[ARM] Custom lower i1 vector truncates

The ISel patterns we have for truncating to i1's under MVE do not seem
to be correct. Instead custom lower to icmp(ne, and(x, 1), 0).

Differential Revision: https://reviews.llvm.org/D94226

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index efe2efe..982397d 100644 (file)
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -443,6 +443,7 @@ void ARMTargetLowering::addMVEVectorTypes(bool HasMVEFP) {
     setOperationAction(ISD::SCALAR_TO_VECTOR, VT, Expand);
     setOperationAction(ISD::LOAD, VT, Custom);
     setOperationAction(ISD::STORE, VT, Custom);
+    setOperationAction(ISD::TRUNCATE, VT, Custom);
   }
 }
 
@@ -8660,6 +8661,23 @@ static SDValue LowerEXTRACT_SUBVECTOR(SDValue Op, SelectionDAG &DAG,
                      DAG.getConstant(ARMCC::NE, dl, MVT::i32));
 }
 
+// Turn a truncate into a predicate (an i1 vector) into icmp(and(x, 1), 0).
+static SDValue LowerTruncatei1(SDValue N, SelectionDAG &DAG,
+                               const ARMSubtarget *ST) {
+  assert(ST->hasMVEIntegerOps() && "Expected MVE!");
+  EVT VT = N.getValueType();
+  assert((VT == MVT::v16i1 || VT == MVT::v8i1 || VT == MVT::v4i1) &&
+         "Expected a vector i1 type!");
+  SDValue Op = N.getOperand(0);
+  EVT FromVT = Op.getValueType();
+  SDLoc DL(N);
+
+  SDValue And =
+      DAG.getNode(ISD::AND, DL, FromVT, Op, DAG.getConstant(1, DL, FromVT));
+  return DAG.getNode(ISD::SETCC, DL, VT, And, DAG.getConstant(0, DL, FromVT),
+                     DAG.getCondCode(ISD::SETNE));
+}
+
 /// isExtendedBUILD_VECTOR - Check if N is a constant BUILD_VECTOR where each
 /// element has been zero/sign-extended, depending on the isSigned parameter,
 /// from an integer type half its size.
@@ -9771,6 +9789,7 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::INSERT_VECTOR_ELT: return LowerINSERT_VECTOR_ELT(Op, DAG);
   case ISD::EXTRACT_VECTOR_ELT: return LowerEXTRACT_VECTOR_ELT(Op, DAG, Subtarget);
   case ISD::CONCAT_VECTORS: return LowerCONCAT_VECTORS(Op, DAG, Subtarget);
+  case ISD::TRUNCATE:      return LowerTruncatei1(Op, DAG, Subtarget);
   case ISD::FLT_ROUNDS_:   return LowerFLT_ROUNDS_(Op, DAG);
   case ISD::MUL:           return LowerMUL(Op, DAG);
   case ISD::SDIV:

diff --git a/llvm/lib/Target/ARM/ARMInstrMVE.td b/llvm/lib/Target/ARM/ARMInstrMVE.td
index b4e4397..0dfea68 100644 (file)
--- a/llvm/lib/Target/ARM/ARMInstrMVE.td
+++ b/llvm/lib/Target/ARM/ARMInstrMVE.td
@@ -6759,13 +6759,6 @@ let Predicates = [HasMVEInt] in {
             (v8i16 (MVE_VPSEL (MVE_VMOVimmi16 1), (MVE_VMOVimmi16 0), ARMVCCNone, VCCR:$pred))>;
   def : Pat<(v4i32 (anyext  (v4i1  VCCR:$pred))),
             (v4i32 (MVE_VPSEL (MVE_VMOVimmi32 1), (MVE_VMOVimmi32 0), ARMVCCNone, VCCR:$pred))>;
-
-  def : Pat<(v16i1 (trunc (v16i8 MQPR:$v1))),
-            (v16i1 (MVE_VCMPi32r (v16i8 MQPR:$v1), ZR, ARMCCne))>;
-  def : Pat<(v8i1 (trunc (v8i16  MQPR:$v1))),
-            (v8i1 (MVE_VCMPi32r (v8i16 MQPR:$v1), ZR, ARMCCne))>;
-  def : Pat<(v4i1 (trunc (v4i32  MQPR:$v1))),
-            (v4i1 (MVE_VCMPi32r (v4i32 MQPR:$v1), ZR, ARMCCne))>;
 }
 
 let Predicates = [HasMVEFloat] in {

diff --git a/llvm/test/CodeGen/Thumb2/mve-pred-ext.ll b/llvm/test/CodeGen/Thumb2/mve-pred-ext.ll
index c280fa2..9fe502a 100644 (file)
--- a/llvm/test/CodeGen/Thumb2/mve-pred-ext.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-pred-ext.ll
@@ -159,8 +159,10 @@ entry:
 define arm_aapcs_vfpcc <4 x i32> @trunc_v4i1_v4i32(<4 x i32> %src) {
 ; CHECK-LABEL: trunc_v4i1_v4i32:
 ; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmov.i32 q2, #0x1
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
-; CHECK-NEXT:    vcmp.i32 ne, q0, zr
+; CHECK-NEXT:    vand q2, q0, q2
+; CHECK-NEXT:    vcmp.i32 ne, q2, zr
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
@@ -172,8 +174,10 @@ entry:
 define arm_aapcs_vfpcc <8 x i16> @trunc_v8i1_v8i16(<8 x i16> %src) {
 ; CHECK-LABEL: trunc_v8i1_v8i16:
 ; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmov.i16 q2, #0x1
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
-; CHECK-NEXT:    vcmp.i32 ne, q0, zr
+; CHECK-NEXT:    vand q2, q0, q2
+; CHECK-NEXT:    vcmp.i16 ne, q2, zr
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
@@ -185,8 +189,10 @@ entry:
 define arm_aapcs_vfpcc <16 x i8> @trunc_v16i1_v16i8(<16 x i8> %src) {
 ; CHECK-LABEL: trunc_v16i1_v16i8:
 ; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmov.i8 q2, #0x1
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
-; CHECK-NEXT:    vcmp.i32 ne, q0, zr
+; CHECK-NEXT:    vand q2, q0, q2
+; CHECK-NEXT:    vcmp.i8 ne, q2, zr
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry: