maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64] Regenerate arm64-neon-simd-ldst-one.ll test checks

This commit is contained in:
Simon Pilgrim 2022-07-16 15:26:51 +01:00
parent f7a9c5c61b
commit 2d4c43d45f
1 changed files with 203 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

270
llvm/test/CodeGen/AArch64/arm64-neon-simd-ldst-one.ll
View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mtriple=arm64-none-linux-gnu -mattr=+neon | FileCheck %s
@ -43,8 +44,11 @@
define <16 x i8> @test_ld_from_poll_v16i8(<16 x i8> %a) {
; CHECK-LABEL: test_ld_from_poll_v16i8:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI0_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
; CHECK-NEXT: add v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%b = add <16 x i8> %a, <i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 2, i8 13, i8 14, i8 15, i8 16>
ret <16 x i8> %b
@ -52,8 +56,11 @@ entry:
define <8 x i16> @test_ld_from_poll_v8i16(<8 x i16> %a) {
; CHECK-LABEL: test_ld_from_poll_v8i16:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI1_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
; CHECK-NEXT: add v0.8h, v0.8h, v1.8h
; CHECK-NEXT: ret
entry:
%b = add <8 x i16> %a, <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>
ret <8 x i16> %b
@ -61,8 +68,11 @@ entry:
define <4 x i32> @test_ld_from_poll_v4i32(<4 x i32> %a) {
; CHECK-LABEL: test_ld_from_poll_v4i32:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI2_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
; CHECK-NEXT: add v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%b = add <4 x i32> %a, <i32 1, i32 2, i32 3, i32 4>
ret <4 x i32> %b
@ -70,8 +80,11 @@ entry:
define <2 x i64> @test_ld_from_poll_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test_ld_from_poll_v2i64:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI3_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI3_0]
; CHECK-NEXT: add v0.2d, v0.2d, v1.2d
; CHECK-NEXT: ret
entry:
%b = add <2 x i64> %a, <i64 1, i64 2>
ret <2 x i64> %b
@ -79,8 +92,11 @@ entry:
define <4 x float> @test_ld_from_poll_v4f32(<4 x float> %a) {
; CHECK-LABEL: test_ld_from_poll_v4f32:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI4_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI4_0]
; CHECK-NEXT: fadd v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%b = fadd <4 x float> %a, <float 1.0, float 2.0, float 3.0, float 4.0>
ret <4 x float> %b
@ -88,8 +104,11 @@ entry:
define <2 x double> @test_ld_from_poll_v2f64(<2 x double> %a) {
; CHECK-LABEL: test_ld_from_poll_v2f64:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI5_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI5_0]
; CHECK-NEXT: fadd v0.2d, v0.2d, v1.2d
; CHECK-NEXT: ret
entry:
%b = fadd <2 x double> %a, <double 1.0, double 2.0>
ret <2 x double> %b
@ -97,8 +116,11 @@ entry:
define <8 x i8> @test_ld_from_poll_v8i8(<8 x i8> %a) {
; CHECK-LABEL: test_ld_from_poll_v8i8:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{d[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI6_0
; CHECK-NEXT: ldr d1, [x8, :lo12:.LCPI6_0]
; CHECK-NEXT: add v0.8b, v0.8b, v1.8b
; CHECK-NEXT: ret
entry:
%b = add <8 x i8> %a, <i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8>
ret <8 x i8> %b
@ -106,8 +128,11 @@ entry:
define <4 x i16> @test_ld_from_poll_v4i16(<4 x i16> %a) {
; CHECK-LABEL: test_ld_from_poll_v4i16:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{d[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI7_0
; CHECK-NEXT: ldr d1, [x8, :lo12:.LCPI7_0]
; CHECK-NEXT: add v0.4h, v0.4h, v1.4h
; CHECK-NEXT: ret
entry:
%b = add <4 x i16> %a, <i16 1, i16 2, i16 3, i16 4>
ret <4 x i16> %b
@ -115,8 +140,11 @@ entry:
define <2 x i32> @test_ld_from_poll_v2i32(<2 x i32> %a) {
; CHECK-LABEL: test_ld_from_poll_v2i32:
; CHECK: adrp {{x[0-9]+}}, .{{[A-Z0-9_]+}}
; CHECK: ldr {{d[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.{{[A-Z0-9_]+}}]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI8_0
; CHECK-NEXT: ldr d1, [x8, :lo12:.LCPI8_0]
; CHECK-NEXT: add v0.2s, v0.2s, v1.2s
; CHECK-NEXT: ret
entry:
