[llvm] [AArch64] Enable aggressivelyPreferBuildVectorSources (PR #142729)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 4 00:12:18 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-globalisel
Author: David Green (davemgreen)
<details>
<summary>Changes</summary>
This helps to remove some inefficient buildvector lowering by converting extract_vector_elt(buildvector) to the original source. It seems to be a general improvement.
---
Patch is 328.02 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/142729.diff
16 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64ISelLowering.h (+4)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/combine-build-vector.mir (+2-6)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/combine-extract-vec-elt.mir (+1-3)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/combine-insert-vec-elt.mir (+1-1)
- (modified) llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll (+271-305)
- (modified) llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll (+177-211)
- (modified) llvm/test/CodeGen/AArch64/fptrunc.ll (+9-19)
- (modified) llvm/test/CodeGen/AArch64/itofp.ll (+112-108)
- (modified) llvm/test/CodeGen/AArch64/sext.ll (+2-4)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-bitcast.ll (+7-12)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-ext-loads.ll (+78-182)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-fp-extend-trunc.ll (+84-150)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-int-extends.ll (+1343-2613)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-int-to-fp.ll (+140-236)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-ld2-alloca.ll (+7-13)
- (modified) llvm/test/CodeGen/AArch64/zext-to-tbl.ll (+78-89)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index b2174487c2fe8..f193fa05dd161 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -449,6 +449,10 @@ class AArch64TargetLowering : public TargetLowering {
/// Enable aggressive FMA fusion on targets that want it.
bool enableAggressiveFMAFusion(EVT VT) const override;
+ bool aggressivelyPreferBuildVectorSources(EVT VecVT) const override {
+ return true;
+ }
+
/// Returns the size of the platform's va_list object.
unsigned getVaListSizeInBits(const DataLayout &DL) const override;
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-build-vector.mir b/llvm/test/CodeGen/AArch64/GlobalISel/combine-build-vector.mir
index 93f6051c3bd3b..5189582d0b6ac 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-build-vector.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-build-vector.mir
@@ -55,13 +55,9 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %arg1:_(s64) = COPY $x0
; CHECK-NEXT: %arg2:_(s64) = COPY $x1
- ; CHECK-NEXT: %zero:_(s64) = G_CONSTANT i64 0
