[AArch64][SVE] Improve codegen for select nodes with fixed types

[bsmith]

Summary

Add support for lowering select nodes with fixed SVE types.

Additionally, move the existing fixed vselect tests to *-vselect.ll.

[paulwalker-arm]

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

7037

Is the call to LowerFixedLengthVectorSelectToSVE strictly necessary? I would have thought return DAG.getNode(ISD::VSELECT.... would be sufficient. We'll then iterate back into the custom lowering code, if required, to lower the VSELECT.

[bsmith]

• Remove superfluous call to LowerFixedLengthVectorSelectToSVE

[peterwaller-arm]

llvm/test/CodeGen/AArch64/sve-fixed-length-fp-select.ll

57

Sanity check: should this be [[PRES]] ?

[bsmith]

• Fixed incorrect parameter in tests

[paulwalker-arm]

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

7035

Is this safe? I know for larger than NEON vectors we'll truncate the mask and thus only care about the bottom bit, however, you're tests show that for NEON sized vectors bif is used and so every bit of the mask is meaningful. I believe this is because it expects the mask to be extended based on setBooleanVectorContents(ZeroOrNegativeOneBooleanContent). Which means a sign extend must be used here to maintain that requirement?

[bsmith]

• Use sext for predicate mask extension, rather than anyext

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

void AArch64TargetLowering::addTypeForFixedLengthSVE(MVT VT) {
   setOperationAction(ISD::FROUNDEVEN, VT, Custom);
   setOperationAction(ISD::FSQRT, VT, Custom);
   setOperationAction(ISD::FSUB, VT, Custom);
   setOperationAction(ISD::FTRUNC, VT, Custom);
   setOperationAction(ISD::LOAD, VT, Custom);
   setOperationAction(ISD::MUL, VT, Custom);
   setOperationAction(ISD::OR, VT, Custom);
   setOperationAction(ISD::SDIV, VT, Custom);
+  setOperationAction(ISD::SELECT, VT, Custom);
   setOperationAction(ISD::SETCC, VT, Custom);
   setOperationAction(ISD::SHL, VT, Custom);
   setOperationAction(ISD::SIGN_EXTEND, VT, Custom);
   setOperationAction(ISD::SIGN_EXTEND_INREG, VT, Custom);
   setOperationAction(ISD::SMAX, VT, Custom);
   setOperationAction(ISD::SMIN, VT, Custom);
   setOperationAction(ISD::SPLAT_VECTOR, VT, Custom);
   setOperationAction(ISD::SRA, VT, Custom);
SDValue AArch64TargetLowering::LowerSELECT(SDValue Op,
   EVT Ty = Op.getValueType();
   if (Ty.isScalableVector()) {
     SDValue TruncCC = DAG.getNode(ISD::TRUNCATE, DL, MVT::i1, CCVal);
     MVT PredVT = MVT::getVectorVT(MVT::i1, Ty.getVectorElementCount());
     SDValue SplatPred = DAG.getNode(ISD::SPLAT_VECTOR, DL, PredVT, TruncCC);
     return DAG.getNode(ISD::VSELECT, DL, Ty, SplatPred, TVal, FVal);
   }
 
+  if (useSVEForFixedLengthVectorVT(Ty)) {
+    // FIXME: Ideally this would be the same as above using i1 types, however
+    // for the moment we can't deal with fixed i1 vector types properly, so
+    // instead extend the predicate to a result type sized integer vector.
+    MVT SplatValVT = MVT::getIntegerVT(Ty.getScalarSizeInBits());
+    MVT PredVT = MVT::getVectorVT(SplatValVT, Ty.getVectorElementCount());
+    SDValue SplatVal = DAG.getSExtOrTrunc(CCVal, DL, SplatValVT);
+    SDValue SplatPred = DAG.getNode(ISD::SPLAT_VECTOR, DL, PredVT, SplatVal);
+    return DAG.getNode(ISD::VSELECT, DL, Ty, SplatPred, TVal, FVal);
+  }
+
   // Optimize {s|u}{add|sub|mul}.with.overflow feeding into a select
   // instruction.
   if (ISD::isOverflowIntrOpRes(CCVal)) {
     // Only lower legal XALUO ops.
     if (!DAG.getTargetLoweringInfo().isTypeLegal(CCVal->getValueType(0)))
       return SDValue();
 
     AArch64CC::CondCode OFCC;

llvm/test/CodeGen/AArch64/sve-fixed-length-fp-select.ll

 ; RUN: llc -aarch64-sve-vector-bits-min=2048 -asm-verbose=0 < %s | FileCheck %s -D#VBYTES=256 -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024,VBITS_GE_2048
 
 target triple = "aarch64-unknown-linux-gnu"
 
 ; Don't use SVE when its registers are no bigger than NEON.
 ; NO_SVE-NOT: ptrue
 
 ; Don't use SVE for 64-bit vectors.
-define <4 x half> @select_v4f16(<4 x half> %op1, <4 x half> %op2, <4 x i1> %mask) #0 {
-; CHECK-LABEL: select_v4f16:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <4 x i1> %mask, <4 x half> %op1, <4 x half> %op2
+define <4 x half> @select_v4f16(<4 x half> %op1, <4 x half> %op2, i1 %mask) #0 {
+; CHECK: select_v4f16:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.4h, w8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <4 x half> %op1, <4 x half> %op2
   ret <4 x half> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <8 x half> @select_v8f16(<8 x half> %op1, <8 x half> %op2, <8 x i1> %mask) #0 {
-; CHECK-LABEL: select_v8f16:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <8 x i1> %mask, <8 x half> %op1, <8 x half> %op2
+define <8 x half> @select_v8f16(<8 x half> %op1, <8 x half> %op2, i1 %mask) #0 {
+; CHECK: select_v8f16:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.8h, w8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <8 x half> %op1, <8 x half> %op2
   ret <8 x half> %sel
 }
 