%b = add <2 x i32> %a, <i32 1, i32 2>
ret <2 x i32> %b
@ -124,7 +152,9 @@ entry:
define <16 x i8> @test_vld1q_dup_s8(i8* %a) {
; CHECK-LABEL: test_vld1q_dup_s8:
; CHECK: ld1r {{{ ?v[0-9]+.16b ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.16b }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i8, i8* %a, align 1
%1 = insertelement <16 x i8> undef, i8 %0, i32 0
@ -134,7 +164,9 @@ entry:
define <8 x i16> @test_vld1q_dup_s16(i16* %a) {
; CHECK-LABEL: test_vld1q_dup_s16:
; CHECK: ld1r {{{ ?v[0-9]+.8h ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.8h }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i16, i16* %a, align 2
%1 = insertelement <8 x i16> undef, i16 %0, i32 0
@ -144,7 +176,9 @@ entry:
define <4 x i32> @test_vld1q_dup_s32(i32* %a) {
; CHECK-LABEL: test_vld1q_dup_s32:
; CHECK: ld1r {{{ ?v[0-9]+.4s ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.4s }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* %a, align 4
%1 = insertelement <4 x i32> undef, i32 %0, i32 0
@ -154,7 +188,9 @@ entry:
define <2 x i64> @test_vld1q_dup_s64(i64* %a) {
; CHECK-LABEL: test_vld1q_dup_s64:
; CHECK: ld1r {{{ ?v[0-9]+.2d ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.2d }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i64, i64* %a, align 8
%1 = insertelement <2 x i64> undef, i64 %0, i32 0
@ -164,7 +200,9 @@ entry:
define <4 x float> @test_vld1q_dup_f32(float* %a) {
; CHECK-LABEL: test_vld1q_dup_f32:
; CHECK: ld1r {{{ ?v[0-9]+.4s ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.4s }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load float, float* %a, align 4
%1 = insertelement <4 x float> undef, float %0, i32 0
@ -174,7 +212,9 @@ entry:
define <2 x double> @test_vld1q_dup_f64(double* %a) {
; CHECK-LABEL: test_vld1q_dup_f64:
; CHECK: ld1r {{{ ?v[0-9]+.2d ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.2d }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load double, double* %a, align 8
%1 = insertelement <2 x double> undef, double %0, i32 0
@ -184,7 +224,9 @@ entry:
define <8 x i8> @test_vld1_dup_s8(i8* %a) {
; CHECK-LABEL: test_vld1_dup_s8:
; CHECK: ld1r {{{ ?v[0-9]+.8b ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.8b }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i8, i8* %a, align 1
%1 = insertelement <8 x i8> undef, i8 %0, i32 0
@ -194,7 +236,9 @@ entry:
define <4 x i16> @test_vld1_dup_s16(i16* %a) {
; CHECK-LABEL: test_vld1_dup_s16:
; CHECK: ld1r {{{ ?v[0-9]+.4h ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.4h }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i16, i16* %a, align 2
%1 = insertelement <4 x i16> undef, i16 %0, i32 0
@ -204,7 +248,9 @@ entry:
define <2 x i32> @test_vld1_dup_s32(i32* %a) {
; CHECK-LABEL: test_vld1_dup_s32:
; CHECK: ld1r {{{ ?v[0-9]+.2s ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.2s }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* %a, align 4
%1 = insertelement <2 x i32> undef, i32 %0, i32 0
@ -214,7 +260,9 @@ entry:
define <1 x i64> @test_vld1_dup_s64(i64* %a) {
; CHECK-LABEL: test_vld1_dup_s64:
; CHECK: ldr {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ldr d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i64, i64* %a, align 8
%1 = insertelement <1 x i64> undef, i64 %0, i32 0
@ -223,7 +271,9 @@ entry:
define <2 x float> @test_vld1_dup_f32(float* %a) {
; CHECK-LABEL: test_vld1_dup_f32:
; CHECK: ld1r {{{ ?v[0-9]+.2s ?}}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1r { v0.2s }, [x0]
; CHECK-NEXT: ret
entry:
%0 = load float, float* %a, align 4
%1 = insertelement <2 x float> undef, float %0, i32 0
@ -233,7 +283,9 @@ entry:
define <1 x double> @test_vld1_dup_f64(double* %a) {
; CHECK-LABEL: test_vld1_dup_f64:
; CHECK: ldr {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ldr d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = load double, double* %a, align 8
%1 = insertelement <1 x double> undef, double %0, i32 0
@ -244,9 +296,11 @@ define <1 x i64> @testDUP.v1i64(i64* %a, i64* %b) #0 {
; As there is a store operation depending on %1, LD1R pattern can't be selected.