- ; CHECK-NEXT: %one:_(s64) = G_CONSTANT i64 1
; CHECK-NEXT: %bv:_(<2 x s64>) = G_BUILD_VECTOR %arg1(s64), %arg2(s64)
- ; CHECK-NEXT: %extract:_(s64) = G_EXTRACT_VECTOR_ELT %bv(<2 x s64>), %zero(s64)
- ; CHECK-NEXT: %extract2:_(s64) = G_EXTRACT_VECTOR_ELT %bv(<2 x s64>), %one(s64)
- ; CHECK-NEXT: $x0 = COPY %extract(s64)
- ; CHECK-NEXT: $x1 = COPY %extract2(s64)
+ ; CHECK-NEXT: $x0 = COPY %arg1(s64)
+ ; CHECK-NEXT: $x1 = COPY %arg2(s64)
; CHECK-NEXT: $q0 = COPY %bv(<2 x s64>)
; CHECK-NEXT: RET_ReallyLR implicit $x0
%arg1:_(s64) = COPY $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-extract-vec-elt.mir b/llvm/test/CodeGen/AArch64/GlobalISel/combine-extract-vec-elt.mir
index e2933690c7c55..e81447a1de4b6 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-extract-vec-elt.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-extract-vec-elt.mir
@@ -175,10 +175,8 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %arg1:_(s64) = COPY $x0
; CHECK-NEXT: %arg2:_(s64) = COPY $x1
- ; CHECK-NEXT: %zero:_(s64) = G_CONSTANT i64 0
; CHECK-NEXT: %bv:_(<2 x s64>) = G_BUILD_VECTOR %arg1(s64), %arg2(s64)
- ; CHECK-NEXT: %extract:_(s64) = G_EXTRACT_VECTOR_ELT %bv(<2 x s64>), %zero(s64)
- ; CHECK-NEXT: $x0 = COPY %extract(s64)
+ ; CHECK-NEXT: $x0 = COPY %arg1(s64)
; CHECK-NEXT: $q0 = COPY %bv(<2 x s64>)
; CHECK-NEXT: RET_ReallyLR implicit $x0
%arg1:_(s64) = COPY $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-insert-vec-elt.mir b/llvm/test/CodeGen/AArch64/GlobalISel/combine-insert-vec-elt.mir
index c000a8e635bc6..86c0575961a17 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-insert-vec-elt.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-insert-vec-elt.mir
@@ -278,8 +278,8 @@ body: |
; CHECK: liveins: $x0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[C:%[0-9]+]]:_(s8) = G_CONSTANT i8 127
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s8>) = G_BUILD_VECTOR [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8), [[C]](s8)
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<32 x s8>), [[COPY]](p0) :: (store (<32 x s8>))
; CHECK-NEXT: RET_ReallyLR
%3:_(s8) = G_CONSTANT i8 127
diff --git a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
index a33b1ef569fc3..04dfdedb42752 100644
--- a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
+++ b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
@@ -726,7 +726,7 @@ define <3 x i32> @test_signed_v3f128_v3i32(<3 x fp128> %f) {
; CHECK-SD-LABEL: test_signed_v3f128_v3i32:
; CHECK-SD: // %bb.0:
; CHECK-SD-NEXT: sub sp, sp, #128
-; CHECK-SD-NEXT: str x30, [sp, #80] // 8-byte Folded Spill
+; CHECK-SD-NEXT: stp x30, x23, [sp, #80] // 16-byte Folded Spill
; CHECK-SD-NEXT: stp x22, x21, [sp, #96] // 16-byte Folded Spill
; CHECK-SD-NEXT: stp x20, x19, [sp, #112] // 16-byte Folded Spill