-define void @select_v16f16(<16 x half>* %a, <16 x half>* %b, <16 x i1>* %c) #0 {
-; CHECK-LABEL: select_v16f16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; CHECK: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; CHECK-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x half>, <16 x half>* %a
-  %op2 = load <16 x half>, <16 x half>* %b
-  %sel = select <16 x i1> %mask, <16 x half> %op1, <16 x half> %op2
+define void @select_v16f16(<16 x half>* %a, <16 x half>* %b, i1 %mask) #0 {
+; CHECK: select_v16f16:
+; CHECK: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),16)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].h
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; CHECK-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <16 x half>, <16 x half>* %a
+  %op2 = load volatile <16 x half>, <16 x half>* %b
+  %sel = select i1 %mask, <16 x half> %op1, <16 x half> %op2
   store <16 x half> %sel, <16 x half>* %a
   ret void
 }
 
-define void @select_v32f16(<32 x half>* %a, <32 x half>* %b, <32 x i1>* %c) #0 {
-; CHECK-LABEL: select_v32f16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_512: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_512-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x half>, <32 x half>* %a
-  %op2 = load <32 x half>, <32 x half>* %b
-  %sel = select <32 x i1> %mask, <32 x half> %op1, <32 x half> %op2
+define void @select_v32f16(<32 x half>* %a, <32 x half>* %b, i1 %mask) #0 {
+; CHECK: select_v32f16:
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),32)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_512-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <32 x half>, <32 x half>* %a
+  %op2 = load volatile <32 x half>, <32 x half>* %b
+  %sel = select i1 %mask, <32 x half> %op1, <32 x half> %op2
   store <32 x half> %sel, <32 x half>* %a
   ret void
 }
 
-define void @select_v64f16(<64 x half>* %a, <64 x half>* %b, <64 x i1>* %c) #0 {
-; CHECK-LABEL: select_v64f16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),64)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_1024: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_1024-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <64 x i1>, <64 x i1>* %c
-  %op1 = load <64 x half>, <64 x half>* %a
-  %op2 = load <64 x half>, <64 x half>* %b
-  %sel = select <64 x i1> %mask, <64 x half> %op1, <64 x half> %op2
+define void @select_v64f16(<64 x half>* %a, <64 x half>* %b, i1 %mask) #0 {
+; CHECK: select_v64f16:
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),64)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_1024-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <64 x half>, <64 x half>* %a
+  %op2 = load volatile <64 x half>, <64 x half>* %b
+  %sel = select i1 %mask, <64 x half> %op1, <64 x half> %op2
   store <64 x half> %sel, <64 x half>* %a
   ret void
 }
 
-define void @select_v128f16(<128 x half>* %a, <128 x half>* %b, <128 x i1>* %c) #0 {
-; CHECK-LABEL: select_v128f16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),128)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_2048: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_2048-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <128 x i1>, <128 x i1>* %c
-  %op1 = load <128 x half>, <128 x half>* %a
-  %op2 = load <128 x half>, <128 x half>* %b
-  %sel = select <128 x i1> %mask, <128 x half> %op1, <128 x half> %op2
+define void @select_v128f16(<128 x half>* %a, <128 x half>* %b, i1 %mask) #0 {
+; CHECK: select_v128f16:
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),128)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_2048-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <128 x half>, <128 x half>* %a
+  %op2 = load volatile <128 x half>, <128 x half>* %b
+  %sel = select i1 %mask, <128 x half> %op1, <128 x half> %op2
   store <128 x half> %sel, <128 x half>* %a
   ret void
 }
 
 ; Don't use SVE for 64-bit vectors.
-define <2 x float> @select_v2f32(<2 x float> %op1, <2 x float> %op2, <2 x i1> %mask) #0 {
-; CHECK-LABEL: select_v2f32:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <2 x i1> %mask, <2 x float> %op1, <2 x float> %op2
+define <2 x float> @select_v2f32(<2 x float> %op1, <2 x float> %op2, i1 %mask) #0 {
+; CHECK: select_v2f32:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.2s, w8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <2 x float> %op1, <2 x float> %op2
   ret <2 x float> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <4 x float> @select_v4f32(<4 x float> %op1, <4 x float> %op2, <4 x i1> %mask) #0 {
-; CHECK-LABEL: select_v4f32:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <4 x i1> %mask, <4 x float> %op1, <4 x float> %op2
+define <4 x float> @select_v4f32(<4 x float> %op1, <4 x float> %op2, i1 %mask) #0 {
+; CHECK: select_v4f32:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.4s, w8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <4 x float> %op1, <4 x float> %op2
   ret <4 x float> %sel
 }
 
-define void @select_v8f32(<8 x float>* %a, <8 x float>* %b, <8 x i1>* %c) #0 {
-; CHECK-LABEL: select_v8f32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),8)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; CHECK: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; CHECK-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <8 x i1>, <8 x i1>* %c
-  %op1 = load <8 x float>, <8 x float>* %a
-  %op2 = load <8 x float>, <8 x float>* %b
-  %sel = select <8 x i1> %mask, <8 x float> %op1, <8 x float> %op2
+define void @select_v8f32(<8 x float>* %a, <8 x float>* %b, i1 %mask) #0 {
+; CHECK: select_v8f32:
+; CHECK: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),8)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].s
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; CHECK-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <8 x float>, <8 x float>* %a
+  %op2 = load volatile <8 x float>, <8 x float>* %b
+  %sel = select i1 %mask, <8 x float> %op1, <8 x float> %op2
   store <8 x float> %sel, <8 x float>* %a
   ret void
 }
 
