[ARM] Combine sub 0, csinc X, Y, CC -> csinv -X, Y, CC

[dmgreen]

Summary

Combine sub 0, csinc X, Y, CC to csinv -X, Y, CC providing that the negation of X is cheap, currently just handling constants. This comes up during the splat of an i1 to a predicate, where we now generate csetm, as opposed to cset; rsb.

[malharJ]

I don't have much context, but I'm just wondering if a similar optimization for csneg might be useful ?
sub(0, csneg( X, Y, <cc>) ) = csinv -X, -Y-1, <cc>

llvm/lib/Target/ARM/ARMISelLowering.cpp

12736

Do you think this would be better worded as:
Fold (sub 0, ( ARMcsinc X, Y, CC) ) -> (ARMcsinv -X, Y, CC)

llvm/test/CodeGen/Thumb2/mve-vmovimm.ll

523

Is the new assembly equivalent to the old one: ie, does this set the condition codes ?

[dmgreen]

In D99940#2671380, @malharJ wrote:

I don't have much context, but I'm just wondering if a similar optimization for csneg might be useful ?
sub(0, csneg( X, Y, <cc>) ) = csinv -X, -Y-1, <cc>

I'm not sure if that will ever come up. LLVM will usually canonicalize to something that is already simpler. The pattern for this patch comes up in splatting i1's to predicates, which is where it is useful.

llvm/test/CodeGen/Thumb2/mve-vmovimm.ll

523

The condition code isn't used though.

[dmgreen]

Add some brackets to a comment, to help readability.

[malharJ]

Thanks. LGTM

llvm/lib/Target/ARM/ARMISelLowering.cpp

static SDValue PerformADDCombine(SDNode *N,
   // First try with the default operand order.
   if (SDValue Result = PerformADDCombineWithOperands(N, N0, N1, DCI, Subtarget))
     return Result;
 
   // If that didn't work, try again with the operands commuted.
   return PerformADDCombineWithOperands(N, N1, N0, DCI, Subtarget);
 }
 
+// Combine (sub 0, (csinc X, Y, CC)) -> (csinv -X, Y, CC)
+//   providing -X is as cheap as X (currently, just a constant).
+static SDValue PerformSubCSINCCombine(SDNode *N,
+                                      TargetLowering::DAGCombinerInfo &DCI) {
+  if (N->getValueType(0) != MVT::i32 || !isNullConstant(N->getOperand(0)))
+    return SDValue();
+  SDValue CSINC = N->getOperand(1);
+  if (CSINC.getOpcode() != ARMISD::CSINC)
+    return SDValue();
+
+  ConstantSDNode *X = dyn_cast<ConstantSDNode>(CSINC.getOperand(0));
+  if (!X)
+    return SDValue();
+
+  return DCI.DAG.getNode(ARMISD::CSINV, SDLoc(N), MVT::i32,
+                         DCI.DAG.getNode(ISD::SUB, SDLoc(N), MVT::i32,
+                                         N->getOperand(0), CSINC.getOperand(0)),
+                         CSINC.getOperand(1), CSINC.getOperand(2),
+                         CSINC.getOperand(3));
+}
+
 /// PerformSUBCombine - Target-specific dag combine xforms for ISD::SUB.
 ///
 static SDValue PerformSUBCombine(SDNode *N,
                                  TargetLowering::DAGCombinerInfo &DCI,
                                  const ARMSubtarget *Subtarget) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);
 
   // fold (sub x, (select cc, 0, c)) -> (select cc, x, (sub, x, c))
   if (N1.getNode()->hasOneUse())
     if (SDValue Result = combineSelectAndUse(N, N1, N0, DCI))
       return Result;
 
+  if (SDValue R = PerformSubCSINCCombine(N, DCI))
+    return R;
+
   if (!Subtarget->hasMVEIntegerOps() || !N->getValueType(0).isVector())
     return SDValue();
 
