derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/Instrumentation/MemorySanitizer/AArch64/arm64-tbl.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

743 lines
62 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; Test memory sanitizer instrumentation for Arm NEON tbl instructions.
;
; RUN: opt < %s -passes=msan -S | FileCheck %s
;
; Forked from llvm/test/CodeGen/AArch64/arm64-tbl.ll
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-android9001"
; -----------------------------------------------------------------------------------------------------------------------------------------------
define <8 x i8> @tbl1_8b(<16 x i8> %A, <8 x i8> %B) nounwind sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbl1_8b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <8 x i8> [[B:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP3:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl1.v8i8(<16 x i8> [[TMP1]], <8 x i8> [[B]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP2]], [[TMP3]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl1.v8i8(<16 x i8> [[A]], <8 x i8> [[B]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbl1.v8i8(<16 x i8> %A, <8 x i8> %B)
ret <8 x i8> %out
}
define <16 x i8> @tbl1_16b(<16 x i8> %A, <16 x i8> %B) nounwind sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbl1_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl1.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[B]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP2]], [[TMP3]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl1.v16i8(<16 x i8> [[A]], <16 x i8> [[B]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbl1.v16i8(<16 x i8> %A, <16 x i8> %B)
ret <16 x i8> %out
}
define <8 x i8> @tbl2_8b(<16 x i8> %A, <16 x i8> %B, <8 x i8> %C) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbl2_8b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <8 x i8> [[C:%.*]]) #[[ATTR1:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <8 x i8> [[C]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[A]], <16 x i8> [[B]], <8 x i8> [[C]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> %A, <16 x i8> %B, <8 x i8> %C)
ret <8 x i8> %out
}
define <16 x i8> @tbl2_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbl2_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[C]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C)
ret <16 x i8> %out
}
define <8 x i8> @tbl3_8b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <8 x i8> %D) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbl3_8b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <8 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl3.v8i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <8 x i8> [[D]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl3.v8i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <8 x i8> [[D]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbl3.v8i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <8 x i8> %D)
ret <8 x i8> %out
}
define <16 x i8> @tbl3_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbl3_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl3.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[D]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl3.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbl3.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D)
ret <16 x i8> %out
}
define <8 x i8> @tbl4_8b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <8 x i8> %E) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbl4_8b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <8 x i8> [[E:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl4.v8i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <8 x i8> [[E]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl4.v8i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <8 x i8> [[E]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbl4.v8i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <8 x i8> %E)
ret <8 x i8> %out
}