-define void @select_v16f32(<16 x float>* %a, <16 x float>* %b, <16 x i1>* %c) #0 {
-; CHECK-LABEL: select_v16f32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_512: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_512-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x float>, <16 x float>* %a
-  %op2 = load <16 x float>, <16 x float>* %b
-  %sel = select <16 x i1> %mask, <16 x float> %op1, <16 x float> %op2
+define void @select_v16f32(<16 x float>* %a, <16 x float>* %b, i1 %mask) #0 {
+; CHECK: select_v16f32:
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),16)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_512-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <16 x float>, <16 x float>* %a
+  %op2 = load volatile <16 x float>, <16 x float>* %b
+  %sel = select i1 %mask, <16 x float> %op1, <16 x float> %op2
   store <16 x float> %sel, <16 x float>* %a
   ret void
 }
 
-define void @select_v32f32(<32 x float>* %a, <32 x float>* %b, <32 x i1>* %c) #0 {
-; CHECK-LABEL: select_v32f32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_1024: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_1024-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x float>, <32 x float>* %a
-  %op2 = load <32 x float>, <32 x float>* %b
-  %sel = select <32 x i1> %mask, <32 x float> %op1, <32 x float> %op2
+define void @select_v32f32(<32 x float>* %a, <32 x float>* %b, i1 %mask) #0 {
+; CHECK: select_v32f32:
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),32)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_1024-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <32 x float>, <32 x float>* %a
+  %op2 = load volatile <32 x float>, <32 x float>* %b
+  %sel = select i1 %mask, <32 x float> %op1, <32 x float> %op2
   store <32 x float> %sel, <32 x float>* %a
   ret void
 }
 
-define void @select_v64f32(<64 x float>* %a, <64 x float>* %b, <64 x i1>* %c) #0 {
-; CHECK-LABEL: select_v64f32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),64)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_2048: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_2048-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <64 x i1>, <64 x i1>* %c
-  %op1 = load <64 x float>, <64 x float>* %a
-  %op2 = load <64 x float>, <64 x float>* %b
-  %sel = select <64 x i1> %mask, <64 x float> %op1, <64 x float> %op2
+define void @select_v64f32(<64 x float>* %a, <64 x float>* %b, i1 %mask) #0 {
+; CHECK: select_v64f32:
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),64)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_2048-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <64 x float>, <64 x float>* %a
+  %op2 = load volatile <64 x float>, <64 x float>* %b
+  %sel = select i1 %mask, <64 x float> %op1, <64 x float> %op2
   store <64 x float> %sel, <64 x float>* %a
   ret void
 }
 
 ; Don't use SVE for 64-bit vectors.
-define <1 x double> @select_v1f64(<1 x double> %op1, <1 x double> %op2, <1 x i1> %mask) #0 {
-; CHECK-LABEL: select_v1f64:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <1 x i1> %mask, <1 x double> %op1, <1 x double> %op2
+define <1 x double> @select_v1f64(<1 x double> %op1, <1 x double> %op2, i1 %mask) #0 {
+; CHECK: select_v1f64:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm x8, ne
+; CHECK-NEXT: fmov d2, x8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <1 x double> %op1, <1 x double> %op2
   ret <1 x double> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <2 x double> @select_v2f64(<2 x double> %op1, <2 x double> %op2, <2 x i1> %mask) #0 {
-; CHECK-LABEL: select_v2f64:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <2 x i1> %mask, <2 x double> %op1, <2 x double> %op2
+define <2 x double> @select_v2f64(<2 x double> %op1, <2 x double> %op2, i1 %mask) #0 {
+; CHECK: select_v2f64:
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm x8, ne
+; CHECK-NEXT: dup v2.2d, x8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <2 x double> %op1, <2 x double> %op2
   ret <2 x double> %sel
 }
 
-define void @select_v4f64(<4 x double>* %a, <4 x double>* %b, <4 x i1>* %c) #0 {
-; CHECK-LABEL: select_v4f64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),4)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; CHECK: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; CHECK-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <4 x i1>, <4 x i1>* %c
-  %op1 = load <4 x double>, <4 x double>* %a
-  %op2 = load <4 x double>, <4 x double>* %b
-  %sel = select <4 x i1> %mask, <4 x double> %op1, <4 x double> %op2
+define void @select_v4f64(<4 x double>* %a, <4 x double>* %b, i1 %mask) #0 {
+; CHECK: select_v4f64:
+; CHECK: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),4)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].d
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; CHECK-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <4 x double>, <4 x double>* %a
+  %op2 = load volatile <4 x double>, <4 x double>* %b
+  %sel = select i1 %mask, <4 x double> %op1, <4 x double> %op2
   store <4 x double> %sel, <4 x double>* %a
   ret void
 }
 
-define void @select_v8f64(<8 x double>* %a, <8 x double>* %b, <8 x i1>* %c) #0 {
-; CHECK-LABEL: select_v8f64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),8)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_512: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_512-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <8 x i1>, <8 x i1>* %c
-  %op1 = load <8 x double>, <8 x double>* %a
-  %op2 = load <8 x double>, <8 x double>* %b
-  %sel = select <8 x i1> %mask, <8 x double> %op1, <8 x double> %op2
+define void @select_v8f64(<8 x double>* %a, <8 x double>* %b, i1 %mask) #0 {
+; CHECK: select_v8f64:
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),8)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_512-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <8 x double>, <8 x double>* %a
+  %op2 = load volatile <8 x double>, <8 x double>* %b
+  %sel = select i1 %mask, <8 x double> %op1, <8 x double> %op2
   store <8 x double> %sel, <8 x double>* %a
   ret void
 }
 
