[clang] [llvm] [Arm] Regenerate tests (NFC) (PR #121801)

via llvm-commits llvm-commits at lists.llvm.org
Mon Jan 6 09:02:04 PST 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-clang

Author: Momchil Velikov (momchil-velikov)

<details>
<summary>Changes</summary>

This patch adds `instcombine` to some tests that were passing
Clang's output to `opt -S --passes=mem2reg`, and converts some
other tests to using `update_cc_test_checks.py`.

Assembly part of some tests was also split out and moved to LLVM.

This makes it easier to compare test changes in upcoming patches.

---

Patch is 6.30 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/121801.diff


48 Files Affected:

- (modified) clang/test/CodeGen/AArch64/bf16-dotprod-intrinsics.c (+30-160) 
- (modified) clang/test/CodeGen/AArch64/bf16-getset-intrinsics.c (+17-33) 
- (modified) clang/test/CodeGen/AArch64/bf16-reinterpret-intrinsics.c (+218-163) 
- (modified) clang/test/CodeGen/AArch64/neon-2velem.c (+775-2178) 
- (modified) clang/test/CodeGen/AArch64/neon-extract.c (+143-145) 
- (modified) clang/test/CodeGen/AArch64/neon-fma.c (+33-75) 
- (modified) clang/test/CodeGen/AArch64/neon-fp16fml.c (+41-865) 
- (modified) clang/test/CodeGen/AArch64/neon-intrinsics-constrained.c (+1173-453) 
- (modified) clang/test/CodeGen/AArch64/neon-intrinsics.c (+15106-10053) 
- (modified) clang/test/CodeGen/AArch64/neon-ldst-one-rcpc3.c (+33-65) 
- (modified) clang/test/CodeGen/AArch64/neon-ldst-one.c (+6458-4665) 
- (modified) clang/test/CodeGen/AArch64/neon-misc-constrained.c (+51-33) 
- (modified) clang/test/CodeGen/AArch64/neon-misc.c (+2094-1396) 
- (modified) clang/test/CodeGen/AArch64/neon-perm.c (+1298-1207) 
- (modified) clang/test/CodeGen/AArch64/neon-scalar-x-indexed-elem-constrained.c (+133-90) 
- (modified) clang/test/CodeGen/AArch64/neon-scalar-x-indexed-elem.c (+338-252) 
- (modified) clang/test/CodeGen/AArch64/poly-add.c (+11-26) 
- (modified) clang/test/CodeGen/AArch64/poly128.c (+32-34) 
- (modified) clang/test/CodeGen/AArch64/poly64.c (+518-338) 
- (modified) clang/test/CodeGen/AArch64/v8.1a-neon-intrinsics.c (+33-53) 
- (modified) clang/test/CodeGen/AArch64/v8.2a-neon-intrinsics-constrained.c (+333-233) 
- (modified) clang/test/CodeGen/AArch64/v8.2a-neon-intrinsics-generic.c (+58-150) 
- (modified) clang/test/CodeGen/AArch64/v8.2a-neon-intrinsics.c (+111-426) 
- (modified) clang/test/CodeGen/AArch64/v8.5a-neon-frint3264-intrinsic.c (+98-49) 
- (modified) clang/test/CodeGen/AArch64/v8.6a-neon-intrinsics.c (+104-88) 
- (modified) clang/test/CodeGen/arm-bf16-convert-intrinsics.c (+84-306) 
- (modified) clang/test/CodeGen/arm-bf16-dotprod-intrinsics.c (+31-161) 
- (modified) clang/test/CodeGen/arm-bf16-getset-intrinsics.c (+18-34) 
- (modified) clang/test/CodeGen/arm-neon-directed-rounding-constrained.c (+53-39) 
- (modified) clang/test/CodeGen/arm-neon-directed-rounding.c (+171-62) 
- (modified) clang/test/CodeGen/arm-neon-fma.c (+13-27) 
- (modified) clang/test/CodeGen/arm-neon-numeric-maxmin.c (+3-15) 
- (modified) clang/test/CodeGen/arm-neon-vcvtX.c (+9-25) 
- (modified) clang/test/CodeGen/arm-poly-add.c (+30-35) 
- (modified) clang/test/CodeGen/arm-v8.1a-neon-intrinsics.c (+82-114) 
- (modified) clang/test/CodeGen/arm-v8.2a-neon-intrinsics-generic.c (+119-277) 
- (modified) clang/test/CodeGen/arm-v8.2a-neon-intrinsics.c (+690-371) 
- (modified) clang/test/CodeGen/arm-v8.6a-neon-intrinsics.c (+62-48) 
- (modified) clang/test/CodeGen/arm64_vdupq_n_f64.c (+44-38) 
- (modified) clang/test/CodeGen/arm_neon_intrinsics.c (+15482-12225) 
- (added) llvm/test/CodeGen/AArch64/neon-misc-constrained.ll (+46) 
- (added) llvm/test/CodeGen/AArch64/neon-misc-unconstrained.ll (+45) 
- (added) llvm/test/CodeGen/AArch64/neon-scalar-x-indexed-elem-constrained.ll (+103) 
- (added) llvm/test/CodeGen/AArch64/neon-scalar-x-indexed-elem-unconstrained.ll (+103) 
- (added) llvm/test/CodeGen/AArch64/v8.2a-neon-intrinsics-constrained.ll (+276) 
- (added) llvm/test/CodeGen/AArch64/v8.2a-neon-intrinsics-unconstrained.ll (+265) 
- (modified) llvm/utils/UpdateTestChecks/common.py (+15) 
- (modified) llvm/utils/update_cc_test_checks.py (+11-6) 


``````````diff