define <16 x i8> @tbl4_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbl4_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <16 x i8> [[E:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl4.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> [[E]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl4.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> [[E]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbl4.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E)
ret <16 x i8> %out
}
define <8 x i8> @shuffled_tbl2_to_tbl4_v8i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @shuffled_tbl2_to_tbl4_v8i8
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> zeroinitializer, [[TMP5]]
; CHECK-NEXT: [[T1:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[A]], <16 x i8> [[B]], <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP1:%.*]] = or <8 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T2:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> [[C]], <16 x i8> [[D]], <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP2:%.*]] = shufflevector <8 x i8> [[_MSPROP]], <8 x i8> [[_MSPROP1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[S:%.*]] = shufflevector <8 x i8> [[T1]], <8 x i8> [[T2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: store <8 x i8> [[_MSPROP2]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[S]]
;
%t1 = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> %a, <16 x i8> %b, <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8> %c, <16 x i8> %d, <8 x i8> <i8 0, i8 4, i8 8, i8 12, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <8 x i8> %t1, <8 x i8> %t2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
ret <8 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> zeroinitializer, [[TMP5]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP2:%.*]] = shufflevector <16 x i8> [[_MSPROP]], <16 x i8> [[_MSPROP1]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP2]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_first_mask(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d, i8 %v) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_first_mask
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], i8 [[V:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[_MSPROP:%.*]] = insertelement <16 x i8> splat (i8 -1), i8 [[TMP1]], i32 0
; CHECK-NEXT: [[INS_0:%.*]] = insertelement <16 x i8> poison, i8 [[V]], i32 0
; CHECK-NEXT: [[_MSPROP1:%.*]] = insertelement <16 x i8> [[_MSPROP]], i8 [[TMP1]], i32 1
; CHECK-NEXT: [[INS_1:%.*]] = insertelement <16 x i8> [[INS_0]], i8 [[V]], i32 1
; CHECK-NEXT: [[_MSPROP2:%.*]] = insertelement <16 x i8> [[_MSPROP1]], i8 [[TMP1]], i32 2
; CHECK-NEXT: [[INS_2:%.*]] = insertelement <16 x i8> [[INS_1]], i8 [[V]], i32 2
; CHECK-NEXT: [[_MSPROP3:%.*]] = insertelement <16 x i8> [[_MSPROP2]], i8 [[TMP1]], i32 3
; CHECK-NEXT: [[INS_3:%.*]] = insertelement <16 x i8> [[INS_2]], i8 [[V]], i32 3
; CHECK-NEXT: [[_MSPROP4:%.*]] = insertelement <16 x i8> [[_MSPROP3]], i8 [[TMP1]], i32 4
; CHECK-NEXT: [[INS_4:%.*]] = insertelement <16 x i8> [[INS_3]], i8 [[V]], i32 4
; CHECK-NEXT: [[_MSPROP5:%.*]] = insertelement <16 x i8> [[_MSPROP4]], i8 [[TMP1]], i32 5
; CHECK-NEXT: [[INS_5:%.*]] = insertelement <16 x i8> [[INS_4]], i8 [[V]], i32 5
; CHECK-NEXT: [[_MSPROP6:%.*]] = insertelement <16 x i8> [[_MSPROP5]], i8 [[TMP1]], i32 6
; CHECK-NEXT: [[INS_6:%.*]] = insertelement <16 x i8> [[INS_5]], i8 [[V]], i32 6
; CHECK-NEXT: [[_MSPROP7:%.*]] = insertelement <16 x i8> [[_MSPROP6]], i8 [[TMP1]], i32 7
; CHECK-NEXT: [[INS_7:%.*]] = insertelement <16 x i8> [[INS_6]], i8 [[V]], i32 7
; CHECK-NEXT: [[_MSPROP8:%.*]] = insertelement <16 x i8> [[_MSPROP7]], i8 0, i32 8
; CHECK-NEXT: [[INS_8:%.*]] = insertelement <16 x i8> [[INS_7]], i8 -1, i32 8
; CHECK-NEXT: [[_MSPROP9:%.*]] = insertelement <16 x i8> [[_MSPROP8]], i8 0, i32 9
; CHECK-NEXT: [[INS_9:%.*]] = insertelement <16 x i8> [[INS_8]], i8 -1, i32 9
; CHECK-NEXT: [[_MSPROP10:%.*]] = insertelement <16 x i8> [[_MSPROP9]], i8 0, i32 10