; So LDR and FMOV should be emitted.
; CHECK-LABEL: testDUP.v1i64:
; CHECK: ldr {{x[0-9]+}}, [{{x[0-9]+}}]
; CHECK-DAG: fmov {{d[0-9]+}}, {{x[0-9]+}}
; CHECK-DAG: str {{x[0-9]+}}, [{{x[0-9]+}}]
; CHECK: // %bb.0:
; CHECK-NEXT: ldr x8, [x0]
; CHECK-NEXT: fmov d0, x8
; CHECK-NEXT: str x8, [x1]
; CHECK-NEXT: ret
%1 = load i64, i64* %a, align 8
store i64 %1, i64* %b, align 8
%vecinit.i = insertelement <1 x i64> undef, i64 %1, i32 0
@ -257,8 +311,10 @@ define <1 x double> @testDUP.v1f64(double* %a, double* %b) #0 {
; As there is a store operation depending on %1, LD1R pattern can't be selected.
; So LDR and FMOV should be emitted.
; CHECK-LABEL: testDUP.v1f64:
; CHECK: ldr {{d[0-9]+}}, [{{x[0-9]+}}]
; CHECK: str {{d[0-9]+}}, [{{x[0-9]+}}]
; CHECK: // %bb.0:
; CHECK-NEXT: ldr d0, [x0]
; CHECK-NEXT: str d0, [x1]
; CHECK-NEXT: ret
%1 = load double, double* %a, align 8
store double %1, double* %b, align 8
%vecinit.i = insertelement <1 x double> undef, double %1, i32 0
@ -267,7 +323,9 @@ define <1 x double> @testDUP.v1f64(double* %a, double* %b) #0 {
define <16 x i8> @test_vld1q_lane_s8(i8* %a, <16 x i8> %b) {
; CHECK-LABEL: test_vld1q_lane_s8:
; CHECK: ld1 { {{v[0-9]+}}.b }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.b }[15], [x0]
; CHECK-NEXT: ret
entry:
%0 = load i8, i8* %a, align 1
%vld1_lane = insertelement <16 x i8> %b, i8 %0, i32 15
@ -276,7 +334,9 @@ entry:
define <8 x i16> @test_vld1q_lane_s16(i16* %a, <8 x i16> %b) {
; CHECK-LABEL: test_vld1q_lane_s16:
; CHECK: ld1 { {{v[0-9]+}}.h }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.h }[7], [x0]
; CHECK-NEXT: ret
entry:
%0 = load i16, i16* %a, align 2
%vld1_lane = insertelement <8 x i16> %b, i16 %0, i32 7
@ -285,7 +345,9 @@ entry:
define <4 x i32> @test_vld1q_lane_s32(i32* %a, <4 x i32> %b) {
; CHECK-LABEL: test_vld1q_lane_s32:
; CHECK: ld1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.s }[3], [x0]
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* %a, align 4
%vld1_lane = insertelement <4 x i32> %b, i32 %0, i32 3
@ -294,7 +356,9 @@ entry:
define <2 x i64> @test_vld1q_lane_s64(i64* %a, <2 x i64> %b) {
; CHECK-LABEL: test_vld1q_lane_s64:
; CHECK: ld1 { {{v[0-9]+}}.d }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.d }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = load i64, i64* %a, align 8
%vld1_lane = insertelement <2 x i64> %b, i64 %0, i32 1
@ -303,7 +367,9 @@ entry:
define <4 x float> @test_vld1q_lane_f32(float* %a, <4 x float> %b) {
; CHECK-LABEL: test_vld1q_lane_f32:
; CHECK: ld1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.s }[3], [x0]
; CHECK-NEXT: ret
entry:
%0 = load float, float* %a, align 4
%vld1_lane = insertelement <4 x float> %b, float %0, i32 3
@ -312,7 +378,9 @@ entry:
define <2 x double> @test_vld1q_lane_f64(double* %a, <2 x double> %b) {
; CHECK-LABEL: test_vld1q_lane_f64:
; CHECK: ld1 { {{v[0-9]+}}.d }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld1 { v0.d }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = load double, double* %a, align 8
%vld1_lane = insertelement <2 x double> %b, double %0, i32 1
@ -321,7 +389,11 @@ entry:
define <8 x i8> @test_vld1_lane_s8(i8* %a, <8 x i8> %b) {
; CHECK-LABEL: test_vld1_lane_s8:
; CHECK: ld1 { {{v[0-9]+}}.b }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: ld1 { v0.b }[7], [x0]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = load i8, i8* %a, align 1
%vld1_lane = insertelement <8 x i8> %b, i8 %0, i32 7
@ -330,7 +402,11 @@ entry:
define <4 x i16> @test_vld1_lane_s16(i16* %a, <4 x i16> %b) {
; CHECK-LABEL: test_vld1_lane_s16:
; CHECK: ld1 { {{v[0-9]+}}.h }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: ld1 { v0.h }[3], [x0]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = load i16, i16* %a, align 2
