {{[0-8]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [3 x [3 x i32]], align 4
     %g2d0 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* %1, i32 0, i32 0
@@ -53,7 +53,7 @@ define void @gep_2d_test ()  {
 ; CHECK-LABEL: gep_3d_test
 define void @gep_3d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [8 x i32], align 4
-    ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 0, i32 {{[0-7]}}
+    ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 {{[0-7]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [2 x[2 x [2 x i32]]], align 4
     %g3d0 = getelementptr inbounds [2 x[2 x [2 x i32]]], [2 x[2 x [2 x i32]]]* %1, i32 0, i32 0
@@ -76,7 +76,7 @@ define void @gep_3d_test ()  {
 ; CHECK-LABEL: gep_4d_test
 define void @gep_4d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [16 x i32], align 4
-    ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 0, i32 {{[0-9]|1[0-5]}}
+    ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 {{[0-9]|1[0-5]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [2x[2 x[2 x [2 x i32]]]], align 4
     %g4d0 = getelementptr inbounds [2x[2 x[2 x [2 x i32]]]], [2x[2 x[2 x [2 x i32]]]]* %1, i32 0, i32 0
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
 @b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
 
 define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 6
+  ; CHECK: load i32, ptr [[GEP_PTR]], align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @a, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -141,7 +142,7 @@ define void @global_gep_load_index(i32 %row, i32 %col, i32 %timeIndex) {
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul i32 [[ROW]], 12
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[TMP4]], [[TMP5]]
-; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP6]]
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP6]]
 ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}}
@@ -162,7 +163,7 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 0, [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i32 [[ROW]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]]
-; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP4]]
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP4]]
 ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}}
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
 }
 