   // Fold (sub (ARMvmovImm 0), (ARMvdup x)) -> (ARMvdup (sub 0, x))
   // so that we can readily pattern match more mve instructions which can use
   // a scalar operand.
   SDValue VDup = N->getOperand(1);
   if (VDup->getOpcode() != ARMISD::VDUP)

llvm/test/CodeGen/Thumb2/mve-masked-store.ll

 ; CHECK-LE-NEXT:    .pad #4
 ; CHECK-LE-NEXT:    sub sp, #4
 ; CHECK-LE-NEXT:    vcmp.f32 s0, #0
 ; CHECK-LE-NEXT:    movs r1, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r1, #1
 ; CHECK-LE-NEXT:    cmp r1, #0
-; CHECK-LE-NEXT:    vcmp.f32 s1, #0
-; CHECK-LE-NEXT:    cset r1, ne
-; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-LE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-LE-NEXT:    mov.w r1, #0
+; CHECK-LE-NEXT:    csetm r3, ne
+; CHECK-LE-NEXT:    vcmp.f32 s1, #0
 ; CHECK-LE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    mov.w r3, #0
+; CHECK-LE-NEXT:    vcmp.f32 s2, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
-; CHECK-LE-NEXT:    cset r3, ne
-; CHECK-LE-NEXT:    vcmp.f32 s2, #0
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-LE-NEXT:    mov.w r3, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
 ; CHECK-LE-NEXT:    vcmp.f32 s3, #0
-; CHECK-LE-NEXT:    cset r3, ne
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    movs r2, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r2, #1
 ; CHECK-LE-NEXT:    cmp r2, #0
-; CHECK-LE-NEXT:    cset r2, ne
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s4, s0
 ; CHECK-LE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-LE-NEXT:    rsbs r2, r2, #0
+; CHECK-LE-NEXT:    csetm r2, ne
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s4, s1
 ; CHECK-LE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s5, s2
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s5, s3
 ; CHECK-LE-NEXT:    lsls r2, r1, #31
 ; CHECK-LE-NEXT:    bne .LBB25_5
 ; CHECK-LE-NEXT:  @ %bb.1: @ %else
 ; CHECK-LE-NEXT:    lsls r2, r1, #30

 ; CHECK-BE-NEXT:    vrev64.32 q1, q0
 ; CHECK-BE-NEXT:    movs r1, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s7, #0
 ; CHECK-BE-NEXT:    movs r2, #0
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r1, #1
 ; CHECK-BE-NEXT:    cmp r1, #0
-; CHECK-BE-NEXT:    vcmp.f32 s6, #0
-; CHECK-BE-NEXT:    cset r1, ne
-; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-BE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-BE-NEXT:    mov.w r1, #0
+; CHECK-BE-NEXT:    csetm r3, ne
+; CHECK-BE-NEXT:    vcmp.f32 s6, #0
 ; CHECK-BE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    mov.w r3, #0
+; CHECK-BE-NEXT:    vcmp.f32 s5, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
-; CHECK-BE-NEXT:    cset r3, ne
-; CHECK-BE-NEXT:    vcmp.f32 s5, #0
-; CHECK-BE-NEXT:    rsbs r3, r3, #0
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-BE-NEXT:    mov.w r3, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s4, #0
-; CHECK-BE-NEXT:    cset r3, ne
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r2, #1
 ; CHECK-BE-NEXT:    cmp r2, #0
-; CHECK-BE-NEXT:    rsb.w r3, r3, #0
-; CHECK-BE-NEXT:    cset r2, ne
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s0, s4
 ; CHECK-BE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-BE-NEXT:    rsbs r2, r2, #0
+; CHECK-BE-NEXT:    csetm r2, ne
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s0, s5
 ; CHECK-BE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s1, s6
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s1, s7
 ; CHECK-BE-NEXT:    lsls r2, r1, #28
 ; CHECK-BE-NEXT:    bmi .LBB25_5
 ; CHECK-BE-NEXT:  @ %bb.1: @ %else
 ; CHECK-BE-NEXT:    lsls r2, r1, #29