; CHECK-NEXT: [[INS_10:%.*]] = insertelement <16 x i8> [[INS_9]], i8 -1, i32 10
; CHECK-NEXT: [[_MSPROP11:%.*]] = insertelement <16 x i8> [[_MSPROP10]], i8 0, i32 11
; CHECK-NEXT: [[INS_11:%.*]] = insertelement <16 x i8> [[INS_10]], i8 -1, i32 11
; CHECK-NEXT: [[_MSPROP12:%.*]] = insertelement <16 x i8> [[_MSPROP11]], i8 0, i32 12
; CHECK-NEXT: [[INS_12:%.*]] = insertelement <16 x i8> [[INS_11]], i8 -1, i32 12
; CHECK-NEXT: [[_MSPROP13:%.*]] = insertelement <16 x i8> [[_MSPROP12]], i8 0, i32 13
; CHECK-NEXT: [[INS_13:%.*]] = insertelement <16 x i8> [[INS_12]], i8 -1, i32 13
; CHECK-NEXT: [[_MSPROP14:%.*]] = insertelement <16 x i8> [[_MSPROP13]], i8 0, i32 14
; CHECK-NEXT: [[INS_14:%.*]] = insertelement <16 x i8> [[INS_13]], i8 -1, i32 14
; CHECK-NEXT: [[_MSPROP15:%.*]] = insertelement <16 x i8> [[_MSPROP14]], i8 0, i32 15
; CHECK-NEXT: [[INS_15:%.*]] = insertelement <16 x i8> [[INS_14]], i8 -1, i32 15
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP16:%.*]] = or <16 x i8> [[_MSPROP15]], [[TMP6]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP17:%.*]] = or <16 x i8> zeroinitializer, [[TMP7]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP18:%.*]] = shufflevector <16 x i8> [[_MSPROP16]], <16 x i8> [[_MSPROP17]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP18]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%ins.0 = insertelement <16 x i8> poison, i8 %v, i32 0
%ins.1 = insertelement <16 x i8> %ins.0, i8 %v, i32 1
%ins.2 = insertelement <16 x i8> %ins.1, i8 %v, i32 2
%ins.3 = insertelement <16 x i8> %ins.2, i8 %v, i32 3
%ins.4 = insertelement <16 x i8> %ins.3, i8 %v, i32 4
%ins.5 = insertelement <16 x i8> %ins.4, i8 %v, i32 5
%ins.6 = insertelement <16 x i8> %ins.5, i8 %v, i32 6
%ins.7 = insertelement <16 x i8> %ins.6, i8 %v, i32 7
%ins.8 = insertelement <16 x i8> %ins.7, i8 -1, i32 8
%ins.9 = insertelement <16 x i8> %ins.8, i8 -1, i32 9
%ins.10 = insertelement <16 x i8> %ins.9, i8 -1, i32 10
%ins.11 = insertelement <16 x i8> %ins.10, i8 -1, i32 11
%ins.12 = insertelement <16 x i8> %ins.11, i8 -1, i32 12
%ins.13 = insertelement <16 x i8> %ins.12, i8 -1, i32 13
%ins.14 = insertelement <16 x i8> %ins.13, i8 -1, i32 14
%ins.15 = insertelement <16 x i8> %ins.14, i8 -1, i32 15
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %ins.15)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_first_mask2(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d, i8 %v) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_first_mask2
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], i8 [[V:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[INS_0:%.*]] = insertelement <16 x i8> poison, i8 1, i32 0
; CHECK-NEXT: [[INS_1:%.*]] = insertelement <16 x i8> [[INS_0]], i8 1, i32 1
; CHECK-NEXT: [[INS_2:%.*]] = insertelement <16 x i8> [[INS_1]], i8 1, i32 2
; CHECK-NEXT: [[INS_3:%.*]] = insertelement <16 x i8> [[INS_2]], i8 1, i32 3
; CHECK-NEXT: [[INS_4:%.*]] = insertelement <16 x i8> [[INS_3]], i8 1, i32 4
; CHECK-NEXT: [[INS_5:%.*]] = insertelement <16 x i8> [[INS_4]], i8 1, i32 5
; CHECK-NEXT: [[INS_6:%.*]] = insertelement <16 x i8> [[INS_5]], i8 1, i32 6
; CHECK-NEXT: [[INS_7:%.*]] = insertelement <16 x i8> [[INS_6]], i8 1, i32 7
; CHECK-NEXT: [[INS_8:%.*]] = insertelement <16 x i8> [[INS_7]], i8 -1, i32 8
; CHECK-NEXT: [[INS_9:%.*]] = insertelement <16 x i8> [[INS_8]], i8 -1, i32 9
; CHECK-NEXT: [[INS_10:%.*]] = insertelement <16 x i8> [[INS_9]], i8 -1, i32 10
; CHECK-NEXT: [[INS_11:%.*]] = insertelement <16 x i8> [[INS_10]], i8 -1, i32 11
; CHECK-NEXT: [[_MSPROP:%.*]] = insertelement <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 -1, i8 -1, i8 -1, i8 -1>, i8 [[TMP1]], i32 12
; CHECK-NEXT: [[INS_12:%.*]] = insertelement <16 x i8> [[INS_11]], i8 [[V]], i32 12
; CHECK-NEXT: [[_MSPROP1:%.*]] = insertelement <16 x i8> [[_MSPROP]], i8 [[TMP1]], i32 13
; CHECK-NEXT: [[INS_13:%.*]] = insertelement <16 x i8> [[INS_12]], i8 [[V]], i32 13
; CHECK-NEXT: [[_MSPROP2:%.*]] = insertelement <16 x i8> [[_MSPROP1]], i8 0, i32 14
