[ISel] Replace expensive mov from wzr by two moves via fpr

Author: juliannagele

llvm/lib/Target/AArch64/AArch64InstrInfo.td

@@ -7356,16 +7356,10 @@ def : Pat<(v4f16 (vector_insert (v4f16 V64:$Rn),
               (i64 0)),
             dsub)>;
 
-def : Pat<(vector_insert (v8f16 V128:$Rn), (f16 fpimm0), (i64 VectorIndexH:$imm)),
-          (INSvi16gpr V128:$Rn, VectorIndexH:$imm, WZR)>;
 def : Pat<(vector_insert (v4f16 V64:$Rn), (f16 fpimm0), (i64 VectorIndexH:$imm)),
           (EXTRACT_SUBREG (INSvi16gpr (v8f16 (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), V64:$Rn, dsub)), VectorIndexH:$imm, WZR), dsub)>;
-def : Pat<(vector_insert (v4f32 V128:$Rn), (f32 fpimm0), (i64 VectorIndexS:$imm)),
-          (INSvi32gpr V128:$Rn, VectorIndexS:$imm, WZR)>;
 def : Pat<(vector_insert (v2f32 V64:$Rn), (f32 fpimm0), (i64 VectorIndexS:$imm)),
           (EXTRACT_SUBREG (INSvi32gpr (v4f32 (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), V64:$Rn, dsub)), VectorIndexS:$imm, WZR), dsub)>;
-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:$imm))),
@@ -8035,6 +8029,18 @@ def MOVIv2d_ns   : SIMDModifiedImmVectorNoShift<1, 1, 0, 0b1110, V128,
                                                 "movi", ".2d",
                    [(set (v2i64 V128:$Rd), (AArch64movi_edit imm0_255:$imm8))]>;
 
+def : Pat<(vector_insert (v8f16 V128:$Rn), (f16 fpimm0), (i64 VectorIndexH:$imm)),
+          (INSvi16lane V128:$Rn, VectorIndexH:$imm,
+          (v8f16 (MOVIv2d_ns (i32 0))), (i64 0))>;
+
+def : Pat<(vector_insert (v4f32 V128:$Rn), (f32 fpimm0), (i64 VectorIndexS:$imm)),
+          (INSvi32lane V128:$Rn, VectorIndexS:$imm,
+          (v4f32 (MOVIv2d_ns (i32 0))), (i64 0))>;
+
+def : Pat<(vector_insert (v2f64 V128:$Rn), (f64 fpimm0), (i64 VectorIndexD:$imm)),
+          (INSvi64lane V128:$Rn, VectorIndexD:$imm,
+          (v2f64 (MOVIv2d_ns (i32 0))), (i64 0))>;
+
 let Predicates = [HasNEON] in {
 def : Pat<(v2i64 immAllZerosV), (MOVIv2d_ns (i32 0))>;
 def : Pat<(v4i32 immAllZerosV), (MOVIv2d_ns (i32 0))>;

llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll

@@ -172,8 +172,9 @@ 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:    movi.2d v1, #0000000000000000
 ; CHECK-NEXT:    dup.8h v0, v0[0]
-; CHECK-NEXT:    mov.h v0[7], wzr
+; CHECK-NEXT:    mov.h v0[7], v1[0]
 ; 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
@@ -278,8 +279,9 @@ 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:    movi.2d v1, #0000000000000000
 ; CHECK-NEXT:    dup.4s v0, v0[0]
-; CHECK-NEXT:    mov.s v0[3], wzr
+; CHECK-NEXT:    mov.s v0[3], v1[0]
 ; 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
@@ -362,7 +364,8 @@ 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:    mov.h v0[6], wzr
+; CHECK-NEXT:    movi.2d v1, #0000000000000000
+; CHECK-NEXT:    mov.h v0[6], v1[0]
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <8 x half> %a, half 0.000000e+00, i32 6
   ret <8 x half> %v.0
@@ -382,7 +385,8 @@ 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:    mov.s v0[3], wzr
+; CHECK-NEXT:    movi.2d v1, #0000000000000000
+; CHECK-NEXT:    mov.s v0[3], v1[0]
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <4 x float> %a, float 0.000000e+00, i32 3
   ret <4 x float> %v.0
@@ -391,7 +395,8 @@ 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:    mov.d v0[1], xzr
+; CHECK-NEXT:    movi.2d v1, #0000000000000000
+; CHECK-NEXT:    mov.d v0[1], v1[0]
 ; CHECK-NEXT:    ret
   %v.0 = insertelement <2 x double> %a, double 0.000000e+00, i32 1
   ret <2 x double> %v.0