[llvm] [LoadStoreVectorizer] Propagate alignment through contiguous chain (PR #145733)
Drew Kersnar via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 3 11:56:29 PDT 2025
================
@@ -0,0 +1,450 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=load-store-vectorizer -S < %s | FileCheck %s
+
+; The IR has the first float3 labeled with align 16, and that 16 should
+; be propagated such that the second set of 4 values
+; can also be vectorized together.
+%struct.float3 = type { float, float, float }
+%struct.S1 = type { %struct.float3, %struct.float3, i32, i32 }
+
+define void @testStore(ptr %1) {
+; CHECK-LABEL: define void @testStore(
+; CHECK-SAME: ptr [[TMP0:%.*]]) {
+; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[TMP0]], align 16
+; CHECK-NEXT: [[GETELEM10:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i64 0, i32 1, i32 1
+; CHECK-NEXT: store <4 x i32> zeroinitializer, ptr [[GETELEM10]], align 16
+; CHECK-NEXT: ret void
+;
+ store float 0.000000e+00, ptr %1, align 16
+ %getElem = getelementptr inbounds %struct.float3, ptr %1, i64 0, i32 1
+ store float 0.000000e+00, ptr %getElem, align 4
+ %getElem8 = getelementptr inbounds %struct.float3, ptr %1, i64 0, i32 2
+ store float 0.000000e+00, ptr %getElem8, align 8
+ %getElem9 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1
+ store float 0.000000e+00, ptr %getElem9, align 4
+ %getElem10 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1, i32 1
+ store float 0.000000e+00, ptr %getElem10, align 4
+ %getElem11 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1, i32 2
+ store float 0.000000e+00, ptr %getElem11, align 4
+ %getElem12 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 2
+ store i32 0, ptr %getElem12, align 8
+ %getElem13 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 3
+ store i32 0, ptr %getElem13, align 4
+ ret void
+}
+
+define void @testLoad(ptr %1) {
+; CHECK-LABEL: define void @testLoad(
+; CHECK-SAME: ptr [[TMP0:%.*]]) {
+; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr [[TMP0]], align 16
+; CHECK-NEXT: [[L11:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[L22:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[L33:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; CHECK-NEXT: [[L44:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
+; CHECK-NEXT: [[GETELEM10:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i64 0, i32 1, i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[GETELEM10]], align 16
+; CHECK-NEXT: [[L55:%.*]] = extractelement <4 x i32> [[TMP3]], i32 0
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32 [[L55]] to float
+; CHECK-NEXT: [[L66:%.*]] = extractelement <4 x i32> [[TMP3]], i32 1
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32 [[L66]] to float
+; CHECK-NEXT: [[L77:%.*]] = extractelement <4 x i32> [[TMP3]], i32 2
+; CHECK-NEXT: [[L88:%.*]] = extractelement <4 x i32> [[TMP3]], i32 3
+; CHECK-NEXT: ret void
+;
+ %l1 = load float, ptr %1, align 16
+ %getElem = getelementptr inbounds %struct.float3, ptr %1, i64 0, i32 1
+ %l2 = load float, ptr %getElem, align 4
+ %getElem8 = getelementptr inbounds %struct.float3, ptr %1, i64 0, i32 2
+ %l3 = load float, ptr %getElem8, align 8
+ %getElem9 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1
+ %l4 = load float, ptr %getElem9, align 4
+ %getElem10 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1, i32 1
+ %l5 = load float, ptr %getElem10, align 4
+ %getElem11 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 1, i32 2
+ %l6 = load float, ptr %getElem11, align 4
+ %getElem12 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 2
+ %l7 = load i32, ptr %getElem12, align 8
+ %getElem13 = getelementptr inbounds %struct.S1, ptr %1, i64 0, i32 3