-define void @select_v16f64(<16 x double>* %a, <16 x double>* %b, <16 x i1>* %c) #0 {
-; CHECK-LABEL: select_v16f64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_1024: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_1024-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x double>, <16 x double>* %a
-  %op2 = load <16 x double>, <16 x double>* %b
-  %sel = select <16 x i1> %mask, <16 x double> %op1, <16 x double> %op2
+define void @select_v16f64(<16 x double>* %a, <16 x double>* %b, i1 %mask) #0 {
+; CHECK: select_v16f64:
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),16)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_1024-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <16 x double>, <16 x double>* %a
+  %op2 = load volatile <16 x double>, <16 x double>* %b
+  %sel = select i1 %mask, <16 x double> %op1, <16 x double> %op2
   store <16 x double> %sel, <16 x double>* %a
   ret void
 }
 
-define void @select_v32f64(<32 x double>* %a, <32 x double>* %b, <32 x i1>* %c) #0 {
-; CHECK-LABEL: select_v32f64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_2048: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_2048-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x double>, <32 x double>* %a
-  %op2 = load <32 x double>, <32 x double>* %b
-  %sel = select <32 x i1> %mask, <32 x double> %op1, <32 x double> %op2
+define void @select_v32f64(<32 x double>* %a, <32 x double>* %b, i1 %mask) #0 {
+; CHECK: select_v32f64:
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),32)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_2048-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <32 x double>, <32 x double>* %a
+  %op2 = load volatile <32 x double>, <32 x double>* %b
+  %sel = select i1 %mask, <32 x double> %op1, <32 x double> %op2
   store <32 x double> %sel, <32 x double>* %a
   ret void
 }
 
 attributes #0 = { "target-features"="+sve" }

llvm/test/CodeGen/AArch64/sve-fixed-length-int-select.ll

 ; RUN: llc -aarch64-sve-vector-bits-min=2048 -asm-verbose=0 < %s | FileCheck %s -D#VBYTES=256 -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024,VBITS_GE_2048
 
 target triple = "aarch64-unknown-linux-gnu"
 
 ; Don't use SVE when its registers are no bigger than NEON.
 ; NO_SVE-NOT: ptrue
 
 ; Don't use SVE for 64-bit vectors.
-define <8 x i8> @select_v8i8(<8 x i8> %op1, <8 x i8> %op2, <8 x i1> %mask) #0 {
+define <8 x i8> @select_v8i8(<8 x i8> %op1, <8 x i8> %op2, i1 %mask) #0 {
 ; CHECK: select_v8i8:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <8 x i1> %mask, <8 x i8> %op1, <8 x i8> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.8b, w8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <8 x i8> %op1, <8 x i8> %op2
   ret <8 x i8> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <16 x i8> @select_v16i8(<16 x i8> %op1, <16 x i8> %op2, <16 x i1> %mask) #0 {
+define <16 x i8> @select_v16i8(<16 x i8> %op1, <16 x i8> %op2, i1 %mask) #0 {
 ; CHECK: select_v16i8:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <16 x i1> %mask, <16 x i8> %op1, <16 x i8> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.16b, w8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <16 x i8> %op1, <16 x i8> %op2
   ret <16 x i8> %sel
 }
 
-define void @select_v32i8(<32 x i8>* %a, <32 x i8>* %b, <32 x i1>* %c) #0 {
+define void @select_v32i8(<32 x i8>* %a, <32 x i8>* %b, i1 %mask) #0 {
 ; CHECK: select_v32i8:
-; CHECK: ptrue [[PG:p[0-9]+]].b, vl[[#min(VBYTES,32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].b
-; CHECK: ld1b { [[MASK:z[0-9]+]].b }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].b, [[MASK]].b, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].b, [[PG1]]/z, [[AND]].b, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].b, [[COND]], [[OP1]].b, [[OP2]].b
-; CHECK-NEXT: st1b { [[RES]].b }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x i8>, <32 x i8>* %a
-  %op2 = load <32 x i8>, <32 x i8>* %b
-  %sel = select <32 x i1> %mask, <32 x i8> %op1, <32 x i8> %op2
+; CHECK: ptrue [[PG1:p[0-9]+]].b, vl[[#min(VBYTES,32)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].b, w[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].b, [[TMP1]].b, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].b
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].b, [[PG2]]/z, [[TMP2]].b, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].b, [[PRES]], [[OP1]].b, [[OP2]].b
+; CHECK-NEXT: st1b { [[RES]].b }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <32 x i8>, <32 x i8>* %a
+  %op2 = load volatile <32 x i8>, <32 x i8>* %b
+  %sel = select i1 %mask, <32 x i8> %op1, <32 x i8> %op2
   store <32 x i8> %sel, <32 x i8>* %a
   ret void
 }
 
-define void @select_v64i8(<64 x i8>* %a, <64 x i8>* %b, <64 x i1>* %c) #0 {
+define void @select_v64i8(<64 x i8>* %a, <64 x i8>* %b, i1 %mask) #0 {
 ; CHECK: select_v64i8:
-; CHECK: ptrue [[PG:p[0-9]+]].b, vl[[#min(VBYTES,64)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].b
-; VBITS_GE_512: ld1b { [[MASK:z[0-9]+]].b }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].b, [[MASK]].b, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].b, [[PG1]]/z, [[AND]].b, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].b, [[COND]], [[OP1]].b, [[OP2]].b
-; VBITS_GE_512-NEXT: st1b { [[RES]].b }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <64 x i1>, <64 x i1>* %c
-  %op1 = load <64 x i8>, <64 x i8>* %a
-  %op2 = load <64 x i8>, <64 x i8>* %b
-  %sel = select <64 x i1> %mask, <64 x i8> %op1, <64 x i8> %op2
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].b, vl[[#min(VBYTES,64)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].b, w[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].b, [[TMP1]].b, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].b
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].b, [[PG2]]/z, [[TMP2]].b, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].b, [[PRES]], [[OP1]].b, [[OP2]].b
+; VBITS_GE_512-NEXT: st1b { [[RES]].b }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <64 x i8>, <64 x i8>* %a
+  %op2 = load volatile <64 x i8>, <64 x i8>* %b
+  %sel = select i1 %mask, <64 x i8> %op1, <64 x i8> %op2
   store <64 x i8> %sel, <64 x i8>* %a
   ret void
 }
 