; CHECK-NEXT: [[INS_14:%.*]] = insertelement <16 x i8> [[INS_13]], i8 -1, i32 14
; CHECK-NEXT: [[_MSPROP3:%.*]] = insertelement <16 x i8> [[_MSPROP2]], i8 [[TMP1]], i32 15
; CHECK-NEXT: [[INS_15:%.*]] = insertelement <16 x i8> [[INS_14]], i8 [[V]], i32 15
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP4:%.*]] = or <16 x i8> [[_MSPROP3]], [[TMP6]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP5:%.*]] = or <16 x i8> zeroinitializer, [[TMP7]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP6:%.*]] = shufflevector <16 x i8> [[_MSPROP4]], <16 x i8> [[_MSPROP5]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 31>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 31>
; CHECK-NEXT: store <16 x i8> [[_MSPROP6]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%ins.0 = insertelement <16 x i8> poison, i8 1, i32 0
%ins.1 = insertelement <16 x i8> %ins.0, i8 1, i32 1
%ins.2 = insertelement <16 x i8> %ins.1, i8 1, i32 2
%ins.3 = insertelement <16 x i8> %ins.2, i8 1, i32 3
%ins.4 = insertelement <16 x i8> %ins.3, i8 1, i32 4
%ins.5 = insertelement <16 x i8> %ins.4, i8 1, i32 5
%ins.6 = insertelement <16 x i8> %ins.5, i8 1, i32 6
%ins.7 = insertelement <16 x i8> %ins.6, i8 1, i32 7
%ins.8 = insertelement <16 x i8> %ins.7, i8 -1, i32 8
%ins.9 = insertelement <16 x i8> %ins.8, i8 -1, i32 9
%ins.10 = insertelement <16 x i8> %ins.9, i8 -1, i32 10
%ins.11 = insertelement <16 x i8> %ins.10, i8 -1, i32 11
%ins.12 = insertelement <16 x i8> %ins.11, i8 %v, i32 12
%ins.13 = insertelement <16 x i8> %ins.12, i8 %v, i32 13
%ins.14 = insertelement <16 x i8> %ins.13, i8 -1, i32 14
%ins.15 = insertelement <16 x i8> %ins.14, i8 %v, i32 15
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %ins.15)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 31>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_second_mask(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d, i8 %v) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_second_mask
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], i8 [[V:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[_MSPROP:%.*]] = insertelement <16 x i8> splat (i8 -1), i8 [[TMP1]], i32 0
; CHECK-NEXT: [[INS_0:%.*]] = insertelement <16 x i8> poison, i8 [[V]], i32 0
; CHECK-NEXT: [[_MSPROP1:%.*]] = insertelement <16 x i8> [[_MSPROP]], i8 [[TMP1]], i32 1
; CHECK-NEXT: [[INS_1:%.*]] = insertelement <16 x i8> [[INS_0]], i8 [[V]], i32 1
; CHECK-NEXT: [[_MSPROP2:%.*]] = insertelement <16 x i8> [[_MSPROP1]], i8 [[TMP1]], i32 2
; CHECK-NEXT: [[INS_2:%.*]] = insertelement <16 x i8> [[INS_1]], i8 [[V]], i32 2
; CHECK-NEXT: [[_MSPROP3:%.*]] = insertelement <16 x i8> [[_MSPROP2]], i8 [[TMP1]], i32 3
; CHECK-NEXT: [[INS_3:%.*]] = insertelement <16 x i8> [[INS_2]], i8 [[V]], i32 3
; CHECK-NEXT: [[_MSPROP4:%.*]] = insertelement <16 x i8> [[_MSPROP3]], i8 [[TMP1]], i32 4
; CHECK-NEXT: [[INS_4:%.*]] = insertelement <16 x i8> [[INS_3]], i8 [[V]], i32 4
; CHECK-NEXT: [[_MSPROP5:%.*]] = insertelement <16 x i8> [[_MSPROP4]], i8 [[TMP1]], i32 5
; CHECK-NEXT: [[INS_5:%.*]] = insertelement <16 x i8> [[INS_4]], i8 [[V]], i32 5
; CHECK-NEXT: [[_MSPROP6:%.*]] = insertelement <16 x i8> [[_MSPROP5]], i8 [[TMP1]], i32 6
; CHECK-NEXT: [[INS_6:%.*]] = insertelement <16 x i8> [[INS_5]], i8 [[V]], i32 6
; CHECK-NEXT: [[_MSPROP7:%.*]] = insertelement <16 x i8> [[_MSPROP6]], i8 [[TMP1]], i32 7
; CHECK-NEXT: [[INS_7:%.*]] = insertelement <16 x i8> [[INS_6]], i8 [[V]], i32 7
; CHECK-NEXT: [[_MSPROP8:%.*]] = insertelement <16 x i8> [[_MSPROP7]], i8 0, i32 8
; CHECK-NEXT: [[INS_8:%.*]] = insertelement <16 x i8> [[INS_7]], i8 -1, i32 8
; CHECK-NEXT: [[_MSPROP9:%.*]] = insertelement <16 x i8> [[_MSPROP8]], i8 0, i32 9
; CHECK-NEXT: [[INS_9:%.*]] = insertelement <16 x i8> [[INS_8]], i8 -1, i32 9
; CHECK-NEXT: [[_MSPROP10:%.*]] = insertelement <16 x i8> [[_MSPROP9]], i8 0, i32 10
; CHECK-NEXT: [[INS_10:%.*]] = insertelement <16 x i8> [[INS_9]], i8 -1, i32 10