 ; CHECK-LE-NEXT:    .pad #4
 ; CHECK-LE-NEXT:    sub sp, #4
 ; CHECK-LE-NEXT:    vcmp.f32 s0, #0
 ; CHECK-LE-NEXT:    movs r1, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r1, #1
 ; CHECK-LE-NEXT:    cmp r1, #0
-; CHECK-LE-NEXT:    vcmp.f32 s1, #0
-; CHECK-LE-NEXT:    cset r1, ne
-; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-LE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-LE-NEXT:    mov.w r1, #0
+; CHECK-LE-NEXT:    csetm r3, ne
+; CHECK-LE-NEXT:    vcmp.f32 s1, #0
 ; CHECK-LE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    mov.w r3, #0
+; CHECK-LE-NEXT:    vcmp.f32 s2, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
-; CHECK-LE-NEXT:    cset r3, ne
-; CHECK-LE-NEXT:    vcmp.f32 s2, #0
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-LE-NEXT:    mov.w r3, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
 ; CHECK-LE-NEXT:    vcmp.f32 s3, #0
-; CHECK-LE-NEXT:    cset r3, ne
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    movs r2, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r2, #1
 ; CHECK-LE-NEXT:    cmp r2, #0
-; CHECK-LE-NEXT:    cset r2, ne
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s4, s0
 ; CHECK-LE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-LE-NEXT:    rsbs r2, r2, #0
+; CHECK-LE-NEXT:    csetm r2, ne
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s4, s1
 ; CHECK-LE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s5, s2
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s5, s3
 ; CHECK-LE-NEXT:    lsls r2, r1, #31
 ; CHECK-LE-NEXT:    bne .LBB26_5
 ; CHECK-LE-NEXT:  @ %bb.1: @ %else
 ; CHECK-LE-NEXT:    lsls r2, r1, #30

 ; CHECK-BE-NEXT:    vrev64.32 q1, q0
 ; CHECK-BE-NEXT:    movs r1, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s7, #0
 ; CHECK-BE-NEXT:    movs r2, #0
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r1, #1
 ; CHECK-BE-NEXT:    cmp r1, #0
-; CHECK-BE-NEXT:    vcmp.f32 s6, #0
-; CHECK-BE-NEXT:    cset r1, ne
-; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-BE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-BE-NEXT:    mov.w r1, #0
+; CHECK-BE-NEXT:    csetm r3, ne
+; CHECK-BE-NEXT:    vcmp.f32 s6, #0
 ; CHECK-BE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    mov.w r3, #0
+; CHECK-BE-NEXT:    vcmp.f32 s5, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
-; CHECK-BE-NEXT:    cset r3, ne
-; CHECK-BE-NEXT:    vcmp.f32 s5, #0
-; CHECK-BE-NEXT:    rsbs r3, r3, #0
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-BE-NEXT:    mov.w r3, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s4, #0
-; CHECK-BE-NEXT:    cset r3, ne
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r2, #1
 ; CHECK-BE-NEXT:    cmp r2, #0
-; CHECK-BE-NEXT:    rsb.w r3, r3, #0
-; CHECK-BE-NEXT:    cset r2, ne
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s0, s4
 ; CHECK-BE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-BE-NEXT:    rsbs r2, r2, #0
+; CHECK-BE-NEXT:    csetm r2, ne
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s0, s5
 ; CHECK-BE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s1, s6
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s1, s7
 ; CHECK-BE-NEXT:    lsls r2, r1, #28
 ; CHECK-BE-NEXT:    bmi .LBB26_5
 ; CHECK-BE-NEXT:  @ %bb.1: @ %else
 ; CHECK-BE-NEXT:    lsls r2, r1, #29

