1 files changed, 180 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoadStoreVectorizer/X86/massive_indirection.ll b/llvm/test/Transforms/LoadStoreVectorizer/X86/massive_indirection.ll
new file mode 100644
index 000000000000..fe8a7e58a6a5
--- /dev/null
+++ b/llvm/test/Transforms/LoadStoreVectorizer/X86/massive_indirection.ll
@@ -0,0 +1,180 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt %s -mtriple=x86_64-unknown-linux-gnu -passes=load-store-vectorizer -mcpu=skx -S -o - | FileCheck %s
+
+; This test verifies that the vectorizer can handle an extended sequence of
+; getelementptr instructions and generate longer vectors. With special handling,
+; some elements can still be vectorized even if they require looking up the
+; common underlying object deeper than 6 levels from the original pointer.
+
+; The test below is the simplified version of actual performance oriented
+; workload; the offsets in getelementptr instructions are similar or same for
+; the test simplicity.
+
+define void @v1_v2_v4_v1_to_v8_levels_6_7_8_8(i32 %arg0, ptr align 16 %arg1) {
+; CHECK-LABEL: define void @v1_v2_v4_v1_to_v8_levels_6_7_8_8(
+; CHECK-SAME: i32 [[ARG0:%.*]], ptr align 16 [[ARG1:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:    [[LEVEL1:%.*]] = getelementptr i8, ptr [[ARG1]], i32 917504
+; CHECK-NEXT:    [[LEVEL2:%.*]] = getelementptr i8, ptr [[LEVEL1]], i32 [[ARG0]]
+; CHECK-NEXT:    [[LEVEL3:%.*]] = getelementptr i8, ptr [[LEVEL2]], i32 32768
+; CHECK-NEXT:    [[LEVEL4:%.*]] = getelementptr i8, ptr [[LEVEL3]], i32 [[ARG0]]
+; CHECK-NEXT:    [[LEVEL5:%.*]] = getelementptr i8, ptr [[LEVEL4]], i32 [[ARG0]]
+; CHECK-NEXT:    [[A6:%.*]] = getelementptr i8, ptr [[LEVEL5]], i32 [[ARG0]]
+; CHECK-NEXT:    store <8 x half> zeroinitializer, ptr [[A6]], align 16
+; CHECK-NEXT:    ret void
+;
+
+  %level1 = getelementptr i8, ptr %arg1, i32 917504
+  %level2 = getelementptr i8, ptr %level1, i32 %arg0
+  %level3 = getelementptr i8, ptr %level2, i32 32768
+  %level4 = getelementptr i8, ptr %level3, i32 %arg0
+  %level5 = getelementptr i8, ptr %level4, i32 %arg0
+
+  %a6 = getelementptr i8, ptr %level5, i32 %arg0
+  %b7 = getelementptr i8, ptr %a6, i32 2
+  %c8 = getelementptr i8, ptr %b7, i32 8
+  %d8 = getelementptr i8, ptr %b7, i32 12
+
+  store half 0xH0000, ptr %a6, align 16
+  store <4 x half> zeroinitializer, ptr %b7, align 2
+  store <2 x half> zeroinitializer, ptr %c8, align 2
+  store half 0xH0000, ptr %d8, align 2
+  ret void
+}
+
+define void @v1x8_levels_6_7_8_9_10_11_12_13(i32 %arg0, ptr align 16 %arg1) {
+; CHECK-LABEL: define void @v1x8_levels_6_7_8_9_10_11_12_13(
+; CHECK-SAME: i32 [[ARG0:%.*]], ptr align 16 [[ARG1:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[LEVEL1:%.*]] = getelementptr i8, ptr [[ARG1]], i32 917504
+; CHECK-NEXT:    [[LEVEL2:%.*]] = getelementptr i8, ptr [[LEVEL1]], i32 [[ARG0]]
+; CHECK-NEXT:    [[LEVEL3:%.*]] = getelementptr i8, ptr [[LEVEL2]], i32 32768
+; CHECK-NEXT:    [[LEVEL4:%.*]] = getelementptr i8, ptr [[LEVEL3]], i32 [[ARG0]]
+; CHECK-NEXT:    [[LEVEL5:%.*]] = getelementptr i8, ptr [[LEVEL4]], i32 [[ARG0]]
+; CHECK-NEXT:    [[A6:%.*]] = getelementptr i8, ptr [[LEVEL5]], i32 [[ARG0]]
+; CHECK-NEXT:    store <8 x half> zeroinitializer, ptr [[A6]], align 16
+; CHECK-NEXT:    ret void
+;
+
+  %level1 = getelementptr i8, ptr %arg1, i32 917504