; CHECK-NEXT: [[_MSPROP11:%.*]] = insertelement <16 x i8> [[_MSPROP10]], i8 0, i32 11
; CHECK-NEXT: [[INS_11:%.*]] = insertelement <16 x i8> [[INS_10]], i8 -1, i32 11
; CHECK-NEXT: [[_MSPROP12:%.*]] = insertelement <16 x i8> [[_MSPROP11]], i8 0, i32 12
; CHECK-NEXT: [[INS_12:%.*]] = insertelement <16 x i8> [[INS_11]], i8 -1, i32 12
; CHECK-NEXT: [[_MSPROP13:%.*]] = insertelement <16 x i8> [[_MSPROP12]], i8 0, i32 13
; CHECK-NEXT: [[INS_13:%.*]] = insertelement <16 x i8> [[INS_12]], i8 -1, i32 13
; CHECK-NEXT: [[_MSPROP14:%.*]] = insertelement <16 x i8> [[_MSPROP13]], i8 0, i32 14
; CHECK-NEXT: [[INS_14:%.*]] = insertelement <16 x i8> [[INS_13]], i8 -1, i32 14
; CHECK-NEXT: [[_MSPROP15:%.*]] = insertelement <16 x i8> [[_MSPROP14]], i8 0, i32 15
; CHECK-NEXT: [[INS_15:%.*]] = insertelement <16 x i8> [[INS_14]], i8 -1, i32 15
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP16:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP17:%.*]] = or <16 x i8> [[_MSPROP15]], [[TMP7]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP18:%.*]] = shufflevector <16 x i8> [[_MSPROP16]], <16 x i8> [[_MSPROP17]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP18]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%ins.0 = insertelement <16 x i8> poison, i8 %v, i32 0
%ins.1 = insertelement <16 x i8> %ins.0, i8 %v, i32 1
%ins.2 = insertelement <16 x i8> %ins.1, i8 %v, i32 2
%ins.3 = insertelement <16 x i8> %ins.2, i8 %v, i32 3
%ins.4 = insertelement <16 x i8> %ins.3, i8 %v, i32 4
%ins.5 = insertelement <16 x i8> %ins.4, i8 %v, i32 5
%ins.6 = insertelement <16 x i8> %ins.5, i8 %v, i32 6
%ins.7 = insertelement <16 x i8> %ins.6, i8 %v, i32 7
%ins.8 = insertelement <16 x i8> %ins.7, i8 -1, i32 8
%ins.9 = insertelement <16 x i8> %ins.8, i8 -1, i32 9
%ins.10 = insertelement <16 x i8> %ins.9, i8 -1, i32 10
%ins.11 = insertelement <16 x i8> %ins.10, i8 -1, i32 11
%ins.12 = insertelement <16 x i8> %ins.11, i8 -1, i32 12
%ins.13 = insertelement <16 x i8> %ins.12, i8 -1, i32 13
%ins.14 = insertelement <16 x i8> %ins.13, i8 -1, i32 14
%ins.15 = insertelement <16 x i8> %ins.14, i8 -1, i32 15
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %ins.15)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_second_mask2(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d, i8 %v) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_nonconst_second_mask2
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], i8 [[V:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[_MSPROP:%.*]] = insertelement <16 x i8> splat (i8 -1), i8 [[TMP1]], i32 0
; CHECK-NEXT: [[INS_0:%.*]] = insertelement <16 x i8> poison, i8 [[V]], i32 0
; CHECK-NEXT: [[_MSPROP1:%.*]] = insertelement <16 x i8> [[_MSPROP]], i8 [[TMP1]], i32 1
; CHECK-NEXT: [[INS_1:%.*]] = insertelement <16 x i8> [[INS_0]], i8 [[V]], i32 1
; CHECK-NEXT: [[_MSPROP2:%.*]] = insertelement <16 x i8> [[_MSPROP1]], i8 [[TMP1]], i32 2
; CHECK-NEXT: [[INS_2:%.*]] = insertelement <16 x i8> [[INS_1]], i8 [[V]], i32 2
; CHECK-NEXT: [[_MSPROP3:%.*]] = insertelement <16 x i8> [[_MSPROP2]], i8 [[TMP1]], i32 3
; CHECK-NEXT: [[INS_3:%.*]] = insertelement <16 x i8> [[INS_2]], i8 [[V]], i32 3
; CHECK-NEXT: [[_MSPROP4:%.*]] = insertelement <16 x i8> [[_MSPROP3]], i8 [[TMP1]], i32 4
; CHECK-NEXT: [[INS_4:%.*]] = insertelement <16 x i8> [[INS_3]], i8 [[V]], i32 4
; CHECK-NEXT: [[_MSPROP5:%.*]] = insertelement <16 x i8> [[_MSPROP4]], i8 [[TMP1]], i32 5
; CHECK-NEXT: [[INS_5:%.*]] = insertelement <16 x i8> [[INS_4]], i8 [[V]], i32 5
; CHECK-NEXT: [[_MSPROP6:%.*]] = insertelement <16 x i8> [[_MSPROP5]], i8 [[TMP1]], i32 6
; CHECK-NEXT: [[INS_6:%.*]] = insertelement <16 x i8> [[INS_5]], i8 [[V]], i32 6
; CHECK-NEXT: [[_MSPROP7:%.*]] = insertelement <16 x i8> [[_MSPROP6]], i8 [[TMP1]], i32 7
; CHECK-NEXT: [[INS_7:%.*]] = insertelement <16 x i8> [[INS_6]], i8 [[V]], i32 7
; CHECK-NEXT: [[_MSPROP8:%.*]] = insertelement <16 x i8> [[_MSPROP7]], i8 0, i32 8
; CHECK-NEXT: [[INS_8:%.*]] = insertelement <16 x i8> [[INS_7]], i8 -1, i32 8