 ; CHECK-LE-NEXT:    .pad #20
 ; CHECK-LE-NEXT:    sub sp, #20
 ; CHECK-LE-NEXT:    vcmp.f32 s0, #0
 ; CHECK-LE-NEXT:    movs r1, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r1, #1
 ; CHECK-LE-NEXT:    cmp r1, #0
-; CHECK-LE-NEXT:    vcmp.f32 s1, #0
-; CHECK-LE-NEXT:    cset r1, ne
-; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-LE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-LE-NEXT:    mov.w r1, #0
+; CHECK-LE-NEXT:    csetm r3, ne
+; CHECK-LE-NEXT:    vcmp.f32 s1, #0
 ; CHECK-LE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    mov.w r3, #0
+; CHECK-LE-NEXT:    vcmp.f32 s2, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
-; CHECK-LE-NEXT:    cset r3, ne
-; CHECK-LE-NEXT:    vcmp.f32 s2, #0
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-LE-NEXT:    mov.w r3, #0
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r3, #1
 ; CHECK-LE-NEXT:    cmp r3, #0
 ; CHECK-LE-NEXT:    vcmp.f32 s3, #0
-; CHECK-LE-NEXT:    cset r3, ne
+; CHECK-LE-NEXT:    csetm r3, ne
 ; CHECK-LE-NEXT:    movs r2, #0
 ; CHECK-LE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-LE-NEXT:    it gt
 ; CHECK-LE-NEXT:    movgt r2, #1
 ; CHECK-LE-NEXT:    cmp r2, #0
-; CHECK-LE-NEXT:    cset r2, ne
-; CHECK-LE-NEXT:    rsbs r3, r3, #0
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s4, s0
 ; CHECK-LE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-LE-NEXT:    rsbs r2, r2, #0
+; CHECK-LE-NEXT:    csetm r2, ne
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s4, s1
 ; CHECK-LE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-LE-NEXT:    vcvtb.f16.f32 s5, s2
 ; CHECK-LE-NEXT:    vcvtt.f16.f32 s5, s3
 ; CHECK-LE-NEXT:    lsls r2, r1, #31
 ; CHECK-LE-NEXT:    bne .LBB27_5
 ; CHECK-LE-NEXT:  @ %bb.1: @ %else
 ; CHECK-LE-NEXT:    lsls r2, r1, #30

 ; CHECK-BE-NEXT:    vrev64.32 q1, q0
 ; CHECK-BE-NEXT:    movs r1, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s7, #0
 ; CHECK-BE-NEXT:    movs r2, #0
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r1, #1
 ; CHECK-BE-NEXT:    cmp r1, #0
-; CHECK-BE-NEXT:    vcmp.f32 s6, #0
-; CHECK-BE-NEXT:    cset r1, ne
-; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
-; CHECK-BE-NEXT:    rsb.w r3, r1, #0
 ; CHECK-BE-NEXT:    mov.w r1, #0
+; CHECK-BE-NEXT:    csetm r3, ne
+; CHECK-BE-NEXT:    vcmp.f32 s6, #0
 ; CHECK-BE-NEXT:    bfi r1, r3, #0, #1
+; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    mov.w r3, #0
+; CHECK-BE-NEXT:    vcmp.f32 s5, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
-; CHECK-BE-NEXT:    cset r3, ne
-; CHECK-BE-NEXT:    vcmp.f32 s5, #0
-; CHECK-BE-NEXT:    rsbs r3, r3, #0
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    bfi r1, r3, #1, #1
 ; CHECK-BE-NEXT:    mov.w r3, #0
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r3, #1
 ; CHECK-BE-NEXT:    cmp r3, #0
 ; CHECK-BE-NEXT:    vcmp.f32 s4, #0
-; CHECK-BE-NEXT:    cset r3, ne
+; CHECK-BE-NEXT:    csetm r3, ne
 ; CHECK-BE-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-BE-NEXT:    it gt
 ; CHECK-BE-NEXT:    movgt r2, #1
 ; CHECK-BE-NEXT:    cmp r2, #0
-; CHECK-BE-NEXT:    rsb.w r3, r3, #0
-; CHECK-BE-NEXT:    cset r2, ne
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s0, s4
 ; CHECK-BE-NEXT:    bfi r1, r3, #2, #1
-; CHECK-BE-NEXT:    rsbs r2, r2, #0
+; CHECK-BE-NEXT:    csetm r2, ne
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s0, s5
 ; CHECK-BE-NEXT:    bfi r1, r2, #3, #1
 ; CHECK-BE-NEXT:    vcvtb.f16.f32 s1, s6
 ; CHECK-BE-NEXT:    vcvtt.f16.f32 s1, s7
 ; CHECK-BE-NEXT:    lsls r2, r1, #28
 ; CHECK-BE-NEXT:    bmi .LBB27_5
 ; CHECK-BE-NEXT:  @ %bb.1: @ %else
 ; CHECK-BE-NEXT:    lsls r2, r1, #29