; CHECK-SD-NEXT: .cfi_def_cfa_offset 128
@@ -734,13 +734,13 @@ define <3 x i32> @test_signed_v3f128_v3i32(<3 x fp128> %f) {
; CHECK-SD-NEXT: .cfi_offset w20, -16
; CHECK-SD-NEXT: .cfi_offset w21, -24
; CHECK-SD-NEXT: .cfi_offset w22, -32
+; CHECK-SD-NEXT: .cfi_offset w23, -40
; CHECK-SD-NEXT: .cfi_offset w30, -48
-; CHECK-SD-NEXT: stp q0, q2, [sp, #48] // 32-byte Folded Spill
-; CHECK-SD-NEXT: mov v2.16b, v1.16b
+; CHECK-SD-NEXT: str q0, [sp, #64] // 16-byte Folded Spill
; CHECK-SD-NEXT: adrp x8, .LCPI16_0
-; CHECK-SD-NEXT: str q1, [sp, #32] // 16-byte Folded Spill
-; CHECK-SD-NEXT: ldr q1, [x8, :lo12:.LCPI16_0]
; CHECK-SD-NEXT: mov v0.16b, v2.16b
+; CHECK-SD-NEXT: stp q2, q1, [sp, #32] // 32-byte Folded Spill
+; CHECK-SD-NEXT: ldr q1, [x8, :lo12:.LCPI16_0]
; CHECK-SD-NEXT: str q1, [sp, #16] // 16-byte Folded Spill
; CHECK-SD-NEXT: bl __getf2
; CHECK-SD-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
@@ -755,15 +755,15 @@ define <3 x i32> @test_signed_v3f128_v3i32(<3 x fp128> %f) {
; CHECK-SD-NEXT: str q1, [sp] // 16-byte Folded Spill
; CHECK-SD-NEXT: bl __gttf2
; CHECK-SD-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
-; CHECK-SD-NEXT: mov w21, #2147483647 // =0x7fffffff
+; CHECK-SD-NEXT: mov w22, #2147483647 // =0x7fffffff
; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: csel w19, w21, w19, gt
+; CHECK-SD-NEXT: csel w19, w22, w19, gt
; CHECK-SD-NEXT: mov v1.16b, v0.16b
; CHECK-SD-NEXT: bl __unordtf2
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: csel w22, wzr, w19, ne
+; CHECK-SD-NEXT: csel w21, wzr, w19, ne
; CHECK-SD-NEXT: bl __getf2
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: mov w19, w0
@@ -775,16 +775,13 @@ define <3 x i32> @test_signed_v3f128_v3i32(<3 x fp128> %f) {
; CHECK-SD-NEXT: bl __gttf2
; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: csel w19, w21, w19, gt
+; CHECK-SD-NEXT: csel w19, w22, w19, gt
; CHECK-SD-NEXT: mov v1.16b, v0.16b
; CHECK-SD-NEXT: bl __unordtf2
-; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
-; CHECK-SD-NEXT: csel w8, wzr, w19, ne
-; CHECK-SD-NEXT: fmov s0, w8
-; CHECK-SD-NEXT: mov v0.s[1], w22
-; CHECK-SD-NEXT: str q0, [sp, #48] // 16-byte Folded Spill
; CHECK-SD-NEXT: ldr q0, [sp, #64] // 16-byte Folded Reload
+; CHECK-SD-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; CHECK-SD-NEXT: cmp w0, #0
+; CHECK-SD-NEXT: csel w23, wzr, w19, ne
; CHECK-SD-NEXT: bl __getf2
; CHECK-SD-NEXT: ldr q0, [sp, #64] // 16-byte Folded Reload
; CHECK-SD-NEXT: mov w19, w0
@@ -796,16 +793,17 @@ define <3 x i32> @test_signed_v3f128_v3i32(<3 x fp128> %f) {
; CHECK-SD-NEXT: bl __gttf2
; CHECK-SD-NEXT: ldr q0, [sp, #64] // 16-byte Folded Reload
; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: csel w19, w21, w19, gt
+; CHECK-SD-NEXT: csel w19, w22, w19, gt