 define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 13
+  ; CHECK:  store i32 1, ptr [[GEP_PTR]], align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @b, i32 0, i32 1
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 0
diff --git a/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
index c73e5017348d1..3ae5832ce8322 100644
--- a/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-bug-117273.ll
@@ -8,9 +8,9 @@
 define internal void @main() {
 ; CHECK-LABEL: define internal void @main() {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 0, i32 1
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 1
 ; CHECK-NEXT:    [[DOTI0:%.*]] = load float, ptr [[TMP0]], align 16
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 0, i32 2
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 2
 ; CHECK-NEXT:    [[DOTI03:%.*]] = load float, ptr [[TMP1]], align 16
 ; CHECK-NEXT:    ret void
 ;
diff --git a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
index c960aad3d2627..7e5a92e1311f8 100644
--- a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
+++ b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll
@@ -32,23 +32,23 @@ define <4 x i32> @load_array_vec_test() #0 {
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(3) [[TMP5]], align 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(3) [[TMP9]], align 4
-; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 1) to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(3) [[TMP11]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 2) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
-; CHECK-NEXT:    [[TMP15:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), i32 3) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP16:%.*]] = load i32, ptr addrspace(3) [[TMP15]], 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]]
+; CHECK-NEXT:    [[DOTI12:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 1) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI13:%.*]] = load i32, ptr addrspace(3) [[DOTI12]], align 4
+; CHECK-NEXT:    [[DOTI24:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 2) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI25:%.*]] = load i32, ptr addrspace(3) [[DOTI24]], align 4
+; CHECK-NEXT:    [[DOTI36:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 1), i32 3) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI37:%.*]] = load i32, ptr addrspace(3) [[DOTI36]], align 4
+; CHECK-NEXT:    [[DOTI08:%.*]] = add i32 [[TMP2]], [[TMP12]]
+; CHECK-NEXT:    [[DOTI19:%.*]] = add i32 [[TMP4]], [[DOTI13]]
+; CHECK-NEXT:    [[DOTI210:%.*]] = add i32 [[TMP6]], [[DOTI25]]
+; CHECK-NEXT:    [[DOTI311:%.*]] = add i32 [[TMP8]], [[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:    [[TMP16:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3
+; CHECK-NEXT:    ret <4 x i32> [[TMP16]]
 ;
   %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
@@ -81,19 +81,23 @@ define <4 x i32> @load_vec_test() #0 {
 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:    [[DOTFLAT:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 0, i32 [[INDEX]]
-; CHECK-NEXT:    [[DOTI0:%.*]] = load i32, ptr [[DOTFLAT]], align 4
-; CHECK-NEXT:    [[DOTFLAT_I1:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 1
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [12 x i32], ptr @staticArrayOfVecData.scalarized.1dim, i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
+; CHECK-NEXT:    [[DOTFLAT_I1:%.*]] = getelementptr i32, ptr [[TMP3]], i32 1
 ; CHECK-NEXT:    [[DOTI1:%.*]] = load i32, ptr [[DOTFLAT_I1]], align 4
-; CHECK-NEXT:    [[DOTFLAT_I2:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 2
+; CHECK-NEXT:    [[TMP4:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
+; CHECK-NEXT:    [[DOTFLAT_I2:%.*]] = getelementptr i32, ptr [[TMP4]], i32 2
 ; CHECK-NEXT:    [[DOTI2:%.*]] = load i32, ptr [[DOTFLAT_I2]], align 4
-; CHECK-NEXT:    [[DOTFLAT_I3:%.*]] = getelementptr i32, ptr [[DOTFLAT]], i32 3
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast ptr [[DOTFLAT]] to ptr
+; CHECK-NEXT:    [[DOTFLAT_I3:%.*]] = getelementptr i32, ptr [[TMP5]], i32 3
 ; 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]]
+; CHECK-NEXT:    [[DOTUPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2]], i32 0
+; CHECK-NEXT:    [[DOTUPTO1:%.*]] = insertelement <4 x i32> [[DOTUPTO0]], i32 [[DOTI1]], i32 1
+; CHECK-NEXT:    [[DOTUPTO2:%.*]] = insertelement <4 x i32> [[DOTUPTO1]], i32 [[DOTI2]], i32 2
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32> [[DOTUPTO2]], i32 [[DOTI3]], i32 3
+; CHECK-NEXT:    ret <4 x i32> [[TMP6]]
 ;
   %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
@@ -111,23 +115,23 @@ define <4 x i32> @multid_load_test() #0 {
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(3) [[TMP5]], align 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 3) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(3) [[TMP9]], align 4
-; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), i32 1) to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1) to ptr addrspace(3)
 ; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(3) [[TMP11]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), i32 2) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
-; CHECK-NEXT:    [[TMP15:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), i32 3) to ptr addrspace(3)
-; CHECK-NEXT:    [[TMP16:%.*]] = load i32, ptr addrspace(3) [[TMP15]], 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]]
+; CHECK-NEXT:    [[DOTI12:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 1) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI13:%.*]] = load i32, ptr addrspace(3) [[DOTI12]], align 4
+; CHECK-NEXT:    [[DOTI24:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 2) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI25:%.*]] = load i32, ptr addrspace(3) [[DOTI24]], align 4
+; CHECK-NEXT:    [[DOTI36:%.*]] = bitcast ptr addrspace(3) getelementptr (i32, ptr addrspace(3) getelementptr inbounds ([36 x i32], ptr addrspace(3) @groushared2dArrayofVectors.scalarized.1dim, i32 1), i32 3) to ptr addrspace(3)
+; CHECK-NEXT:    [[DOTI37:%.*]] = load i32, ptr addrspace(3) [[DOTI36]], align 4
+; CHECK-NEXT:    [[DOTI08:%.*]] = add i32 [[TMP2]], [[TMP12]]
+; CHECK-NEXT:    [[DOTI19:%.*]] = add i32 [[TMP4]], [[DOTI13]]
+; CHECK-NEXT:    [[DOTI210:%.*]] = add i32 [[TMP6]], [[DOTI25]]
+; CHECK-NEXT:    [[DOTI311:%.*]] = add i32 [[TMP8]], [[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:    [[TMP16:%.*]] = insertelement <4 x i32> [[DOTUPTO217]], i32 [[DOTI311]], i32 3
+; CHECK-NEXT:    ret <4 x i32> [[TMP16]]
 ;
   %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)* @"groushared2dArrayofVectors", 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)* @"groushared2dArrayofVectors", i32 0, i32 1, i32 1), align 4
diff --git a/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll
index a07ce2c24f7ac..2676abec1d8ae 100644
--- a/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll
+++ b/llvm/test/CodeGen/DirectX/scalar-bug-117273.ll
@@ -8,13 +8,13 @@
 define internal void @main() #1 {
 ; CHECK-LABEL: define internal void @main() {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 0, i32 1
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 1
 ; CHECK-NEXT:    [[DOTI0:%.*]] = load float, ptr [[TMP0]], align 16
 ; CHECK-NEXT:    [[DOTI1:%.*]] = getelementptr float, ptr [[TMP0]], i32 1
 ; CHECK-NEXT:    [[DOTI11:%.*]] = load float, ptr [[DOTI1]], align 4
 ; CHECK-NEXT:    [[DOTI2:%.*]] = getelementptr float, ptr [[TMP0]], i32 2
 ; CHECK-NEXT:    [[DOTI22:%.*]] = load float, ptr [[DOTI2]], align 8
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 0, i32 2
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [24 x float], ptr @StaticArr.scalarized.1dim, i32 2
 ; CHECK-NEXT:    [[DOTI03:%.*]] = load float, ptr [[TMP1]], align 16
 ; CHECK-NEXT:    [[DOTI14:%.*]] = getelementptr float, ptr [[TMP1]], i32 1
 ; CHECK-NEXT:    [[DOTI15:%.*]] = load float, ptr [[DOTI14]], align 4