llvm/test/CodeGen/Thumb2/mve-pred-build-var.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve -verify-machineinstrs %s -o - | FileCheck %s
 
 
 define arm_aapcs_vfpcc <4 x i32> @build_var0_v4i1(i32 %s, i32 %t, <4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: build_var0_v4i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #0, #4
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <4 x i1> zeroinitializer, i1 %c, i64 0
   %r = select <4 x i1> %vc, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %r
 }
 
 define arm_aapcs_vfpcc <4 x i32> @build_var3_v4i1(i32 %s, i32 %t, <4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: build_var3_v4i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #12, #4
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <4 x i1> zeroinitializer, i1 %c, i64 3
   %r = select <4 x i1> %vc, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %r
 }
 
 define arm_aapcs_vfpcc <4 x i32> @build_varN_v4i1(i32 %s, i32 %t, <4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: build_varN_v4i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vmsr p0, r0
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc1 = insertelement <4 x i1> undef, i1 %c, i64 0
   %vc4 = shufflevector <4 x i1> %vc1, <4 x i1> undef, <4 x i32> zeroinitializer
   %r = select <4 x i1> %vc4, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %r
 }
 
 
 define arm_aapcs_vfpcc <8 x i16> @build_var0_v8i1(i32 %s, i32 %t, <8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: build_var0_v8i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #0, #2
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <8 x i1> zeroinitializer, i1 %c, i64 0
   %r = select <8 x i1> %vc, <8 x i16> %a, <8 x i16> %b
   ret <8 x i16> %r
 }
 
 define arm_aapcs_vfpcc <8 x i16> @build_var3_v8i1(i32 %s, i32 %t, <8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: build_var3_v8i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #6, #2
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <8 x i1> zeroinitializer, i1 %c, i64 3
   %r = select <8 x i1> %vc, <8 x i16> %a, <8 x i16> %b
   ret <8 x i16> %r
 }
 
 define arm_aapcs_vfpcc <8 x i16> @build_varN_v8i1(i32 %s, i32 %t, <8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: build_varN_v8i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vmsr p0, r0
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc1 = insertelement <8 x i1> undef, i1 %c, i64 0
   %vc4 = shufflevector <8 x i1> %vc1, <8 x i1> undef, <8 x i32> zeroinitializer
   %r = select <8 x i1> %vc4, <8 x i16> %a, <8 x i16> %b
   ret <8 x i16> %r
 }
 
 
 define arm_aapcs_vfpcc <16 x i8> @build_var0_v16i1(i32 %s, i32 %t, <16 x i8> %a, <16 x i8> %b) {
 ; CHECK-LABEL: build_var0_v16i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #0, #1
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <16 x i1> zeroinitializer, i1 %c, i64 0
   %r = select <16 x i1> %vc, <16 x i8> %a, <16 x i8> %b
   ret <16 x i8> %r
 }
 
 define arm_aapcs_vfpcc <16 x i8> @build_var3_v16i1(i32 %s, i32 %t, <16 x i8> %a, <16 x i8> %b) {
 ; CHECK-LABEL: build_var3_v16i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    mov.w r1, #0
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    bfi r1, r0, #3, #1
 ; CHECK-NEXT:    vmsr p0, r1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <16 x i1> zeroinitializer, i1 %c, i64 3
   %r = select <16 x i1> %vc, <16 x i8> %a, <16 x i8> %b
   ret <16 x i8> %r
 }
 
 define arm_aapcs_vfpcc <16 x i8> @build_varN_v16i1(i32 %s, i32 %t, <16 x i8> %a, <16 x i8> %b) {
 ; CHECK-LABEL: build_varN_v16i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vmsr p0, r0
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc1 = insertelement <16 x i1> undef, i1 %c, i64 0
   %vc4 = shufflevector <16 x i1> %vc1, <16 x i1> undef, <16 x i32> zeroinitializer
   %r = select <16 x i1> %vc4, <16 x i8> %a, <16 x i8> %b
   ret <16 x i8> %r
 }
 