; CHECK-SD-NEXT: mov v1.16b, v0.16b
; CHECK-SD-NEXT: bl __unordtf2
; CHECK-SD-NEXT: cmp w0, #0
-; CHECK-SD-NEXT: ldr q0, [sp, #48] // 16-byte Folded Reload
-; CHECK-SD-NEXT: ldr x30, [sp, #80] // 8-byte Folded Reload
; CHECK-SD-NEXT: csel w8, wzr, w19, ne
; CHECK-SD-NEXT: ldp x20, x19, [sp, #112] // 16-byte Folded Reload
+; CHECK-SD-NEXT: fmov s0, w8
+; CHECK-SD-NEXT: mov v0.s[1], w23
+; CHECK-SD-NEXT: ldp x30, x23, [sp, #80] // 16-byte Folded Reload
+; CHECK-SD-NEXT: mov v0.s[2], w21
; CHECK-SD-NEXT: ldp x22, x21, [sp, #96] // 16-byte Folded Reload
-; CHECK-SD-NEXT: mov v0.s[2], w8
; CHECK-SD-NEXT: add sp, sp, #128
; CHECK-SD-NEXT: ret
;
@@ -4890,63 +4888,61 @@ define <16 x i16> @test_signed_v16f16_v16i16(<16 x half> %f) {
define <8 x i8> @test_signed_v8f64_v8i8(<8 x double> %f) {
; CHECK-SD-LABEL: test_signed_v8f64_v8i8:
; CHECK-SD: // %bb.0:
-; CHECK-SD-NEXT: mov d4, v3.d[1]
-; CHECK-SD-NEXT: fcvtzs w11, d3
-; CHECK-SD-NEXT: mov w9, #127 // =0x7f
-; CHECK-SD-NEXT: mov d3, v1.d[1]
-; CHECK-SD-NEXT: fcvtzs w13, d2
-; CHECK-SD-NEXT: fcvtzs w15, d1
-; CHECK-SD-NEXT: fcvtzs w17, d0
-; CHECK-SD-NEXT: fcvtzs w8, d4
-; CHECK-SD-NEXT: mov d4, v2.d[1]
-; CHECK-SD-NEXT: mov d2, v0.d[1]
-; CHECK-SD-NEXT: fcvtzs w14, d3
-; CHECK-SD-NEXT: cmp w8, #127
-; CHECK-SD-NEXT: fcvtzs w12, d4
-; CHECK-SD-NEXT: fcvtzs w16, d2
-; CHECK-SD-NEXT: csel w10, w8, w9, lt
-; CHECK-SD-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-SD-NEXT: mov d4, v0.d[1]
+; CHECK-SD-NEXT: fcvtzs w10, d0
+; CHECK-SD-NEXT: mov w8, #127 // =0x7f
+; CHECK-SD-NEXT: fcvtzs w12, d1
+; CHECK-SD-NEXT: mov d1, v1.d[1]
+; CHECK-SD-NEXT: fcvtzs w9, d4
+; CHECK-SD-NEXT: cmp w9, #127
+; CHECK-SD-NEXT: csel w11, w9, w8, lt
+; CHECK-SD-NEXT: mov w9, #-128 // =0xffffff80
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
+; CHECK-SD-NEXT: cmn w10, #128
+; CHECK-SD-NEXT: csel w10, w10, w9, gt
+; CHECK-SD-NEXT: cmp w12, #127
+; CHECK-SD-NEXT: fmov s0, w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: mov d1, v2.d[1]
+; CHECK-SD-NEXT: mov v0.b[1], w11
+; CHECK-SD-NEXT: csel w11, w12, w8, lt
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
+; CHECK-SD-NEXT: mov v0.b[2], w11
+; CHECK-SD-NEXT: fcvtzs w11, d2
; CHECK-SD-NEXT: cmn w10, #128
-; CHECK-SD-NEXT: csel w10, w10, w8, gt
+; CHECK-SD-NEXT: csel w10, w10, w9, gt
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: csel w11, w11, w9, lt
+; CHECK-SD-NEXT: mov v0.b[3], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v3.d[1]
; CHECK-SD-NEXT: cmn w11, #128
-; CHECK-SD-NEXT: csel w11, w11, w8, gt
-; CHECK-SD-NEXT: cmp w12, #127
-; CHECK-SD-NEXT: csel w12, w12, w9, lt
-; CHECK-SD-NEXT: fmov s3, w11
-; CHECK-SD-NEXT: cmn w12, #128
-; CHECK-SD-NEXT: csel w12, w12, w8, gt
-; CHECK-SD-NEXT: cmp w13, #127