-define void @select_v128i8(<128 x i8>* %a, <128 x i8>* %b, <128 x i1>* %c) #0 {
+define void @select_v128i8(<128 x i8>* %a, <128 x i8>* %b, i1 %mask) #0 {
 ; CHECK: select_v128i8:
-; CHECK: ptrue [[PG:p[0-9]+]].b, vl[[#min(VBYTES,128)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].b
-; VBITS_GE_1024: ld1b { [[MASK:z[0-9]+]].b }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].b, [[MASK]].b, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].b, [[PG1]]/z, [[AND]].b, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].b, [[COND]], [[OP1]].b, [[OP2]].b
-; VBITS_GE_1024-NEXT: st1b { [[RES]].b }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <128 x i1>, <128 x i1>* %c
-  %op1 = load <128 x i8>, <128 x i8>* %a
-  %op2 = load <128 x i8>, <128 x i8>* %b
-  %sel = select <128 x i1> %mask, <128 x i8> %op1, <128 x i8> %op2
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].b, vl[[#min(VBYTES,128)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].b, w[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].b, [[TMP1]].b, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].b
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].b, [[PG2]]/z, [[TMP2]].b, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].b, [[PRES]], [[OP1]].b, [[OP2]].b
+; VBITS_GE_1024-NEXT: st1b { [[RES]].b }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <128 x i8>, <128 x i8>* %a
+  %op2 = load volatile <128 x i8>, <128 x i8>* %b
+  %sel = select i1 %mask, <128 x i8> %op1, <128 x i8> %op2
   store <128 x i8> %sel, <128 x i8>* %a
   ret void
 }
 
-define void @select_v256i8(<256 x i8>* %a, <256 x i8>* %b, <256 x i1>* %c) #0 {
+define void @select_v256i8(<256 x i8>* %a, <256 x i8>* %b, i1 %mask) #0 {
 ; CHECK: select_v256i8:
-; CHECK: ptrue [[PG:p[0-9]+]].b, vl[[#min(VBYTES,256)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].b
-; VBITS_GE_2048: ld1b { [[MASK:z[0-9]+]].b }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].b, [[MASK]].b, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].b, [[PG1]]/z, [[AND]].b, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].b, [[COND]], [[OP1]].b, [[OP2]].b
-; VBITS_GE_2048-NEXT: st1b { [[RES]].b }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <256 x i1>, <256 x i1>* %c
-  %op1 = load <256 x i8>, <256 x i8>* %a
-  %op2 = load <256 x i8>, <256 x i8>* %b
-  %sel = select <256 x i1> %mask, <256 x i8> %op1, <256 x i8> %op2
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].b, vl[[#min(VBYTES,256)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1b { [[OP1:z[0-9]+]].b }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1b { [[OP2:z[0-9]+]].b }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].b, w[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].b, [[TMP1]].b, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].b
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].b, [[PG2]]/z, [[TMP2]].b, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].b, [[PRES]], [[OP1]].b, [[OP2]].b
+; VBITS_GE_2048-NEXT: st1b { [[RES]].b }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <256 x i8>, <256 x i8>* %a
+  %op2 = load volatile <256 x i8>, <256 x i8>* %b
+  %sel = select i1 %mask, <256 x i8> %op1, <256 x i8> %op2
   store <256 x i8> %sel, <256 x i8>* %a
   ret void
 }
 
 ; Don't use SVE for 64-bit vectors.
-define <4 x i16> @select_v4i16(<4 x i16> %op1, <4 x i16> %op2, <4 x i1> %mask) #0 {
+define <4 x i16> @select_v4i16(<4 x i16> %op1, <4 x i16> %op2, i1 %mask) #0 {
 ; CHECK: select_v4i16:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <4 x i1> %mask, <4 x i16> %op1, <4 x i16> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.4h, w8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <4 x i16> %op1, <4 x i16> %op2
   ret <4 x i16> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <8 x i16> @select_v8i16(<8 x i16> %op1, <8 x i16> %op2, <8 x i1> %mask) #0 {
+define <8 x i16> @select_v8i16(<8 x i16> %op1, <8 x i16> %op2, i1 %mask) #0 {
 ; CHECK: select_v8i16:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <8 x i1> %mask, <8 x i16> %op1, <8 x i16> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.8h, w8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <8 x i16> %op1, <8 x i16> %op2
   ret <8 x i16> %sel
 }
 
-define void @select_v16i16(<16 x i16>* %a, <16 x i16>* %b, <16 x i1>* %c) #0 {
+define void @select_v16i16(<16 x i16>* %a, <16 x i16>* %b, i1 %mask) #0 {
 ; CHECK: select_v16i16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; CHECK: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; CHECK-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x i16>, <16 x i16>* %a
-  %op2 = load <16 x i16>, <16 x i16>* %b
-  %sel = select <16 x i1> %mask, <16 x i16> %op1, <16 x i16> %op2
+; CHECK: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),16)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].h
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; CHECK-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <16 x i16>, <16 x i16>* %a
+  %op2 = load volatile <16 x i16>, <16 x i16>* %b
+  %sel = select i1 %mask, <16 x i16> %op1, <16 x i16> %op2
   store <16 x i16> %sel, <16 x i16>* %a
   ret void
 }
 