 
 define arm_aapcs_vfpcc <2 x i64> @build_var0_v2i1(i32 %s, i32 %t, <2 x i64> %a, <2 x i64> %b) {
 ; CHECK-LABEL: build_var0_v2i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vmov s8, r0
 ; CHECK-NEXT:    vldr s10, .LCPI9_0
 ; CHECK-NEXT:    vmov.f32 s9, s8
 ; CHECK-NEXT:    vmov.f32 s11, s10
 ; CHECK-NEXT:    vbic q1, q1, q2
 ; CHECK-NEXT:    vand q0, q0, q2
 ; CHECK-NEXT:    vorr q0, q0, q1
 ; CHECK-NEXT:    bx lr
 ; CHECK-NEXT:    .p2align 2
 ; CHECK-NEXT:  @ %bb.1:
 ; CHECK-NEXT:  .LCPI9_0:
 ; CHECK-NEXT:    .long 0x00000000 @ float 0
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <2 x i1> zeroinitializer, i1 %c, i64 0
   %r = select <2 x i1> %vc, <2 x i64> %a, <2 x i64> %b
   ret <2 x i64> %r
 }
 
 define arm_aapcs_vfpcc <2 x i64> @build_var1_v2i1(i32 %s, i32 %t, <2 x i64> %a, <2 x i64> %b) {
 ; CHECK-LABEL: build_var1_v2i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vmov s10, r0
 ; CHECK-NEXT:    vldr s8, .LCPI10_0
 ; CHECK-NEXT:    vmov.f32 s9, s8
 ; CHECK-NEXT:    vmov.f32 s11, s10
 ; CHECK-NEXT:    vbic q1, q1, q2
 ; CHECK-NEXT:    vand q0, q0, q2
 ; CHECK-NEXT:    vorr q0, q0, q1
 ; CHECK-NEXT:    bx lr
 ; CHECK-NEXT:    .p2align 2
 ; CHECK-NEXT:  @ %bb.1:
 ; CHECK-NEXT:  .LCPI10_0:
 ; CHECK-NEXT:    .long 0x00000000 @ float 0
 entry:
   %c = icmp ult i32 %s, %t
   %vc = insertelement <2 x i1> zeroinitializer, i1 %c, i64 1
   %r = select <2 x i1> %vc, <2 x i64> %a, <2 x i64> %b
   ret <2 x i64> %r
 }
 
 define arm_aapcs_vfpcc <2 x i64> @build_varN_v2i1(i32 %s, i32 %t, <2 x i64> %a, <2 x i64> %b) {
 ; CHECK-LABEL: build_varN_v2i1:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    cmp r0, r1
-; CHECK-NEXT:    cset r0, lo
-; CHECK-NEXT:    rsbs r0, r0, #0
+; CHECK-NEXT:    csetm r0, lo
 ; CHECK-NEXT:    vdup.32 q2, r0
 ; CHECK-NEXT:    vbic q1, q1, q2
 ; CHECK-NEXT:    vand q0, q0, q2
 ; CHECK-NEXT:    vorr q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %c = icmp ult i32 %s, %t
   %vc1 = insertelement <2 x i1> undef, i1 %c, i64 0
   %vc4 = shufflevector <2 x i1> %vc1, <2 x i1> undef, <2 x i32> zeroinitializer
   %r = select <2 x i1> %vc4, <2 x i64> %a, <2 x i64> %b
   ret <2 x i64> %r
 }