-; CHECK-SD-NEXT: csel w13, w13, w9, lt
-; CHECK-SD-NEXT: mov v3.s[1], w10
-; CHECK-SD-NEXT: cmn w13, #128
-; CHECK-SD-NEXT: csel w13, w13, w8, gt
-; CHECK-SD-NEXT: cmp w14, #127
-; CHECK-SD-NEXT: csel w14, w14, w9, lt
-; CHECK-SD-NEXT: fmov s2, w13
-; CHECK-SD-NEXT: cmn w14, #128
-; CHECK-SD-NEXT: csel w14, w14, w8, gt
-; CHECK-SD-NEXT: cmp w15, #127
-; CHECK-SD-NEXT: csel w15, w15, w9, lt
-; CHECK-SD-NEXT: mov v2.s[1], w12
-; CHECK-SD-NEXT: cmn w15, #128
-; CHECK-SD-NEXT: csel w15, w15, w8, gt
-; CHECK-SD-NEXT: cmp w16, #127
-; CHECK-SD-NEXT: csel w11, w16, w9, lt
-; CHECK-SD-NEXT: fmov s1, w15
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[4], w11
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: fcvtzs w11, d3
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
+; CHECK-SD-NEXT: cmn w10, #128
+; CHECK-SD-NEXT: csel w10, w10, w9, gt
+; CHECK-SD-NEXT: mov v0.b[5], w10
+; CHECK-SD-NEXT: cmp w11, #127
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
; CHECK-SD-NEXT: cmn w11, #128
-; CHECK-SD-NEXT: csel w10, w11, w8, gt
-; CHECK-SD-NEXT: cmp w17, #127
-; CHECK-SD-NEXT: csel w9, w17, w9, lt
-; CHECK-SD-NEXT: mov v1.s[1], w14
-; CHECK-SD-NEXT: cmn w9, #128
-; CHECK-SD-NEXT: csel w8, w9, w8, gt
-; CHECK-SD-NEXT: fmov s0, w8
-; CHECK-SD-NEXT: adrp x8, .LCPI82_0
-; CHECK-SD-NEXT: ldr d4, [x8, :lo12:.LCPI82_0]
-; CHECK-SD-NEXT: mov v0.s[1], w10
-; CHECK-SD-NEXT: tbl v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v4.8b
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[6], w11
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w8, w10, w8, lt
+; CHECK-SD-NEXT: cmn w8, #128
+; CHECK-SD-NEXT: csel w8, w8, w9, gt
+; CHECK-SD-NEXT: mov v0.b[7], w8
+; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_signed_v8f64_v8i8:
@@ -4990,11 +4986,9 @@ define <16 x i8> @test_signed_v16f64_v16i8(<16 x double> %f) {
; CHECK-SD-NEXT: mov d16, v0.d[1]
; CHECK-SD-NEXT: fcvtzs w10, d0
; CHECK-SD-NEXT: mov w8, #127 // =0x7f
-; CHECK-SD-NEXT: mov d0, v1.d[1]
-; CHECK-SD-NEXT: fcvtzs w13, d1
-; CHECK-SD-NEXT: mov d1, v2.d[1]
+; CHECK-SD-NEXT: fcvtzs w12, d1
+; CHECK-SD-NEXT: mov d1, v1.d[1]
; CHECK-SD-NEXT: fcvtzs w9, d16
-; CHECK-SD-NEXT: fcvtzs w12, d0
; CHECK-SD-NEXT: cmp w9, #127
; CHECK-SD-NEXT: csel w11, w9, w8, lt
; CHECK-SD-NEXT: mov w9, #-128 // =0xffffff80
@@ -5006,115 +5000,94 @@ define <16 x i8> @test_signed_v16f64_v16i8(<16 x double> %f) {
; CHECK-SD-NEXT: csel w10, w10, w9, gt
; CHECK-SD-NEXT: cmp w12, #127
; CHECK-SD-NEXT: fmov s0, w10
-; CHECK-SD-NEXT: csel w10, w12, w8, lt
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: mov d1, v2.d[1]
+; CHECK-SD-NEXT: mov v0.b[1], w11
+; CHECK-SD-NEXT: csel w11, w12, w8, lt
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
+; CHECK-SD-NEXT: mov v0.b[2], w11
+; CHECK-SD-NEXT: fcvtzs w11, d2