-define void @select_v32i16(<32 x i16>* %a, <32 x i16>* %b, <32 x i1>* %c) #0 {
+define void @select_v32i16(<32 x i16>* %a, <32 x i16>* %b, i1 %mask) #0 {
 ; CHECK: select_v32i16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_512: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_512-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x i16>, <32 x i16>* %a
-  %op2 = load <32 x i16>, <32 x i16>* %b
-  %sel = select <32 x i1> %mask, <32 x i16> %op1, <32 x i16> %op2
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),32)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_512-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <32 x i16>, <32 x i16>* %a
+  %op2 = load volatile <32 x i16>, <32 x i16>* %b
+  %sel = select i1 %mask, <32 x i16> %op1, <32 x i16> %op2
   store <32 x i16> %sel, <32 x i16>* %a
   ret void
 }
 
-define void @select_v64i16(<64 x i16>* %a, <64 x i16>* %b, <64 x i1>* %c) #0 {
+define void @select_v64i16(<64 x i16>* %a, <64 x i16>* %b, i1 %mask) #0 {
 ; CHECK: select_v64i16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),64)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_1024: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_1024-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <64 x i1>, <64 x i1>* %c
-  %op1 = load <64 x i16>, <64 x i16>* %a
-  %op2 = load <64 x i16>, <64 x i16>* %b
-  %sel = select <64 x i1> %mask, <64 x i16> %op1, <64 x i16> %op2
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),64)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_1024-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <64 x i16>, <64 x i16>* %a
+  %op2 = load volatile <64 x i16>, <64 x i16>* %b
+  %sel = select i1 %mask, <64 x i16> %op1, <64 x i16> %op2
   store <64 x i16> %sel, <64 x i16>* %a
   ret void
 }
 
-define void @select_v128i16(<128 x i16>* %a, <128 x i16>* %b, <128 x i1>* %c) #0 {
+define void @select_v128i16(<128 x i16>* %a, <128 x i16>* %b, i1 %mask) #0 {
 ; CHECK: select_v128i16:
-; CHECK: ptrue [[PG:p[0-9]+]].h, vl[[#min(div(VBYTES,2),128)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].h
-; VBITS_GE_2048: ld1h { [[MASK:z[0-9]+]].h }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].h, [[MASK]].h, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].h, [[PG1]]/z, [[AND]].h, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].h, [[COND]], [[OP1]].h, [[OP2]].h
-; VBITS_GE_2048-NEXT: st1h { [[RES]].h }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <128 x i1>, <128 x i1>* %c
-  %op1 = load <128 x i16>, <128 x i16>* %a
-  %op2 = load <128 x i16>, <128 x i16>* %b
-  %sel = select <128 x i1> %mask, <128 x i16> %op1, <128 x i16> %op2
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].h, vl[[#min(div(VBYTES,2),128)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1h { [[OP1:z[0-9]+]].h }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1h { [[OP2:z[0-9]+]].h }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].h, w[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].h, [[TMP1]].h, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].h
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].h, [[PG2]]/z, [[TMP2]].h, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].h, [[PRES]], [[OP1]].h, [[OP2]].h
+; VBITS_GE_2048-NEXT: st1h { [[RES]].h }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <128 x i16>, <128 x i16>* %a
+  %op2 = load volatile <128 x i16>, <128 x i16>* %b
+  %sel = select i1 %mask, <128 x i16> %op1, <128 x i16> %op2
   store <128 x i16> %sel, <128 x i16>* %a
   ret void
 }
 
 ; Don't use SVE for 64-bit vectors.
-define <2 x i32> @select_v2i32(<2 x i32> %op1, <2 x i32> %op2, <2 x i1> %mask) #0 {
+define <2 x i32> @select_v2i32(<2 x i32> %op1, <2 x i32> %op2, i1 %mask) #0 {
 ; CHECK: select_v2i32:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <2 x i1> %mask, <2 x i32> %op1, <2 x i32> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.2s, w8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <2 x i32> %op1, <2 x i32> %op2
   ret <2 x i32> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <4 x i32> @select_v4i32(<4 x i32> %op1, <4 x i32> %op2, <4 x i1> %mask) #0 {
+define <4 x i32> @select_v4i32(<4 x i32> %op1, <4 x i32> %op2, i1 %mask) #0 {
 ; CHECK: select_v4i32:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <4 x i1> %mask, <4 x i32> %op1, <4 x i32> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm w8, ne
+; CHECK-NEXT: dup v2.4s, w8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <4 x i32> %op1, <4 x i32> %op2
   ret <4 x i32> %sel
 }
 
-define void @select_v8i32(<8 x i32>* %a, <8 x i32>* %b, <8 x i1>* %c) #0 {
+define void @select_v8i32(<8 x i32>* %a, <8 x i32>* %b, i1 %mask) #0 {
 ; CHECK: select_v8i32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),8)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; CHECK: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; CHECK-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <8 x i1>, <8 x i1>* %c
-  %op1 = load <8 x i32>, <8 x i32>* %a
-  %op2 = load <8 x i32>, <8 x i32>* %b
-  %sel = select <8 x i1> %mask, <8 x i32> %op1, <8 x i32> %op2
+; CHECK: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),8)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].s
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; CHECK-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <8 x i32>, <8 x i32>* %a
+  %op2 = load volatile <8 x i32>, <8 x i32>* %b
+  %sel = select i1 %mask, <8 x i32> %op1, <8 x i32> %op2
   store <8 x i32> %sel, <8 x i32>* %a
   ret void
 }
 
-define void @select_v16i32(<16 x i32>* %a, <16 x i32>* %b, <16 x i1>* %c) #0 {
+define void @select_v16i32(<16 x i32>* %a, <16 x i32>* %b, i1 %mask) #0 {
 ; CHECK: select_v16i32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_512: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_512-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x i32>, <16 x i32>* %a
-  %op2 = load <16 x i32>, <16 x i32>* %b
-  %sel = select <16 x i1> %mask, <16 x i32> %op1, <16 x i32> %op2
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),16)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_512-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <16 x i32>, <16 x i32>* %a
+  %op2 = load volatile <16 x i32>, <16 x i32>* %b
+  %sel = select i1 %mask, <16 x i32> %op1, <16 x i32> %op2
   store <16 x i32> %sel, <16 x i32>* %a
   ret void
 }
 
