[DAG] SimplifyDemandedVectorElts - add ISD::AVGCEILS/AVGCEILU/AVGFLOORS/AVGFLOORU nodes (#86284)

Fixes #84768

Author: aniplcc

llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -3524,6 +3524,10 @@ bool TargetLowering::SimplifyDemandedVectorElts(
     }
     [[fallthrough]];
   }
+  case ISD::AVGCEILS:
+  case ISD::AVGCEILU:
+  case ISD::AVGFLOORS:
+  case ISD::AVGFLOORU:
   case ISD::OR:
   case ISD::XOR:
   case ISD::SUB:

llvm/test/CodeGen/AArch64/hadd-combine.ll

@@ -903,6 +903,58 @@ define <8 x i16> @shadd_fixedwidth_v8i16(<8 x i16> %a0, <8 x i16> %a1)  {
   ret <8 x i16> %res
 }
 
+define <8 x i16> @shadd_demandedelts(<8 x i16> %a0, <8 x i16> %a1) {
+; CHECK-LABEL: shadd_demandedelts:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    shadd v0.8h, v0.8h, v1.8h
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    ret
+  %s0 = shufflevector <8 x i16> %a0, <8 x i16> undef, <8 x i32> zeroinitializer
+  %op = call <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16> %s0, <8 x i16> %a1)
+  %r0 = shufflevector <8 x i16> %op, <8 x i16> undef, <8 x i32> zeroinitializer
+  ret <8 x i16> %r0
+}
+
+define <8 x i16> @srhadd_demandedelts(<8 x i16> %a0, <8 x i16> %a1) {
+; CHECK-LABEL: srhadd_demandedelts:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    srhadd v0.8h, v0.8h, v1.8h
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    ret
+  %s0 = shufflevector <8 x i16> %a0, <8 x i16> undef, <8 x i32> zeroinitializer
+  %op = call <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16> %s0, <8 x i16> %a1)
+  %r0 = shufflevector <8 x i16> %op, <8 x i16> undef, <8 x i32> zeroinitializer
+  ret <8 x i16> %r0
+}
+
+define <8 x i16> @uhadd_demandedelts(<8 x i16> %a0, <8 x i16> %a1) {
+; CHECK-LABEL: uhadd_demandedelts:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    uhadd v0.8h, v0.8h, v1.8h
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    ret
+  %s0 = shufflevector <8 x i16> %a0, <8 x i16> undef, <8 x i32> zeroinitializer
+  %op = call <8 x i16> @llvm.aarch64.neon.uhadd.v8i16(<8 x i16> %s0, <8 x i16> %a1)
+  %r0 = shufflevector <8 x i16> %op, <8 x i16> undef, <8 x i32> zeroinitializer
+  ret <8 x i16> %r0
+}
+
+define <8 x i16> @urhadd_demandedelts(<8 x i16> %a0, <8 x i16> %a1) {
+; CHECK-LABEL: urhadd_demandedelts:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    urhadd v0.8h, v0.8h, v1.8h
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    ret
+  %s0 = shufflevector <8 x i16> %a0, <8 x i16> undef, <8 x i32> zeroinitializer
+  %op = call <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16> %s0, <8 x i16> %a1)
+  %r0 = shufflevector <8 x i16> %op, <8 x i16> undef, <8 x i32> zeroinitializer
+  ret <8 x i16> %r0
+}
+
 declare <8 x i8> @llvm.aarch64.neon.shadd.v8i8(<8 x i8>, <8 x i8>)
 declare <4 x i16> @llvm.aarch64.neon.shadd.v4i16(<4 x i16>, <4 x i16>)
 declare <2 x i32> @llvm.aarch64.neon.shadd.v2i32(<2 x i32>, <2 x i32>)
@@ -927,4 +979,4 @@ declare <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16>, <8 x i16>)
 declare <4 x i32> @llvm.aarch64.neon.srhadd.v4i32(<4 x i32>, <4 x i32>)
 declare <16 x i8> @llvm.aarch64.neon.urhadd.v16i8(<16 x i8>, <16 x i8>)
 declare <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16>, <8 x i16>)
-declare <4 x i32> @llvm.aarch64.neon.urhadd.v4i32(<4 x i32>, <4 x i32>)
+declare <4 x i32> @llvm.aarch64.neon.urhadd.v4i32(<4 x i32>, <4 x i32>)

llvm/test/CodeGen/X86/combine-pavg.ll

@@ -84,25 +84,22 @@ define <16 x i8> @combine_pavgw_knownbits(<8 x i16> %a0, <8 x i16> %a1, <8 x i16
 define <8 x i16> @combine_pavgw_demandedelts(<8 x i16> %a0, <8 x i16> %a1) {
 ; SSE-LABEL: combine_pavgw_demandedelts:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; SSE-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,8,9,8,9,12,13,12,13]
 ; SSE-NEXT:    pavgw %xmm1, %xmm0
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: combine_pavgw_demandedelts:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,8,9,8,9,12,13,12,13]
 ; AVX1-NEXT:    vpavgw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: combine_pavgw_demandedelts:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpbroadcastw %xmm1, %xmm1
-; AVX2-NEXT:    vpbroadcastw %xmm0, %xmm0
 ; AVX2-NEXT:    vpavgw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpbroadcastw %xmm0, %xmm0
 ; AVX2-NEXT:    retq
   %s0 = shufflevector <8 x i16> %a0, <8 x i16> poison, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   %avg = tail call <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16> %s0, <8 x i16> %a1)