[llvm] 03e675f - [ARM] Turn pred_cast(xor(x, -1)) into xor(pred_cast(x), -1)

[David Green via llvm-commits]

Author: David Green
Date: 2020-12-08T15:22:46Z
New Revision: 03e675fd128bed754454fc176357ad0ec6660c47

URL: https://github.com/llvm/llvm-project/commit/03e675fd128bed754454fc176357ad0ec6660c47
DIFF: https://github.com/llvm/llvm-project/commit/03e675fd128bed754454fc176357ad0ec6660c47.diff

LOG: [ARM] Turn pred_cast(xor(x, -1)) into xor(pred_cast(x), -1)

This folds a not (an xor -1) though a predicate_cast, so that it can be
turned into a VPNOT and potentially be folded away as an else predicate
inside a VPT block.

Differential Revision: https://reviews.llvm.org/D92235

Added: 
    

Modified: 
    llvm/lib/Target/ARM/ARMISelLowering.cpp
    llvm/test/CodeGen/Thumb2/mve-pred-constfold.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index bc9222151899..1c6acbcf1a88 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -13848,6 +13848,16 @@ PerformPREDICATE_CASTCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI) {
     return DCI.DAG.getNode(ARMISD::PREDICATE_CAST, dl, VT, Op->getOperand(0));
   }
 
+  // Turn pred_cast(xor x, -1) into xor(pred_cast x, -1), in order to produce
+  // more VPNOT which might get folded as else predicates.
+  if (Op.getValueType() == MVT::i32 && isBitwiseNot(Op)) {
+    SDValue X =
+        DCI.DAG.getNode(ARMISD::PREDICATE_CAST, dl, VT, Op->getOperand(0));
+    SDValue C = DCI.DAG.getNode(ARMISD::PREDICATE_CAST, dl, VT,
+                                DCI.DAG.getConstant(65535, dl, MVT::i32));
+    return DCI.DAG.getNode(ISD::XOR, dl, VT, X, C);
+  }
+
   // Only the bottom 16 bits of the source register are used.
   if (Op.getValueType() == MVT::i32) {
     APInt DemandedMask = APInt::getLowBitsSet(32, 16);

diff  --git a/llvm/test/CodeGen/Thumb2/mve-pred-constfold.ll b/llvm/test/CodeGen/Thumb2/mve-pred-constfold.ll
index 17f57743c301..2d5b6ba0cafa 100644
--- a/llvm/test/CodeGen/Thumb2/mve-pred-constfold.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-pred-constfold.ll
@@ -52,14 +52,11 @@ define arm_aapcs_vfpcc void @const(<8 x i16> %acc0, <8 x i16> %acc1, i32* nocapt
 ; CHECK-NEXT:    .save {r4, r6, r7, lr}
 ; CHECK-NEXT:    push {r4, r6, r7, lr}
 ; CHECK-NEXT:    vmsr p0, r1
-; CHECK-NEXT:    mvns r1, r1
-; CHECK-NEXT:    vpstt
+; CHECK-NEXT:    vpsttee
 ; CHECK-NEXT:    vaddvt.s16 r12, q1
 ; CHECK-NEXT:    vaddvt.s16 r2, q0
-; CHECK-NEXT:    vmsr p0, r1
-; CHECK-NEXT:    vpstt
-; CHECK-NEXT:    vaddvt.s16 r4, q1
-; CHECK-NEXT:    vaddvt.s16 r6, q0
+; CHECK-NEXT:    vaddve.s16 r4, q1
+; CHECK-NEXT:    vaddve.s16 r6, q0
 ; CHECK-NEXT:    stm.w r0, {r2, r6, r12}
 ; CHECK-NEXT:    str r4, [r0, #12]
 ; CHECK-NEXT:    pop {r4, r6, r7, pc}
@@ -88,9 +85,9 @@ entry:
 define arm_aapcs_vfpcc <4 x i32> @xorvpnot_i32(<4 x i32> %acc0, i16 signext %p0) {
 ; CHECK-LABEL: xorvpnot_i32:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    mvns r0, r0
-; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vmov.i32 q1, #0x0
+; CHECK-NEXT:    vpnot
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
@@ -104,9 +101,9 @@ entry:
 define arm_aapcs_vfpcc <8 x i16> @xorvpnot_i16(<8 x i16> %acc0, i16 signext %p0) {
 ; CHECK-LABEL: xorvpnot_i16:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    mvns r0, r0
-; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vmov.i32 q1, #0x0
+; CHECK-NEXT:    vpnot
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
@@ -120,9 +117,9 @@ entry:
 define arm_aapcs_vfpcc <16 x i8> @xorvpnot_i8(<16 x i8> %acc0, i16 signext %p0) {
 ; CHECK-LABEL: xorvpnot_i8:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    mvns r0, r0
-; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vmov.i32 q1, #0x0
+; CHECK-NEXT:    vpnot
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
@@ -133,6 +130,21 @@ entry:
   ret <16 x i8> %l6
 }
 
+define arm_aapcs_vfpcc <16 x i8> @xorvpnot_i8_2(<16 x i8> %acc0, i32 %p0) {
+; CHECK-LABEL: xorvpnot_i8_2:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vmov.i32 q1, #0x0
+; CHECK-NEXT:    vpnot
+; CHECK-NEXT:    vpsel q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %l3 = xor i32 %p0, 65535
+  %l5 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %l3)
+  %l6 = select <16 x i1> %l5, <16 x i8> %acc0, <16 x i8> zeroinitializer
+  ret <16 x i8> %l6
+}
+
 
 
 declare i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1>)