; CHECK-NEXT: [[_MSPROP9:%.*]] = insertelement <16 x i8> [[_MSPROP8]], i8 0, i32 9
; CHECK-NEXT: [[INS_9:%.*]] = insertelement <16 x i8> [[INS_8]], i8 -1, i32 9
; CHECK-NEXT: [[_MSPROP10:%.*]] = insertelement <16 x i8> [[_MSPROP9]], i8 0, i32 10
; CHECK-NEXT: [[INS_10:%.*]] = insertelement <16 x i8> [[INS_9]], i8 -1, i32 10
; CHECK-NEXT: [[_MSPROP11:%.*]] = insertelement <16 x i8> [[_MSPROP10]], i8 0, i32 11
; CHECK-NEXT: [[INS_11:%.*]] = insertelement <16 x i8> [[INS_10]], i8 -1, i32 11
; CHECK-NEXT: [[_MSPROP12:%.*]] = insertelement <16 x i8> [[_MSPROP11]], i8 0, i32 12
; CHECK-NEXT: [[INS_12:%.*]] = insertelement <16 x i8> [[INS_11]], i8 -1, i32 12
; CHECK-NEXT: [[_MSPROP13:%.*]] = insertelement <16 x i8> [[_MSPROP12]], i8 0, i32 13
; CHECK-NEXT: [[INS_13:%.*]] = insertelement <16 x i8> [[INS_12]], i8 -1, i32 13
; CHECK-NEXT: [[_MSPROP14:%.*]] = insertelement <16 x i8> [[_MSPROP13]], i8 [[TMP1]], i32 14
; CHECK-NEXT: [[INS_14:%.*]] = insertelement <16 x i8> [[INS_13]], i8 [[V]], i32 14
; CHECK-NEXT: [[_MSPROP15:%.*]] = insertelement <16 x i8> [[_MSPROP14]], i8 [[TMP1]], i32 15
; CHECK-NEXT: [[INS_15:%.*]] = insertelement <16 x i8> [[INS_14]], i8 [[V]], i32 15
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP16:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP17:%.*]] = or <16 x i8> [[_MSPROP15]], [[TMP7]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[INS_15]])
; CHECK-NEXT: [[_MSPROP18:%.*]] = shufflevector <16 x i8> [[_MSPROP16]], <16 x i8> [[_MSPROP17]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 30, i32 31>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 30, i32 31>
; CHECK-NEXT: store <16 x i8> [[_MSPROP18]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%ins.0 = insertelement <16 x i8> poison, i8 %v, i32 0
%ins.1 = insertelement <16 x i8> %ins.0, i8 %v, i32 1
%ins.2 = insertelement <16 x i8> %ins.1, i8 %v, i32 2
%ins.3 = insertelement <16 x i8> %ins.2, i8 %v, i32 3
%ins.4 = insertelement <16 x i8> %ins.3, i8 %v, i32 4
%ins.5 = insertelement <16 x i8> %ins.4, i8 %v, i32 5
%ins.6 = insertelement <16 x i8> %ins.5, i8 %v, i32 6
%ins.7 = insertelement <16 x i8> %ins.6, i8 %v, i32 7
%ins.8 = insertelement <16 x i8> %ins.7, i8 -1, i32 8
%ins.9 = insertelement <16 x i8> %ins.8, i8 -1, i32 9
%ins.10 = insertelement <16 x i8> %ins.9, i8 -1, i32 10
%ins.11 = insertelement <16 x i8> %ins.10, i8 -1, i32 11
%ins.12 = insertelement <16 x i8> %ins.11, i8 -1, i32 12
%ins.13 = insertelement <16 x i8> %ins.12, i8 -1, i32 13
%ins.14 = insertelement <16 x i8> %ins.13, i8 %v, i32 14
%ins.15 = insertelement <16 x i8> %ins.14, i8 %v, i32 15
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %ins.15)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 30, i32 31>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_shuffle(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_shuffle
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> zeroinitializer, [[TMP5]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP2:%.*]] = shufflevector <16 x i8> [[_MSPROP]], <16 x i8> [[_MSPROP1]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP2]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_tbl2_mask1(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_tbl2_mask1
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> zeroinitializer, [[TMP5]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP2:%.*]] = shufflevector <16 x i8> [[_MSPROP]], <16 x i8> [[_MSPROP1]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP2]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_tbl2_mask2(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @shuffled_tbl2_to_tbl4_mixed_tbl2_mask2
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> zeroinitializer, [[TMP5]]
; CHECK-NEXT: [[T1:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[T2:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