+  %level2 = getelementptr i8, ptr %level1, i32 %arg0
+  %level3 = getelementptr i8, ptr %level2, i32 32768
+  %level4 = getelementptr i8, ptr %level3, i32 %arg0
+  %level5 = getelementptr i8, ptr %level4, i32 %arg0
+
+  %a6 = getelementptr i8, ptr %level5, i32 %arg0
+  %b7 = getelementptr i8, ptr %a6, i32 2
+  %c8 = getelementptr i8, ptr %b7, i32 2
+  %d9 = getelementptr i8, ptr %c8, i32 2
+  %e10 = getelementptr i8, ptr %d9, i32 2
+  %f11 = getelementptr i8, ptr %e10, i32 2
+  %g12 = getelementptr i8, ptr %f11, i32 2
+  %h13 = getelementptr i8, ptr %g12, i32 2
+
+  store half 0xH0000, ptr %a6, align 16
+  store half 0xH0000, ptr %b7, align 2
+  store half 0xH0000, ptr %c8, align 2
+  store half 0xH0000, ptr %d9, align 2
+  store half 0xH0000, ptr %e10, align 8
+  store half 0xH0000, ptr %f11, align 2
+  store half 0xH0000, ptr %g12, align 2
+  store half 0xH0000, ptr %h13, align 2
+  ret void
+}
+
+define void @v1_4_4_4_2_1_to_v8_8_levels_6_7(i32 %arg0, ptr addrspace(3) align 16 %arg1_ptr, i32 %arg2, i32 %arg3, i32 %arg4, i32 %arg5, half %arg6_half, half %arg7_half, <2 x half> %arg8_2xhalf) {
+; CHECK-LABEL: define void @v1_4_4_4_2_1_to_v8_8_levels_6_7(
+; CHECK-SAME: i32 [[ARG0:%.*]], ptr addrspace(3) align 16 [[ARG1_PTR:%.*]], i32 [[ARG2:%.*]], i32 [[ARG3:%.*]], i32 [[ARG4:%.*]], i32 [[ARG5:%.*]], half [[ARG6_HALF:%.*]], half [[ARG7_HALF:%.*]], <2 x half> [[ARG8_2XHALF:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[ARG1_PTR]], i32 458752
+; CHECK-NEXT:    br [[DOTPREHEADER11_PREHEADER:label %.*]]
+; CHECK:       [[_PREHEADER11_PREHEADER:.*:]]
+; CHECK-NEXT:    [[TMP2:%.*]] = shl nuw nsw i32 [[ARG0]], 6
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP1]], i32 [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP3]], i32 [[ARG2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[ARG3]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[ARG0]], 2
+; CHECK-NEXT:    br i1 [[CMP]], [[DOTLR_PH:label %.*]], [[DOTEXIT_POINT:label %.*]]
+; CHECK:       [[_LR_PH:.*:]]
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP5]], i32 [[ARG4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[GEP]], i32 [[ARG5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x half> poison, half [[ARG6_HALF]], i32 0
+; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <8 x half> [[TMP7]], half 0xH0000, i32 1
+; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <8 x half> [[TMP8]], half 0xH0000, i32 2
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <8 x half> [[TMP9]], half 0xH0000, i32 3
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <8 x half> [[TMP10]], half 0xH0000, i32 4
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x half> [[ARG8_2XHALF]], i32 0
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <8 x half> [[TMP11]], half [[TMP12]], i32 5
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x half> [[ARG8_2XHALF]], i32 1
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <8 x half> [[TMP13]], half [[TMP14]], i32 6
+; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <8 x half> [[TMP15]], half [[ARG7_HALF]], i32 7
+; CHECK-NEXT:    store <8 x half> [[TMP16]], ptr addrspace(3) [[TMP6]], align 2
+; CHECK-NEXT:    br [[DOTEXIT_POINT]]
+; CHECK:       [[_EXIT_POINT:.*:]]
+; CHECK-NEXT:    ret void
+;
+  %base1 = getelementptr inbounds i8, ptr addrspace(3) %arg1_ptr, i32 458752