llvm/test/CodeGen/Thumb2/mve-vmovimm.ll

entry:
   ret <8 x i16> %o
 }
 
 define arm_aapcs_vfpcc <4 x i32> @i1and_vmov(<4 x i32> %a, <4 x i32> %b, i32 %c) {
 ; CHECKLE-LABEL: i1and_vmov:
 ; CHECKLE:       @ %bb.0: @ %entry
 ; CHECKLE-NEXT:    cmp r0, #0
 ; CHECKLE-NEXT:    mov.w r1, #15
-; CHECKLE-NEXT:    cset r0, eq
-; CHECKLE-NEXT:    rsbs r0, r0, #0
+; CHECKLE-NEXT:    csetm r0, eq
 ; CHECKLE-NEXT:    ands r0, r1
 ; CHECKLE-NEXT:    vmsr p0, r0
 ; CHECKLE-NEXT:    vpsel q0, q0, q1
 ; CHECKLE-NEXT:    bx lr
 ;
 ; CHECKBE-LABEL: i1and_vmov:
 ; CHECKBE:       @ %bb.0: @ %entry
 ; CHECKBE-NEXT:    cmp r0, #0
 ; CHECKBE-NEXT:    mov.w r1, #15
-; CHECKBE-NEXT:    cset r0, eq
+; CHECKBE-NEXT:    csetm r0, eq
 ; CHECKBE-NEXT:    vrev64.32 q2, q1
-; CHECKBE-NEXT:    rsbs r0, r0, #0
-; CHECKBE-NEXT:    vrev64.32 q1, q0
 ; CHECKBE-NEXT:    ands r0, r1
+; CHECKBE-NEXT:    vrev64.32 q1, q0
 ; CHECKBE-NEXT:    vmsr p0, r0
 ; CHECKBE-NEXT:    vpsel q1, q1, q2
 ; CHECKBE-NEXT:    vrev64.32 q0, q1
 ; CHECKBE-NEXT:    bx lr
 entry:
   %c1 = icmp eq i32 %c, zeroinitializer
   %broadcast.splatinsert1967 = insertelement <4 x i1> undef, i1 %c1, i32 0
   %broadcast.splat1968 = shufflevector <4 x i1> %broadcast.splatinsert1967, <4 x i1> undef, <4 x i32> zeroinitializer
   %l699 = and <4 x i1> %broadcast.splat1968, <i1 true, i1 false, i1 false, i1 false>
   %s = select <4 x i1> %l699, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %s
 }
 
 define arm_aapcs_vfpcc <4 x i32> @i1or_vmov(<4 x i32> %a, <4 x i32> %b, i32 %c) {
 ; CHECKLE-LABEL: i1or_vmov:
 ; CHECKLE:       @ %bb.0: @ %entry
 ; CHECKLE-NEXT:    cmp r0, #0
 ; CHECKLE-NEXT:    mov.w r1, #15
-; CHECKLE-NEXT:    cset r0, eq
-; CHECKLE-NEXT:    rsbs r0, r0, #0
+; CHECKLE-NEXT:    csetm r0, eq
 ; CHECKLE-NEXT:    orrs r0, r1
 ; CHECKLE-NEXT:    vmsr p0, r0
 ; CHECKLE-NEXT:    vpsel q0, q0, q1
 ; CHECKLE-NEXT:    bx lr
 ;
 ; CHECKBE-LABEL: i1or_vmov:
 ; CHECKBE:       @ %bb.0: @ %entry
 ; CHECKBE-NEXT:    cmp r0, #0
 ; CHECKBE-NEXT:    mov.w r1, #15
-; CHECKBE-NEXT:    cset r0, eq
+; CHECKBE-NEXT:    csetm r0, eq
 ; CHECKBE-NEXT:    vrev64.32 q2, q1
-; CHECKBE-NEXT:    rsbs r0, r0, #0
-; CHECKBE-NEXT:    vrev64.32 q1, q0
 ; CHECKBE-NEXT:    orrs r0, r1
+; CHECKBE-NEXT:    vrev64.32 q1, q0
 ; CHECKBE-NEXT:    vmsr p0, r0
 ; CHECKBE-NEXT:    vpsel q1, q1, q2
 ; CHECKBE-NEXT:    vrev64.32 q0, q1
 ; CHECKBE-NEXT:    bx lr
 entry:
   %c1 = icmp eq i32 %c, zeroinitializer
   %broadcast.splatinsert1967 = insertelement <4 x i1> undef, i1 %c1, i32 0
   %broadcast.splat1968 = shufflevector <4 x i1> %broadcast.splatinsert1967, <4 x i1> undef, <4 x i32> zeroinitializer
   %l699 = or <4 x i1> %broadcast.splat1968, <i1 true, i1 false, i1 false, i1 false>
   %s = select <4 x i1> %l699, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %s
 }