@farzonl farzonl force-pushed the revert_gep_change branch from f626e91 to babc67e Compare June 6, 2025 00:03
@farzonl farzonl changed the title Revert "[DirectX] Array GEPs need two indices (#142853)" Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" Jun 6, 2025
@farzonl farzonl merged commit 76c4ba6 into llvm:main Jun 6, 2025
6 of 8 checks passed
rorth pushed a commit to rorth/llvm-project that referenced this pull request Jun 11, 2025
@farzonl @rorth
Revert "[DirectX] Array GEPs need two indices (llvm#142853)" and "Adj…
60dacef 
…ust bit cast instruction filter for DXIL Prepare pass (llvm#142678)" (llvm#143043)

- This reverts commit 9ab4c16.
- This reverts commit 1d6e8ec.

Noticed a really weird behavior where release and debug builds have
different codegen for loads with geps after this PR. This is going to
take a minute to debug and figure out why so revert seems to make the
most sense.

```diff
diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50..efa9efe 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
@b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 6
+  ; CHECK-NEXT: %2 = load i32, ptr %1, align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @A, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
}
define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 0, i32 13
+  ; CHECK-NEXT: store i32 1, ptr %1, align 4
   ; CHECK-NEXT:    ret void
```
DhruvSrivastavaX pushed a commit to DhruvSrivastavaX/lldb-for-aix that referenced this pull request Jun 12, 2025
@farzonl @DhruvSrivastavaX
Revert "[DirectX] Array GEPs need two indices (llvm#142853)" and "Adj…
ee12d29 
…ust bit cast instruction filter for DXIL Prepare pass (llvm#142678)" (llvm#143043)

- This reverts commit 9ab4c16.
- This reverts commit 1d6e8ec.

Noticed a really weird behavior where release and debug builds have
different codegen for loads with geps after this PR. This is going to
take a minute to debug and figure out why so revert seems to make the
most sense.

```diff
diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50..efa9efe 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
@b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 6
+  ; CHECK-NEXT: %2 = load i32, ptr %1, align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @A, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
}
define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 0, i32 13
+  ; CHECK-NEXT: store i32 1, ptr %1, align 4
   ; CHECK-NEXT:    ret void
```
@farzonl farzonl self-assigned this Jun 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bob80905 bob80905 bob80905 approved these changes

@inbelic inbelic inbelic approved these changes

Assignees

@farzonl farzonl

Labels
backend:DirectX
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@farzonl @llvmbot @bob80905 @inbelic