[AArch64] Improve lowering of insert_vector_elt with 0.0 consts.

When moving +0.0 into a float vector, we can use to vi*gpr variants of
INS.

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D90176

diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index c390473..2691eaf 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -5177,6 +5177,16 @@ def : Pat<(v4f16 (vector_insert (v4f16 V64:$Rn),
               (i64 0)),
             dsub)>;
 
+def : Pat<(vector_insert (v8f16 v8f16:$Rn), (f16 fpimm0),
+            (i64 VectorIndexH:$imm)),
+          (INSvi16gpr V128:$Rn, VectorIndexH:$imm, WZR)>;
+def : Pat<(vector_insert v4f32:$Rn, (f32 fpimm0),
+            (i64 VectorIndexS:$imm)),
+          (INSvi32gpr V128:$Rn, VectorIndexS:$imm, WZR)>;
+def : Pat<(vector_insert v2f64:$Rn, (f64 fpimm0),
+            (i64 VectorIndexD:$imm)),
+          (INSvi64gpr V128:$Rn, VectorIndexS:$imm, XZR)>;
+
 def : Pat<(v8f16 (vector_insert (v8f16 V128:$Rn),
             (f16 FPR16:$Rm), (i64 VectorIndexH:$imm))),
           (INSvi16lane

diff --git a/llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll b/llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll
index 0ddb87b..afefe77 100644 (file)
--- a/llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=arm64-eabi -mcpu=generic -aarch64-neon-syntax=apple | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-eabi -mcpu=generic -aarch64-neon-syntax=apple -mattr="+fullfp16" | FileCheck %s
 
 define void @test0f(float* nocapture %x, float %a) #0 {
 ; CHECK-LABEL: test0f:
@@ -109,10 +109,8 @@ define <8 x half> @test_insert_v8f16_insert_1(half %a) {
 ; CHECK-LABEL: test_insert_v8f16_insert_1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $h0 killed $h0 def $q0
-; CHECK-NEXT:    adrp x8, .LCPI6_0
 ; CHECK-NEXT:    dup.8h v0, v0[0]
-; CHECK-NEXT:    add x8, x8, :lo12:.LCPI6_0
-; CHECK-NEXT:    ld1.h { v0 }[7], [x8]
+; CHECK-NEXT:    mov.h v0[7], wzr
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <8 x half> <half undef, half undef, half undef, half undef, half undef, half undef, half undef, half 0.0>, half %a, i32 0
   %v.1 = insertelement <8 x half> %v.0, half %a, i32 1
@@ -217,9 +215,8 @@ define <4 x float> @test_insert_3_f32_undef_zero_vector(float %a) {
 ; CHECK-LABEL: test_insert_3_f32_undef_zero_vector:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
-; CHECK-NEXT:    fmov s1, wzr
 ; CHECK-NEXT:    dup.4s v0, v0[0]
-; CHECK-NEXT:    mov.s v0[3], v1[0]
+; CHECK-NEXT:    mov.s v0[3], wzr
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <4 x float> <float undef, float undef, float undef, float 0.000000e+00>, float %a, i32 0
   %v.1 = insertelement <4 x float> %v.0, float %a, i32 1
@@ -277,6 +274,7 @@ define <4 x float> @test_insert_2_f32_var(float %a, <4 x float> %b) {
   %v.1 = insertelement <4 x float> %v.0, float %a, i32 2
   ret <4 x float> %v.1
 }
+
 define <8 x i16> @test_insert_v8i16_i16_zero(<8 x i16> %a) {
 ; CHECK-LABEL: test_insert_v8i16_i16_zero:
 ; CHECK:       // %bb.0:
@@ -290,10 +288,8 @@ define <8 x i16> @test_insert_v8i16_i16_zero(<8 x i16> %a) {
 define <4 x half> @test_insert_v4f16_f16_zero(<4 x half> %a) {
 ; CHECK-LABEL: test_insert_v4f16_f16_zero:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    adrp x8, .LCPI19_0
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    add x8, x8, :lo12:.LCPI19_0
-; CHECK-NEXT:    ld1.h { v0 }[0], [x8]
+; CHECK-NEXT:    mov.h v0[0], wzr
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <4 x half> %a, half 0.000000e+00, i32 0
@@ -303,9 +299,7 @@ define <4 x half> @test_insert_v4f16_f16_zero(<4 x half> %a) {
 define <8 x half> @test_insert_v8f16_f16_zero(<8 x half> %a) {
 ; CHECK-LABEL: test_insert_v8f16_f16_zero:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    adrp x8, .LCPI20_0
-; CHECK-NEXT:    add x8, x8, :lo12:.LCPI20_0
-; CHECK-NEXT:    ld1.h { v0 }[6], [x8]
+; CHECK-NEXT:    mov.h v0[6], wzr
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <8 x half> %a, half 0.000000e+00, i32 6
   ret <8 x half> %v.0
@@ -315,8 +309,7 @@ define <2 x float> @test_insert_v2f32_f32_zero(<2 x float> %a) {
 ; CHECK-LABEL: test_insert_v2f32_f32_zero:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    fmov s1, wzr
-; CHECK-NEXT:    mov.s v0[0], v1[0]
+; CHECK-NEXT:    mov.s v0[0], wzr
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <2 x float> %a, float 0.000000e+00, i32 0
@@ -326,8 +319,7 @@ define <2 x float> @test_insert_v2f32_f32_zero(<2 x float> %a) {
 define <4 x float> @test_insert_v4f32_f32_zero(<4 x float> %a) {
 ; CHECK-LABEL: test_insert_v4f32_f32_zero:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov s1, wzr
-; CHECK-NEXT:    mov.s v0[3], v1[0]
+; CHECK-NEXT:    mov.s v0[3], wzr
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <4 x float> %a, float 0.000000e+00, i32 3
   ret <4 x float> %v.0
@@ -336,8 +328,7 @@ define <4 x float> @test_insert_v4f32_f32_zero(<4 x float> %a) {
 define <2 x double> @test_insert_v2f64_f64_zero(<2 x double> %a) {
 ; CHECK-LABEL: test_insert_v2f64_f64_zero:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov d1, xzr
-; CHECK-NEXT:    mov.d v0[1], v1[0]
+; CHECK-NEXT:    mov.d v0[1], xzr
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <2 x double> %a, double 0.000000e+00, i32 1
   ret <2 x double> %v.0

diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
index e098c08..950995f 100644 (file)
--- a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
+++ b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
@@ -47,8 +47,7 @@ define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
 define float @test_v3f32(<3 x float> %a) nounwind {
 ; CHECK-LABEL: test_v3f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov s1, wzr
-; CHECK-NEXT:    mov v0.s[3], v1.s[0]
+; CHECK-NEXT:    mov v0.s[3], wzr
 ; CHECK-NEXT:    ext v1.16b, v0.16b, v0.16b, #8
 ; CHECK-NEXT:    fadd v0.2s, v0.2s, v1.2s
 ; CHECK-NEXT:    faddp s0, v0.2s