-define void @select_v32i32(<32 x i32>* %a, <32 x i32>* %b, <32 x i1>* %c) #0 {
+define void @select_v32i32(<32 x i32>* %a, <32 x i32>* %b, i1 %mask) #0 {
 ; CHECK: select_v32i32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_1024: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_1024-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x i32>, <32 x i32>* %a
-  %op2 = load <32 x i32>, <32 x i32>* %b
-  %sel = select <32 x i1> %mask, <32 x i32> %op1, <32 x i32> %op2
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),32)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_1024-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <32 x i32>, <32 x i32>* %a
+  %op2 = load volatile <32 x i32>, <32 x i32>* %b
+  %sel = select i1 %mask, <32 x i32> %op1, <32 x i32> %op2
   store <32 x i32> %sel, <32 x i32>* %a
   ret void
 }
 
-define void @select_v64i32(<64 x i32>* %a, <64 x i32>* %b, <64 x i1>* %c) #0 {
+define void @select_v64i32(<64 x i32>* %a, <64 x i32>* %b, i1 %mask) #0 {
 ; CHECK: select_v64i32:
-; CHECK: ptrue [[PG:p[0-9]+]].s, vl[[#min(div(VBYTES,4),64)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].s
-; VBITS_GE_2048: ld1w { [[MASK:z[0-9]+]].s }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].s, [[MASK]].s, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].s, [[PG1]]/z, [[AND]].s, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].s, [[COND]], [[OP1]].s, [[OP2]].s
-; VBITS_GE_2048-NEXT: st1w { [[RES]].s }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <64 x i1>, <64 x i1>* %c
-  %op1 = load <64 x i32>, <64 x i32>* %a
-  %op2 = load <64 x i32>, <64 x i32>* %b
-  %sel = select <64 x i1> %mask, <64 x i32> %op1, <64 x i32> %op2
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].s, vl[[#min(div(VBYTES,4),64)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1w { [[OP1:z[0-9]+]].s }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1w { [[OP2:z[0-9]+]].s }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].s, w[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].s, [[TMP1]].s, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].s
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].s, [[PG2]]/z, [[TMP2]].s, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].s, [[PRES]], [[OP1]].s, [[OP2]].s
+; VBITS_GE_2048-NEXT: st1w { [[RES]].s }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <64 x i32>, <64 x i32>* %a
+  %op2 = load volatile <64 x i32>, <64 x i32>* %b
+  %sel = select i1 %mask, <64 x i32> %op1, <64 x i32> %op2
   store <64 x i32> %sel, <64 x i32>* %a
   ret void
 }
 
 ; Don't use SVE for 64-bit vectors.
-define <1 x i64> @select_v1i64(<1 x i64> %op1, <1 x i64> %op2, <1 x i1> %mask) #0 {
+define <1 x i64> @select_v1i64(<1 x i64> %op1, <1 x i64> %op2, i1 %mask) #0 {
 ; CHECK: select_v1i64:
-; CHECK: bif v0.8b, v1.8b, v2.8b
-; CHECK: ret
-  %sel = select <1 x i1> %mask, <1 x i64> %op1, <1 x i64> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm x8, ne
+; CHECK-NEXT: fmov d2, x8
+; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <1 x i64> %op1, <1 x i64> %op2
   ret <1 x i64> %sel
 }
 
 ; Don't use SVE for 128-bit vectors.
-define <2 x i64> @select_v2i64(<2 x i64> %op1, <2 x i64> %op2, <2 x i1> %mask) #0 {
+define <2 x i64> @select_v2i64(<2 x i64> %op1, <2 x i64> %op2, i1 %mask) #0 {
 ; CHECK: select_v2i64:
-; CHECK: bif v0.16b, v1.16b, v2.16b
-; CHECK: ret
-  %sel = select <2 x i1> %mask, <2 x i64> %op1, <2 x i64> %op2
+; CHECK: tst w0, #0x1
+; CHECK-NEXT: csetm x8, ne
+; CHECK-NEXT: dup v2.2d, x8
+; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
+; CHECK-NEXT: ret
+  %sel = select i1 %mask, <2 x i64> %op1, <2 x i64> %op2
   ret <2 x i64> %sel
 }
 
-define void @select_v4i64(<4 x i64>* %a, <4 x i64>* %b, <4 x i1>* %c) #0 {
+define void @select_v4i64(<4 x i64>* %a, <4 x i64>* %b, i1 %mask) #0 {
 ; CHECK: select_v4i64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),4)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; CHECK: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; CHECK-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; CHECK-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; CHECK-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; CHECK-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; CHECK-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; CHECK-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; CHECK: ret
-  %mask = load <4 x i1>, <4 x i1>* %c
-  %op1 = load <4 x i64>, <4 x i64>* %a
-  %op2 = load <4 x i64>, <4 x i64>* %b
-  %sel = select <4 x i1> %mask, <4 x i64> %op1, <4 x i64> %op2
+; CHECK: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),4)]]
+; CHECK-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; CHECK-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; CHECK-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; CHECK-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; CHECK-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; CHECK-NEXT: ptrue [[PG2:p[0-9]+]].d
+; CHECK-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; CHECK-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; CHECK-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; CHECK-NEXT: ret
+  %op1 = load volatile <4 x i64>, <4 x i64>* %a
+  %op2 = load volatile <4 x i64>, <4 x i64>* %b
+  %sel = select i1 %mask, <4 x i64> %op1, <4 x i64> %op2
   store <4 x i64> %sel, <4 x i64>* %a
   ret void
 }
 