%vld1_lane = insertelement <4 x i16> %b, i16 %0, i32 3
@ -339,7 +415,11 @@ entry:
define <2 x i32> @test_vld1_lane_s32(i32* %a, <2 x i32> %b) {
; CHECK-LABEL: test_vld1_lane_s32:
; CHECK: ld1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: ld1 { v0.s }[1], [x0]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* %a, align 4
%vld1_lane = insertelement <2 x i32> %b, i32 %0, i32 1
@ -348,7 +428,9 @@ entry:
define <1 x i64> @test_vld1_lane_s64(i64* %a, <1 x i64> %b) {
; CHECK-LABEL: test_vld1_lane_s64:
; CHECK: ldr {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ldr d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = load i64, i64* %a, align 8
%vld1_lane = insertelement <1 x i64> undef, i64 %0, i32 0
@ -357,7 +439,11 @@ entry:
define <2 x float> @test_vld1_lane_f32(float* %a, <2 x float> %b) {
; CHECK-LABEL: test_vld1_lane_f32:
; CHECK: ld1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: ld1 { v0.s }[1], [x0]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = load float, float* %a, align 4
%vld1_lane = insertelement <2 x float> %b, float %0, i32 1
@ -366,7 +452,9 @@ entry:
define <1 x double> @test_vld1_lane_f64(double* %a, <1 x double> %b) {
; CHECK-LABEL: test_vld1_lane_f64:
; CHECK: ldr {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ldr d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = load double, double* %a, align 8
%vld1_lane = insertelement <1 x double> undef, double %0, i32 0
@ -375,7 +463,9 @@ entry:
define void @test_vst1q_lane_s8(i8* %a, <16 x i8> %b) {
; CHECK-LABEL: test_vst1q_lane_s8:
; CHECK: st1 { {{v[0-9]+}}.b }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.b }[15], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <16 x i8> %b, i32 15
store i8 %0, i8* %a, align 1
@ -384,7 +474,9 @@ entry:
define void @test_vst1q_lane_s16(i16* %a, <8 x i16> %b) {
; CHECK-LABEL: test_vst1q_lane_s16:
; CHECK: st1 { {{v[0-9]+}}.h }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.h }[7], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <8 x i16> %b, i32 7
store i16 %0, i16* %a, align 2
@ -393,7 +485,9 @@ entry:
define void @test_vst1q_lane0_s16(i16* %a, <8 x i16> %b) {
; CHECK-LABEL: test_vst1q_lane0_s16:
; CHECK: str {{h[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str h0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <8 x i16> %b, i32 0
store i16 %0, i16* %a, align 2
@ -402,7 +496,9 @@ entry:
define void @test_vst1q_lane_s32(i32* %a, <4 x i32> %b) {
; CHECK-LABEL: test_vst1q_lane_s32:
; CHECK: st1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.s }[3], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x i32> %b, i32 3
store i32 %0, i32* %a, align 4
@ -411,7 +507,9 @@ entry:
define void @test_vst1q_lane0_s32(i32* %a, <4 x i32> %b) {
; CHECK-LABEL: test_vst1q_lane0_s32:
; CHECK: str {{s[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str s0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x i32> %b, i32 0
store i32 %0, i32* %a, align 4
@ -420,7 +518,9 @@ entry:
define void @test_vst1q_lane_s64(i64* %a, <2 x i64> %b) {
; CHECK-LABEL: test_vst1q_lane_s64:
; CHECK: st1 { {{v[0-9]+}}.d }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.d }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x i64> %b, i32 1
store i64 %0, i64* %a, align 8
@ -429,7 +529,9 @@ entry:
define void @test_vst1q_lane0_s64(i64* %a, <2 x i64> %b) {
; CHECK-LABEL: test_vst1q_lane0_s64:
; CHECK: str {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x i64> %b, i32 0
store i64 %0, i64* %a, align 8
@ -438,7 +540,9 @@ entry:
define void @test_vst1q_lane_f32(float* %a, <4 x float> %b) {
; CHECK-LABEL: test_vst1q_lane_f32:
; CHECK: st1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.s }[3], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x float> %b, i32 3