+ %l8 = load i32, ptr %getElem13, align 4
+ ret void
+}
+
+; Also, test without the struct geps, to see if it still works with i8 geps/ptradd
+
+define void @testStorei8(ptr %1) {
+; CHECK-LABEL: define void @testStorei8(
+; CHECK-SAME: ptr [[TMP0:%.*]]) {
+; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[TMP0]], align 16
+; CHECK-NEXT: [[GETELEM10:%.*]] = getelementptr inbounds i8, ptr [[TMP0]], i64 16
+; CHECK-NEXT: store <4 x i32> zeroinitializer, ptr [[GETELEM10]], align 16
+; CHECK-NEXT: ret void
+;
+ store float 0.000000e+00, ptr %1, align 16
+ %getElem = getelementptr inbounds i8, ptr %1, i64 4
+ store float 0.000000e+00, ptr %getElem, align 4
+ %getElem8 = getelementptr inbounds i8, ptr %1, i64 8
+ store float 0.000000e+00, ptr %getElem8, align 8
+ %getElem9 = getelementptr inbounds i8, ptr %1, i64 12
+ store float 0.000000e+00, ptr %getElem9, align 4
+ %getElem10 = getelementptr inbounds i8, ptr %1, i64 16
+ store float 0.000000e+00, ptr %getElem10, align 4
+ %getElem11 = getelementptr inbounds i8, ptr %1, i64 20
+ store float 0.000000e+00, ptr %getElem11, align 4
+ %getElem12 = getelementptr inbounds i8, ptr %1, i64 24
+ store i32 0, ptr %getElem12, align 8
+ %getElem13 = getelementptr inbounds i8, ptr %1, i64 28
+ store i32 0, ptr %getElem13, align 4
+ ret void
+}
+
+define void @testLoadi8(ptr %1) {
+; CHECK-LABEL: define void @testLoadi8(
+; CHECK-SAME: ptr [[TMP0:%.*]]) {
+; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr [[TMP0]], align 16
+; CHECK-NEXT: [[L11:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[L22:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[L33:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; CHECK-NEXT: [[L44:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
+; CHECK-NEXT: [[GETELEM10:%.*]] = getelementptr inbounds i8, ptr [[TMP0]], i64 16
+; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, ptr [[GETELEM10]], align 16
+; CHECK-NEXT: [[L55:%.*]] = extractelement <4 x i32> [[TMP3]], i32 0
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32 [[L55]] to float
+; CHECK-NEXT: [[L66:%.*]] = extractelement <4 x i32> [[TMP3]], i32 1
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32 [[L66]] to float
+; CHECK-NEXT: [[L77:%.*]] = extractelement <4 x i32> [[TMP3]], i32 2
+; CHECK-NEXT: [[L88:%.*]] = extractelement <4 x i32> [[TMP3]], i32 3
+; CHECK-NEXT: ret void
+;
+ %l1 = load float, ptr %1, align 16
+ %getElem = getelementptr inbounds i8, ptr %1, i64 4
+ %l2 = load float, ptr %getElem, align 4
+ %getElem8 = getelementptr inbounds i8, ptr %1, i64 8
+ %l3 = load float, ptr %getElem8, align 8
+ %getElem9 = getelementptr inbounds i8, ptr %1, i64 12
+ %l4 = load float, ptr %getElem9, align 4
+ %getElem10 = getelementptr inbounds i8, ptr %1, i64 16
+ %l5 = load float, ptr %getElem10, align 4
+ %getElem11 = getelementptr inbounds i8, ptr %1, i64 20
+ %l6 = load float, ptr %getElem11, align 4
+ %getElem12 = getelementptr inbounds i8, ptr %1, i64 24
+ %l7 = load i32, ptr %getElem12, align 8
+ %getElem13 = getelementptr inbounds i8, ptr %1, i64 28
+ %l8 = load i32, ptr %getElem13, align 4
+ ret void
----------------
dakersnar wrote:
Slight pushback, my understanding is that lit tests are most useful when they are minimal reproducers of the problem the optimization is targeting. Adding uses would not really change the nature of this optimization. Tests like `llvm/test/Transforms/LoadStoreVectorizer/NVPTX/vectorize_i1.ll` follow this thinking.
If you think it would be better, I could combine each pair of load and store tests into individual tests, storing the result of the loads. Other LSV tests use that pattern a lot.
https://github.com/llvm/llvm-project/pull/145733
More information about the llvm-commits
mailing list