; CHECK-SD-NEXT: cmn w10, #128
; CHECK-SD-NEXT: csel w10, w10, w9, gt
-; CHECK-SD-NEXT: cmp w13, #127
-; CHECK-SD-NEXT: csel w12, w13, w8, lt
-; CHECK-SD-NEXT: mov v0.s[1], w11
-; CHECK-SD-NEXT: fcvtzs w11, d1
-; CHECK-SD-NEXT: cmn w12, #128
-; CHECK-SD-NEXT: csel w12, w12, w9, gt
-; CHECK-SD-NEXT: fmov s1, w12
-; CHECK-SD-NEXT: fcvtzs w12, d2
-; CHECK-SD-NEXT: mov d2, v3.d[1]
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: mov w13, v0.s[1]
-; CHECK-SD-NEXT: mov v1.s[1], w10
-; CHECK-SD-NEXT: csel w10, w11, w8, lt
+; CHECK-SD-NEXT: mov v0.b[3], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v3.d[1]
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[4], w11
+; CHECK-SD-NEXT: fcvtzs w11, d3
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
; CHECK-SD-NEXT: cmn w10, #128
-; CHECK-SD-NEXT: fcvtzs w11, d2
; CHECK-SD-NEXT: csel w10, w10, w9, gt
-; CHECK-SD-NEXT: cmp w12, #127
-; CHECK-SD-NEXT: mov v0.b[1], w13
-; CHECK-SD-NEXT: csel w12, w12, w8, lt
-; CHECK-SD-NEXT: cmn w12, #128
-; CHECK-SD-NEXT: mov w13, v1.s[1]
-; CHECK-SD-NEXT: csel w12, w12, w9, gt
+; CHECK-SD-NEXT: mov v0.b[5], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: fmov s2, w12
-; CHECK-SD-NEXT: fcvtzs w12, d3
-; CHECK-SD-NEXT: mov d3, v4.d[1]
-; CHECK-SD-NEXT: mov v0.b[2], v1.b[0]
-; CHECK-SD-NEXT: mov v2.s[1], w10
-; CHECK-SD-NEXT: csel w10, w11, w8, lt
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v4.d[1]
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[6], w11
+; CHECK-SD-NEXT: fcvtzs w11, d4
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
; CHECK-SD-NEXT: cmn w10, #128
-; CHECK-SD-NEXT: fcvtzs w11, d3
; CHECK-SD-NEXT: csel w10, w10, w9, gt
-; CHECK-SD-NEXT: cmp w12, #127
-; CHECK-SD-NEXT: mov v0.b[3], w13
-; CHECK-SD-NEXT: csel w12, w12, w8, lt
-; CHECK-SD-NEXT: cmn w12, #128
-; CHECK-SD-NEXT: mov w13, v2.s[1]
-; CHECK-SD-NEXT: csel w12, w12, w9, gt
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: fmov s3, w12
-; CHECK-SD-NEXT: fcvtzs w12, d4
-; CHECK-SD-NEXT: mov v0.b[4], v2.b[0]
-; CHECK-SD-NEXT: mov d4, v5.d[1]
-; CHECK-SD-NEXT: mov v3.s[1], w10
-; CHECK-SD-NEXT: csel w10, w11, w8, lt
+; CHECK-SD-NEXT: mov v0.b[7], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v5.d[1]
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[8], w11
+; CHECK-SD-NEXT: fcvtzs w11, d5
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
; CHECK-SD-NEXT: cmn w10, #128
-; CHECK-SD-NEXT: mov v0.b[5], w13
; CHECK-SD-NEXT: csel w10, w10, w9, gt
-; CHECK-SD-NEXT: cmp w12, #127
-; CHECK-SD-NEXT: fcvtzs w11, d4
-; CHECK-SD-NEXT: csel w12, w12, w8, lt
-; CHECK-SD-NEXT: cmn w12, #128
-; CHECK-SD-NEXT: mov w13, v3.s[1]
-; CHECK-SD-NEXT: csel w12, w12, w9, gt
-; CHECK-SD-NEXT: mov v0.b[6], v3.b[0]
-; CHECK-SD-NEXT: fmov s4, w12