store float %0, float* %a, align 4
@ -447,7 +551,9 @@ entry:
define void @test_vst1q_lane0_f32(float* %a, <4 x float> %b) {
; CHECK-LABEL: test_vst1q_lane0_f32:
; CHECK: str {{s[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str s0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x float> %b, i32 0
store float %0, float* %a, align 4
@ -456,7 +562,9 @@ entry:
define void @test_vst1q_lane_f64(double* %a, <2 x double> %b) {
; CHECK-LABEL: test_vst1q_lane_f64:
; CHECK: st1 { {{v[0-9]+}}.d }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: st1 { v0.d }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x double> %b, i32 1
store double %0, double* %a, align 8
@ -465,7 +573,9 @@ entry:
define void @test_vst1q_lane0_f64(double* %a, <2 x double> %b) {
; CHECK-LABEL: test_vst1q_lane0_f64:
; CHECK: str {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x double> %b, i32 0
store double %0, double* %a, align 8
@ -474,7 +584,10 @@ entry:
define void @test_vst1_lane_s8(i8* %a, <8 x i8> %b) {
; CHECK-LABEL: test_vst1_lane_s8:
; CHECK: st1 { {{v[0-9]+}}.b }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: st1 { v0.b }[7], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <8 x i8> %b, i32 7
store i8 %0, i8* %a, align 1
@ -483,7 +596,10 @@ entry:
define void @test_vst1_lane_s16(i16* %a, <4 x i16> %b) {
; CHECK-LABEL: test_vst1_lane_s16:
; CHECK: st1 { {{v[0-9]+}}.h }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: st1 { v0.h }[3], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x i16> %b, i32 3
store i16 %0, i16* %a, align 2
@ -492,7 +608,10 @@ entry:
define void @test_vst1_lane0_s16(i16* %a, <4 x i16> %b) {
; CHECK-LABEL: test_vst1_lane0_s16:
; CHECK: str {{h[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: str h0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <4 x i16> %b, i32 0
store i16 %0, i16* %a, align 2
@ -501,7 +620,10 @@ entry:
define void @test_vst1_lane_s32(i32* %a, <2 x i32> %b) {
; CHECK-LABEL: test_vst1_lane_s32:
; CHECK: st1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: st1 { v0.s }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x i32> %b, i32 1
store i32 %0, i32* %a, align 4
@ -510,7 +632,10 @@ entry:
define void @test_vst1_lane0_s32(i32* %a, <2 x i32> %b) {
; CHECK-LABEL: test_vst1_lane0_s32:
; CHECK: str {{s[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: str s0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x i32> %b, i32 0
store i32 %0, i32* %a, align 4
@ -519,7 +644,10 @@ entry:
define void @test_vst1_lane_s64(i64* %a, <1 x i64> %b) {
; CHECK-LABEL: test_vst1_lane_s64:
; CHECK: str {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <1 x i64> %b, i32 0
store i64 %0, i64* %a, align 8
@ -528,7 +656,10 @@ entry:
define void @test_vst1_lane_f32(float* %a, <2 x float> %b) {
; CHECK-LABEL: test_vst1_lane_f32:
; CHECK: st1 { {{v[0-9]+}}.s }[{{[0-9]+}}], [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: st1 { v0.s }[1], [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x float> %b, i32 1
store float %0, float* %a, align 4
@ -537,7 +668,10 @@ entry:
define void @test_vst1_lane0_f32(float* %a, <2 x float> %b) {
; CHECK-LABEL: test_vst1_lane0_f32:
; CHECK: str {{s[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: str s0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <2 x float> %b, i32 0
store float %0, float* %a, align 4
@ -546,7 +680,9 @@ entry:
define void @test_vst1_lane_f64(double* %a, <1 x double> %b) {
; CHECK-LABEL: test_vst1_lane_f64:
; CHECK: str {{d[0-9]+}}, [x0]
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
entry:
%0 = extractelement <1 x double> %b, i32 0
store double %0, double* %a, align 8