; CHECK-NEXT: [[_MSPROP2:%.*]] = shufflevector <16 x i8> [[_MSPROP]], <16 x i8> [[_MSPROP1]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: [[S:%.*]] = shufflevector <16 x i8> [[T1]], <16 x i8> [[T2]], <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; CHECK-NEXT: store <16 x i8> [[_MSPROP2]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[S]]
;
%t1 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%t2 = call <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8> %c, <16 x i8> %d, <16 x i8> <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 0, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>)
%s = shufflevector <16 x i8> %t1, <16 x i8> %t2, <16 x i32> <i32 0, i32 1, i32 21, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
ret <16 x i8> %s
}
declare <8 x i8> @llvm.aarch64.neon.tbl1.v8i8(<16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbl1.v16i8(<16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbl2.v8i8(<16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbl2.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbl3.v8i8(<16 x i8>, <16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbl3.v16i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbl4.v8i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbl4.v16i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
define <8 x i8> @tbx1_8b(<8 x i8> %A, <16 x i8> %B, <8 x i8> %C) nounwind sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbx1_8b
; CHECK-SAME: (<8 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <8 x i8> [[C:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 24), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx1.v8i8(<8 x i8> [[TMP1]], <16 x i8> [[TMP2]], <8 x i8> [[C]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx1.v8i8(<8 x i8> [[A]], <16 x i8> [[B]], <8 x i8> [[C]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbx1.v8i8(<8 x i8> %A, <16 x i8> %B, <8 x i8> %C)
ret <8 x i8> %out
}
define <16 x i8> @tbx1_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) nounwind sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbx1_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx1.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[C]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP3]], [[TMP4]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx1.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbx1.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C)
ret <16 x i8> %out
}
define <8 x i8> @tbx2_8b(<8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <8 x i8> %D) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbx2_8b
; CHECK-SAME: (<8 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <8 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 24), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 40), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx2.v8i8(<8 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <8 x i8> [[D]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx2.v8i8(<8 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <8 x i8> [[D]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbx2.v8i8(<8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <8 x i8> %D)
ret <8 x i8> %out
}
define <16 x i8> @tbx2_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbx2_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx2.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[D]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx2.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbx2.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D)
ret <16 x i8> %out
}
define <8 x i8> @tbx3_8b(<8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <8 x i8> %E) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbx3_8b
; CHECK-SAME: (<8 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <8 x i8> [[E:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 24), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 40), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 56), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx3.v8i8(<8 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <8 x i8> [[E]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx3.v8i8(<8 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <8 x i8> [[E]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbx3.v8i8(< 8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <8 x i8> %E)