-; CHECK-SD-NEXT: fcvtzs w12, d5
+; CHECK-SD-NEXT: mov v0.b[9], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: mov d5, v6.d[1]
-; CHECK-SD-NEXT: mov v4.s[1], w10
-; CHECK-SD-NEXT: csel w10, w11, w8, lt
-; CHECK-SD-NEXT: mov v0.b[7], w13
-; CHECK-SD-NEXT: cmn w10, #128
-; CHECK-SD-NEXT: csel w10, w10, w9, gt
-; CHECK-SD-NEXT: cmp w12, #127
-; CHECK-SD-NEXT: fcvtzs w13, d5
-; CHECK-SD-NEXT: csel w11, w12, w8, lt
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v6.d[1]
; CHECK-SD-NEXT: cmn w11, #128
-; CHECK-SD-NEXT: mov w12, v4.s[1]
-; CHECK-SD-NEXT: mov v0.b[8], v4.b[0]
; CHECK-SD-NEXT: csel w11, w11, w9, gt
-; CHECK-SD-NEXT: fmov s5, w11
+; CHECK-SD-NEXT: mov v0.b[10], w11
; CHECK-SD-NEXT: fcvtzs w11, d6
-; CHECK-SD-NEXT: cmp w13, #127
-; CHECK-SD-NEXT: mov d6, v7.d[1]
-; CHECK-SD-NEXT: mov v0.b[9], w12
-; CHECK-SD-NEXT: mov v5.s[1], w10
-; CHECK-SD-NEXT: csel w10, w13, w8, lt
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
; CHECK-SD-NEXT: cmn w10, #128
; CHECK-SD-NEXT: csel w10, w10, w9, gt
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: fcvtzs w13, d6
+; CHECK-SD-NEXT: mov v0.b[11], w10
+; CHECK-SD-NEXT: fcvtzs w10, d1
; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: mov d1, v7.d[1]
; CHECK-SD-NEXT: cmn w11, #128
-; CHECK-SD-NEXT: mov v0.b[10], v5.b[0]
-; CHECK-SD-NEXT: mov w12, v5.s[1]
; CHECK-SD-NEXT: csel w11, w11, w9, gt
-; CHECK-SD-NEXT: fmov s6, w11
+; CHECK-SD-NEXT: mov v0.b[12], w11
+; CHECK-SD-NEXT: cmp w10, #127
; CHECK-SD-NEXT: fcvtzs w11, d7
-; CHECK-SD-NEXT: cmp w13, #127
-; CHECK-SD-NEXT: mov v0.b[11], w12
-; CHECK-SD-NEXT: mov v6.s[1], w10
-; CHECK-SD-NEXT: csel w10, w13, w8, lt
+; CHECK-SD-NEXT: csel w10, w10, w8, lt
; CHECK-SD-NEXT: cmn w10, #128
; CHECK-SD-NEXT: csel w10, w10, w9, gt
+; CHECK-SD-NEXT: mov v0.b[13], w10
; CHECK-SD-NEXT: cmp w11, #127
-; CHECK-SD-NEXT: csel w8, w11, w8, lt
+; CHECK-SD-NEXT: fcvtzs w10, d1
+; CHECK-SD-NEXT: csel w11, w11, w8, lt
+; CHECK-SD-NEXT: cmn w11, #128
+; CHECK-SD-NEXT: csel w11, w11, w9, gt
+; CHECK-SD-NEXT: mov v0.b[14], w11
+; CHECK-SD-NEXT: cmp w10, #127
+; CHECK-SD-NEXT: csel w8, w10, w8, lt
; CHECK-SD-NEXT: cmn w8, #128
-; CHECK-SD-NEXT: mov v0.b[12], v6.b[0]
-; CHECK-SD-NEXT: mov w11, v6.s[1]
; CHECK-SD-NEXT: csel w8, w8, w9, gt
-; CHECK-SD-NEXT: fmov s7, w8
-; CHECK-SD-NEXT: mov v0.b[13], w11
-; CHECK-SD-NEXT: mov v7.s[1], w10
-; CHECK-SD-NEXT: mov v0.b[14], v7.b[0]
-; CHECK-SD-NEXT: mov w8, v7.s[1]
; CHECK-SD-NEXT: mov v0.b[15], w8
; CHECK-SD-NEXT: ret
;
@@ -5179,63 +5152,60 @@ define <16 x i8> @test_signed_v16f64_v16i8(<16 x double> %f) {
define <8 x i16> @test_signed_v8f64_v8i16(<8 x double> %f) {
; CHECK-...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/142729
More information about the llvm-commits
mailing list