diff --git a/clang/test/CodeGen/AArch64/bf16-dotprod-intrinsics.c b/clang/test/CodeGen/AArch64/bf16-dotprod-intrinsics.c
index 877d83c0fa3954..caa803ee794603 100644
--- a/clang/test/CodeGen/AArch64/bf16-dotprod-intrinsics.c
+++ b/clang/test/CodeGen/AArch64/bf16-dotprod-intrinsics.c
@@ -1,6 +1,6 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // RUN: %clang_cc1 -triple aarch64 -target-feature +neon -target-feature +bf16 \
-// RUN: -disable-O0-optnone -emit-llvm %s -o - | opt -S -passes=mem2reg | FileCheck %s
+// RUN: -disable-O0-optnone -emit-llvm %s -o - | opt -S -passes=mem2reg,instcombine | FileCheck %s
 
 // REQUIRES: aarch64-registered-target || arm-registered-target
 
@@ -8,10 +8,7 @@
 
 // CHECK-LABEL: @test_vbfdot_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x float> [[R:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x bfloat> [[A:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x bfloat> [[B:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R]], <4 x bfloat> [[A]], <4 x bfloat> [[B]])
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[B:%.*]])
 // CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
 //
 float32x2_t test_vbfdot_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b) {
@@ -20,10 +17,7 @@ float32x2_t test_vbfdot_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b) {
 
 // CHECK-LABEL: @test_vbfdotq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[B]])
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]])
 // CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
 //
 float32x4_t test_vbfdotq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b){
@@ -32,19 +26,10 @@ float32x4_t test_vbfdotq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b){
 
 // CHECK-LABEL: @test_vbfdot_lane_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[__REINT_128:%.*]] = alloca <4 x bfloat>, align 8
-// CHECK-NEXT:    [[__REINT1_128:%.*]] = alloca <2 x float>, align 8
-// CHECK-NEXT:    store <4 x bfloat> [[B:%.*]], ptr [[__REINT_128]], align 8
-// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[__REINT_128]], align 8
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x float> [[TMP0]] to <8 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x i8> [[TMP1]] to <2 x float>
-// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> [[TMP2]], <2 x i32> zeroinitializer
-// CHECK-NEXT:    store <2 x float> [[LANE]], ptr [[__REINT1_128]], align 8
-// CHECK-NEXT:    [[TMP3:%.*]] = load <4 x bfloat>, ptr [[__REINT1_128]], align 8
-// CHECK-NEXT:    [[TMP4:%.*]] = bitcast <2 x float> [[R:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x bfloat> [[A:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP6:%.*]] = bitcast <4 x bfloat> [[TMP3]] to <8 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R]], <4 x bfloat> [[A]], <4 x bfloat> [[TMP3]])
+// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <4 x bfloat> [[B:%.*]] to <2 x float>
+// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[DOTCAST]], <2 x float> poison, <2 x i32> zeroinitializer
+// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <2 x float> [[LANE]] to <4 x bfloat>
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[DOTCAST1]])
 // CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
 //
 float32x2_t test_vbfdot_lane_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b){
@@ -53,19 +38,10 @@ float32x2_t test_vbfdot_lane_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b){
 
 // CHECK-LABEL: @test_vbfdotq_laneq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[__REINT_130:%.*]] = alloca <8 x bfloat>, align 16
-// CHECK-NEXT:    [[__REINT1_130:%.*]] = alloca <4 x float>, align 16
-// CHECK-NEXT:    store <8 x bfloat> [[B:%.*]], ptr [[__REINT_130]], align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[__REINT_130]], align 16
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x float> [[TMP0]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <16 x i8> [[TMP1]] to <4 x float>
-// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> [[TMP2]], <4 x i32> <i32 3, i32 3, i32 3, i32 3>
-// CHECK-NEXT:    store <4 x float> [[LANE]], ptr [[__REINT1_130]], align 16
-// CHECK-NEXT:    [[TMP3:%.*]] = load <8 x bfloat>, ptr [[__REINT1_130]], align 16