ret <8 x i8> %out
}
define <16 x i8> @tbx3_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbx3_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <16 x i8> [[E:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx3.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> [[E]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx3.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> [[E]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbx3.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E)
ret <16 x i8> %out
}
define <8 x i8> @tbx4_8b(<8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E, <8 x i8> %F) sanitize_memory {
; CHECK-LABEL: define <8 x i8> @tbx4_8b
; CHECK-SAME: (<8 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <16 x i8> [[E:%.*]], <8 x i8> [[F:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 24), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 40), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 56), align 8
; CHECK-NEXT: [[TMP6:%.*]] = load <8 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 72), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP7:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx4.v8i8(<8 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <8 x i8> [[F]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i8> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[OUT:%.*]] = call <8 x i8> @llvm.aarch64.neon.tbx4.v8i8(<8 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> [[E]], <8 x i8> [[F]])
; CHECK-NEXT: store <8 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i8> [[OUT]]
;
%out = call <8 x i8> @llvm.aarch64.neon.tbx4.v8i8(<8 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E, <8 x i8> %F)
ret <8 x i8> %out
}
define <16 x i8> @tbx4_16b(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E, <16 x i8> %F) sanitize_memory {
; CHECK-LABEL: define <16 x i8> @tbx4_16b
; CHECK-SAME: (<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i8> [[D:%.*]], <16 x i8> [[E:%.*]], <16 x i8> [[F:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 16), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 32), align 8
; CHECK-NEXT: [[TMP4:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 48), align 8
; CHECK-NEXT: [[TMP5:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 64), align 8
; CHECK-NEXT: [[TMP6:%.*]] = load <16 x i8>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 80), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx4.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i8> [[TMP5]], <16 x i8> [[F]])
; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[OUT:%.*]] = call <16 x i8> @llvm.aarch64.neon.tbx4.v16i8(<16 x i8> [[A]], <16 x i8> [[B]], <16 x i8> [[C]], <16 x i8> [[D]], <16 x i8> [[E]], <16 x i8> [[F]])
; CHECK-NEXT: store <16 x i8> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[OUT]]
;
%out = call <16 x i8> @llvm.aarch64.neon.tbx4.v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C, <16 x i8> %D, <16 x i8> %E, <16 x i8> %F)
ret <16 x i8> %out
}
declare <8 x i8> @llvm.aarch64.neon.tbx1.v8i8(<8 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbx1.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbx2.v8i8(<8 x i8>, <16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbx2.v16i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbx3.v8i8(<8 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbx3.v16i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
declare <8 x i8> @llvm.aarch64.neon.tbx4.v8i8(<8 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <8 x i8>) nounwind sanitize_memory readnone
declare <16 x i8> @llvm.aarch64.neon.tbx4.v16i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind sanitize_memory readnone
Reference in new issue View Git Blame Copy Permalink