-define void @select_v8i64(<8 x i64>* %a, <8 x i64>* %b, <8 x i1>* %c) #0 {
+define void @select_v8i64(<8 x i64>* %a, <8 x i64>* %b, i1 %mask) #0 {
 ; CHECK: select_v8i64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),8)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_512: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_512-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_512-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_512-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_512-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_512-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_512: ret
-  %mask = load <8 x i1>, <8 x i1>* %c
-  %op1 = load <8 x i64>, <8 x i64>* %a
-  %op2 = load <8 x i64>, <8 x i64>* %b
-  %sel = select <8 x i1> %mask, <8 x i64> %op1, <8 x i64> %op2
+; VBITS_GE_512: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),8)]]
+; VBITS_GE_512-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_512-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_512-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_512-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_512-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_512-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_512-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_512-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_512-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_512-NEXT: ret
+  %op1 = load volatile <8 x i64>, <8 x i64>* %a
+  %op2 = load volatile <8 x i64>, <8 x i64>* %b
+  %sel = select i1 %mask, <8 x i64> %op1, <8 x i64> %op2
   store <8 x i64> %sel, <8 x i64>* %a
   ret void
 }
 
-define void @select_v16i64(<16 x i64>* %a, <16 x i64>* %b, <16 x i1>* %c) #0 {
+define void @select_v16i64(<16 x i64>* %a, <16 x i64>* %b, i1 %mask) #0 {
 ; CHECK: select_v16i64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),16)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_1024: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_1024-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_1024-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_1024-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_1024-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_1024-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_1024: ret
-  %mask = load <16 x i1>, <16 x i1>* %c
-  %op1 = load <16 x i64>, <16 x i64>* %a
-  %op2 = load <16 x i64>, <16 x i64>* %b
-  %sel = select <16 x i1> %mask, <16 x i64> %op1, <16 x i64> %op2
+; VBITS_GE_1024: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),16)]]
+; VBITS_GE_1024-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_1024-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_1024-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_1024-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_1024-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_1024-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_1024-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_1024-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_1024-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_1024-NEXT: ret
+  %op1 = load volatile <16 x i64>, <16 x i64>* %a
+  %op2 = load volatile <16 x i64>, <16 x i64>* %b
+  %sel = select i1 %mask, <16 x i64> %op1, <16 x i64> %op2
   store <16 x i64> %sel, <16 x i64>* %a
   ret void
 }
 
-define void @select_v32i64(<32 x i64>* %a, <32 x i64>* %b, <32 x i1>* %c) #0 {
+define void @select_v32i64(<32 x i64>* %a, <32 x i64>* %b, i1 %mask) #0 {
 ; CHECK: select_v32i64:
-; CHECK: ptrue [[PG:p[0-9]+]].d, vl[[#min(div(VBYTES,8),32)]]
-; CHECK: ptrue [[PG1:p[0-9]+]].d
-; VBITS_GE_2048: ld1d { [[MASK:z[0-9]+]].d }, [[PG]]/z, [x9]
-; VBITS_GE_2048-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG]]/z, [x0]
-; VBITS_GE_2048-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG]]/z, [x1]
-; VBITS_GE_2048-NEXT: and [[AND:z[0-9]+]].d, [[MASK]].d, #0x1
-; VBITS_GE_2048-NEXT: cmpne [[COND:p[0-9]+]].d, [[PG1]]/z, [[AND]].d, #0
-; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].d, [[COND]], [[OP1]].d, [[OP2]].d
-; VBITS_GE_2048-NEXT: st1d { [[RES]].d }, [[PG]], [x0]
-; VBITS_GE_2048: ret
-  %mask = load <32 x i1>, <32 x i1>* %c
-  %op1 = load <32 x i64>, <32 x i64>* %a
-  %op2 = load <32 x i64>, <32 x i64>* %b
-  %sel = select <32 x i1> %mask, <32 x i64> %op1, <32 x i64> %op2
+; VBITS_GE_2048: ptrue [[PG1:p[0-9]+]].d, vl[[#min(div(VBYTES,8),32)]]
+; VBITS_GE_2048-NEXT: and w[[AND:[0-9]+]], w2, #0x1
+; VBITS_GE_2048-NEXT: ld1d { [[OP1:z[0-9]+]].d }, [[PG1]]/z, [x0]
+; VBITS_GE_2048-NEXT: ld1d { [[OP2:z[0-9]+]].d }, [[PG1]]/z, [x1]
+; VBITS_GE_2048-NEXT: mov [[TMP1:z[0-9]+]].d, x[[AND]]
+; VBITS_GE_2048-NEXT: and [[TMP2:z[0-9]+]].d, [[TMP1]].d, #0x1
+; VBITS_GE_2048-NEXT: ptrue [[PG2:p[0-9]+]].d
+; VBITS_GE_2048-NEXT: cmpne [[PRES:p[0-9]+]].d, [[PG2]]/z, [[TMP2]].d, #0
+; VBITS_GE_2048-NEXT: sel [[RES:z[0-9]+]].d, [[PRES]], [[OP1]].d, [[OP2]].d
+; VBITS_GE_2048-NEXT: st1d { [[RES]].d }, [[PG1]], [x0]
+; VBITS_GE_2048-NEXT: ret
+  %op1 = load volatile <32 x i64>, <32 x i64>* %a
+  %op2 = load volatile <32 x i64>, <32 x i64>* %b
+  %sel = select i1 %mask, <32 x i64> %op1, <32 x i64> %op2
   store <32 x i64> %sel, <32 x i64>* %a
   ret void
 }
 
 attributes #0 = { "target-features"="+sve" }