-// CHECK-NEXT:    [[TMP4:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP5:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP6:%.*]] = bitcast <8 x bfloat> [[TMP3]] to <16 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[TMP3]])
+// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <4 x float>
+// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[DOTCAST]], <4 x float> poison, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
+// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <4 x float> [[LANE]] to <8 x bfloat>
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[DOTCAST1]])
 // CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
 //
 float32x4_t test_vbfdotq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
@@ -74,19 +50,10 @@ float32x4_t test_vbfdotq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b
 
 // CHECK-LABEL: @test_vbfdot_laneq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[__REINT_132:%.*]] = alloca <8 x bfloat>, align 16
-// CHECK-NEXT:    [[__REINT1_132:%.*]] = alloca <2 x float>, align 8
-// CHECK-NEXT:    store <8 x bfloat> [[B:%.*]], ptr [[__REINT_132]], align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[__REINT_132]], align 16
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x float> [[TMP0]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <16 x i8> [[TMP1]] to <4 x float>
-// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> [[TMP2]], <2 x i32> <i32 3, i32 3>
-// CHECK-NEXT:    store <2 x float> [[LANE]], ptr [[__REINT1_132]], align 8
-// CHECK-NEXT:    [[TMP3:%.*]] = load <4 x bfloat>, ptr [[__REINT1_132]], align 8
-// CHECK-NEXT:    [[TMP4:%.*]] = bitcast <2 x float> [[R:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x bfloat> [[A:%.*]] to <8 x i8>
-// CHECK-NEXT:    [[TMP6:%.*]] = bitcast <4 x bfloat> [[TMP3]] to <8 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R]], <4 x bfloat> [[A]], <4 x bfloat> [[TMP3]])
+// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <4 x float>
+// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[DOTCAST]], <4 x float> poison, <2 x i32> <i32 3, i32 3>
+// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <2 x float> [[LANE]] to <4 x bfloat>
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[DOTCAST1]])
 // CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
 //
 float32x2_t test_vbfdot_laneq_f32(float32x2_t r, bfloat16x4_t a, bfloat16x8_t b) {
@@ -95,19 +62,10 @@ float32x2_t test_vbfdot_laneq_f32(float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
 
 // CHECK-LABEL: @test_vbfdotq_lane_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[__REINT_126:%.*]] = alloca <4 x bfloat>, align 8
-// CHECK-NEXT:    [[__REINT1_126:%.*]] = alloca <4 x float>, align 16
-// CHECK-NEXT:    store <4 x bfloat> [[B:%.*]], ptr [[__REINT_126]], align 8
-// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[__REINT_126]], align 8
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x float> [[TMP0]] to <8 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x i8> [[TMP1]] to <2 x float>
-// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> [[TMP2]], <4 x i32> zeroinitializer
-// CHECK-NEXT:    store <4 x float> [[LANE]], ptr [[__REINT1_126]], align 16
-// CHECK-NEXT:    [[TMP3:%.*]] = load <8 x bfloat>, ptr [[__REINT1_126]], align 16
-// CHECK-NEXT:    [[TMP4:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP5:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP6:%.*]] = bitcast <8 x bfloat> [[TMP3]] to <16 x i8>
-// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[TMP3]])
+// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <4 x bfloat> [[B:%.*]] to <2 x float>
+// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[DOTCAST]], <2 x float> poison, <4 x i32> zeroinitializer
+// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <4 x float> [[LANE]] to <8 x bfloat>
+// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[DOTCAST1]])
 // CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
 //
 float32x4_t test_vbfdotq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b) {
@@ -116,11 +74,7 @@ float32x4_t test_vbfdotq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b)
 