+  br label %.preheader11.preheader
+
+.preheader11.preheader:
+  %base2 = shl nuw nsw i32 %arg0, 6
+  %base3 = getelementptr inbounds i8, ptr addrspace(3) %base1, i32 %base2
+
+  %base4 = getelementptr inbounds i8, ptr addrspace(3) %base3, i32 %arg2
+  %base5 = getelementptr inbounds i8, ptr addrspace(3) %base4, i32 %arg3
+
+  %cmp = icmp sgt i32 %arg0, 2
+  br i1 %cmp, label %.lr.ph, label %.exit_point
+
+.lr.ph:
+  %gep = getelementptr inbounds i8, ptr addrspace(3) %base5, i32 %arg4
+
+  %dst = getelementptr inbounds i8, ptr addrspace(3) %gep, i32 %arg5
+  %dst_off2 = getelementptr inbounds i8, ptr addrspace(3) %dst, i32 2
+  %dst_off10 = getelementptr inbounds i8, ptr addrspace(3) %dst, i32 10
+  %dst_off14 = getelementptr inbounds i8, ptr addrspace(3) %dst, i32 14
+
+  store half %arg6_half, ptr addrspace(3) %dst, align 2
+  store <4 x half> zeroinitializer, ptr addrspace(3) %dst_off2, align 2
+  store <2 x half> %arg8_2xhalf, ptr addrspace(3) %dst_off10, align 2
+  store half %arg7_half, ptr addrspace(3) %dst_off14, align 2
+  br label %.exit_point
+
+.exit_point:
+  ret void
+}
+
+; The regression test for merging equivalence classes. It is reduced and adapted
+; for LSV from llvm/test/CodeGen/NVPTX/variadics-backend.ll, which failed at
+; post-commit checks with memory sanitizer on the initial attempt to implement
+; the merging of the equivalence classes.
+define void @variadics1(ptr %vlist) {
+; CHECK-LABEL: define void @variadics1(
+; CHECK-SAME: ptr [[VLIST:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[ARGP_CUR7_ALIGNED2:%.*]] = call ptr @llvm.ptrmask.p0.i64(ptr [[VLIST]], i64 0)
+; CHECK-NEXT:    [[ARGP_NEXT8:%.*]] = getelementptr i8, ptr [[ARGP_CUR7_ALIGNED2]], i64 8
+; CHECK-NEXT:    [[X0:%.*]] = getelementptr i8, ptr [[ARGP_NEXT8]], i32 7
+; CHECK-NEXT:    [[ARGP_CUR11_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i64(ptr [[X0]], i64 0)
+; CHECK-NEXT:    [[ARGP_NEXT12:%.*]] = getelementptr i8, ptr [[ARGP_CUR11_ALIGNED]], i64 8
+; CHECK-NEXT:    [[X2:%.*]] = getelementptr i8, ptr [[ARGP_NEXT12]], i32 7
+; CHECK-NEXT:    [[ARGP_CUR16_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i64(ptr [[X2]], i64 0)
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, ptr [[ARGP_CUR16_ALIGNED]], align 4294967296
+; CHECK-NEXT:    [[X31:%.*]] = extractelement <2 x double> [[TMP1]], i32 0
+; CHECK-NEXT:    [[X42:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
+; CHECK-NEXT:    [[X5:%.*]] = fadd double [[X42]], [[X31]]
+; CHECK-NEXT:    store double [[X5]], ptr null, align 8
+; CHECK-NEXT:    ret void
+;
+  %argp.cur7.aligned2 = call ptr @llvm.ptrmask.p0.i64(ptr %vlist, i64 0)
+  %argp.next8 = getelementptr i8, ptr %argp.cur7.aligned2, i64 8
+  %x0 = getelementptr i8, ptr %argp.next8, i32 7
+  %argp.cur11.aligned = call ptr @llvm.ptrmask.p0.i64(ptr %x0, i64 0)
+  %argp.next12 = getelementptr i8, ptr %argp.cur11.aligned, i64 8
+  %x2 = getelementptr i8, ptr %argp.next12, i32 7
+  %argp.cur16.aligned = call ptr @llvm.ptrmask.p0.i64(ptr %x2, i64 0)
+  %x3 = load double, ptr %argp.cur16.aligned, align 8
+  %argp.cur16.aligned_off8 = getelementptr i8, ptr %argp.cur16.aligned, i32 8
+  %x4 = load double, ptr %argp.cur16.aligned_off8, align 8
+  %x5 = fadd double %x4, %x3
+  store double %x5, ptr null, align 8
+  ret void
+}
+
+declare ptr @llvm.ptrmask.p0.i64(ptr, i64)