 // CHECK-LABEL: @test_vbfmmlaq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMMLAQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmmla(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[B]])
-// CHECK-NEXT:    [[VBFMMLAQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMMLAQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VBFMMLAQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmmla(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]])
 // CHECK-NEXT:    ret <4 x float> [[VBFMMLAQ_F323_I]]
 //
 float32x4_t test_vbfmmlaq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
@@ -129,11 +83,7 @@ float32x4_t test_vbfmmlaq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
 
 // CHECK-LABEL: @test_vbfmlalbq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[B]])
-// CHECK-NEXT:    [[VBFMLALBQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMLALBQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]])
 // CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_F323_I]]
 //
 float32x4_t test_vbfmlalbq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
@@ -142,11 +92,7 @@ float32x4_t test_vbfmlalbq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
 
 // CHECK-LABEL: @test_vbfmlaltq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMLALTQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[B]])
-// CHECK-NEXT:    [[VBFMLALTQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMLALTQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VBFMLALTQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]])
 // CHECK-NEXT:    ret <4 x float> [[VBFMLALTQ_F323_I]]
 //
 float32x4_t test_vbfmlaltq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
@@ -155,27 +101,8 @@ float32x4_t test_vbfmlaltq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
 
 // CHECK-LABEL: @test_vbfmlalbq_lane_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[VGET_LANE:%.*]] = extractelement <4 x bfloat> [[B:%.*]], i32 0
-// CHECK-NEXT:    [[VECINIT:%.*]] = insertelement <8 x bfloat> poison, bfloat [[VGET_LANE]], i32 0
-// CHECK-NEXT:    [[VGET_LANE3:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT5:%.*]] = insertelement <8 x bfloat> [[VECINIT]], bfloat [[VGET_LANE3]], i32 1
-// CHECK-NEXT:    [[VGET_LANE8:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT10:%.*]] = insertelement <8 x bfloat> [[VECINIT5]], bfloat [[VGET_LANE8]], i32 2
-// CHECK-NEXT:    [[VGET_LANE13:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT15:%.*]] = insertelement <8 x bfloat> [[VECINIT10]], bfloat [[VGET_LANE13]], i32 3
-// CHECK-NEXT:    [[VGET_LANE18:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT20:%.*]] = insertelement <8 x bfloat> [[VECINIT15]], bfloat [[VGET_LANE18]], i32 4
-// CHECK-NEXT:    [[VGET_LANE23:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT25:%.*]] = insertelement <8 x bfloat> [[VECINIT20]], bfloat [[VGET_LANE23]], i32 5
-// CHECK-NEXT:    [[VGET_LANE28:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT30:%.*]] = insertelement <8 x bfloat> [[VECINIT25]], bfloat [[VGET_LANE28]], i32 6
-// CHECK-NEXT:    [[VGET_LANE33:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT35:%.*]] = insertelement <8 x bfloat> [[VECINIT30]], bfloat [[VGET_LANE33]], i32 7
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[VECINIT35]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[VECINIT35]])
-// CHECK-NEXT:    [[VBFMLALBQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMLALBQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <4 x bfloat> [[B:%.*]], <4 x bfloat> poison, <8 x i32> zeroinitializer
+// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]])
 // CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_F323_I]]
 //
 float32x4_t test_vbfmlalbq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b) {
@@ -184,27 +111,8 @@ float32x4_t test_vbfmlalbq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t
 
 // CHECK-LABEL: @test_vbfmlalbq_laneq_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[VGETQ_LANE:%.*]] = extractelement <8 x bfloat> [[B:%.*]], i32 3
-// CHECK-NEXT:    [[VECINIT:%.*]] = insertelement <8 x bfloat> poison, bfloat [[VGETQ_LANE]], i32 0
-// CHECK-NEXT:    [[VGETQ_LANE3:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT5:%.*]] = insertelement <8 x bfloat> [[VECINIT]], bfloat [[VGETQ_LANE3]], i32 1
-// CHECK-NEXT:    [[VGETQ_LANE8:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT10:%.*]] = insertelement <8 x bfloat> [[VECINIT5]], bfloat [[VGETQ_LANE8]], i32 2
-// CHECK-NEXT:    [[VGETQ_LANE13:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT15:%.*]] = insertelement <8 x bfloat> [[VECINIT10]], bfloat [[VGETQ_LANE13]], i32 3
-// CHECK-NEXT:    [[VGETQ_LANE18:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT20:%.*]] = insertelement <8 x bfloat> [[VECINIT15]], bfloat [[VGETQ_LANE18]], i32 4
-// CHECK-NEXT:    [[VGETQ_LANE23:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT25:%.*]] = insertelement <8 x bfloat> [[VECINIT20]], bfloat [[VGETQ_LANE23]], i32 5
-// CHECK-NEXT:    [[VGETQ_LANE28:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT30:%.*]] = insertelement <8 x bfloat> [[VECINIT25]], bfloat [[VGETQ_LANE28]], i32 6
-// CHECK-NEXT:    [[VGETQ_LANE33:%.*]] = extractelement <8 x bfloat> [[B]], i32 3
-// CHECK-NEXT:    [[VECINIT35:%.*]] = insertelement <8 x bfloat> [[VECINIT30]], bfloat [[VGETQ_LANE33]], i32 7
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[VECINIT35]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[VECINIT35]])
-// CHECK-NEXT:    [[VBFMLALBQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMLALBQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <8 x bfloat> [[B:%.*]], <8 x bfloat> poison, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
+// CHECK-NEXT:    [[VBFMLALBQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]])
 // CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_F323_I]]
 //
 float32x4_t test_vbfmlalbq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
@@ -213,27 +121,8 @@ float32x4_t test_vbfmlalbq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t
 
 // CHECK-LABEL: @test_vbfmlaltq_lane_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[VGET_LANE:%.*]] = extractelement <4 x bfloat> [[B:%.*]], i32 0
-// CHECK-NEXT:    [[VECINIT:%.*]] = insertelement <8 x bfloat> poison, bfloat [[VGET_LANE]], i32 0
-// CHECK-NEXT:    [[VGET_LANE3:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT5:%.*]] = insertelement <8 x bfloat> [[VECINIT]], bfloat [[VGET_LANE3]], i32 1
-// CHECK-NEXT:    [[VGET_LANE8:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT10:%.*]] = insertelement <8 x bfloat> [[VECINIT5]], bfloat [[VGET_LANE8]], i32 2
-// CHECK-NEXT:    [[VGET_LANE13:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT15:%.*]] = insertelement <8 x bfloat> [[VECINIT10]], bfloat [[VGET_LANE13]], i32 3
-// CHECK-NEXT:    [[VGET_LANE18:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT20:%.*]] = insertelement <8 x bfloat> [[VECINIT15]], bfloat [[VGET_LANE18]], i32 4
-// CHECK-NEXT:    [[VGET_LANE23:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT25:%.*]] = insertelement <8 x bfloat> [[VECINIT20]], bfloat [[VGET_LANE23]], i32 5
-// CHECK-NEXT:    [[VGET_LANE28:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT30:%.*]] = insertelement <8 x bfloat> [[VECINIT25]], bfloat [[VGET_LANE28]], i32 6
-// CHECK-NEXT:    [[VGET_LANE33:%.*]] = extractelement <4 x bfloat> [[B]], i32 0
-// CHECK-NEXT:    [[VECINIT35:%.*]] = insertelement <8 x bfloat> [[VECINIT30]], bfloat [[VGET_LANE33]], i32 7
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[R:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x bfloat> [[A:%.*]] to <16 x i8>
-// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x bfloat> [[VECINIT35]] to <16 x i8>
-// CHECK-NEXT:    [[VBFMLALTQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R]], <8 x bfloat> [[A]], <8 x bfloat> [[VECINIT35]])
-// CHECK-NEXT:    [[VBFMLALTQ_F324_I:%.*]] = bitcast <4 x float> [[VBFMLALTQ_F323_I]] to <16 x i8>
+// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <4 x bfloat> [[B:%.*]], <4 x bfloat> poison, <8 x i32> zeroinitializer
+// CHECK-NEXT:    [[VBFMLALTQ_F323_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]])
 // CHECK-NEXT:   ...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/121801


More information about the llvm-commits mailing list