[RISCV][SelectionDAG] Support VECREDUCE_ADD mask operation

[Jimerlife]

Summary

Support VECREDUCE_ADD mask operation, turn it to VECREDUCE_XOR in getNode

[craig.topper]

LGTM

[thakis]

This seems to break check-llvm: http://45.33.8.238/linux/75725/step_12.txt

Please take a look, and revert for now if it takes a while to fix.

[Jimerlife]

In D125206#3502897, @thakis wrote:

This seems to break check-llvm: http://45.33.8.238/linux/75725/step_12.txt

Please take a look, and revert for now if it takes a while to fix.

I have revert this patch, Thanks.

[Jimerlife]

update for re-landed

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

case ISD::CTPOP:
     if (Operand.getValueType().getScalarType() == MVT::i1)
       return Operand;
     break;
   case ISD::CTLZ:
   case ISD::CTTZ:
     if (Operand.getValueType().getScalarType() == MVT::i1)
       return getNOT(DL, Operand, Operand.getValueType());
     break;
+  case ISD::VECREDUCE_ADD:
+    if (Operand.getValueType().getScalarType() == MVT::i1)
+      return getNode(ISD::VECREDUCE_XOR, DL, VT, Operand);
+    break;
   case ISD::VECREDUCE_SMIN:
   case ISD::VECREDUCE_UMAX:
     if (Operand.getValueType().getScalarType() == MVT::i1)
       return getNode(ISD::VECREDUCE_OR, DL, VT, Operand);
     break;
   case ISD::VECREDUCE_SMAX:
   case ISD::VECREDUCE_UMIN:
     if (Operand.getValueType().getScalarType() == MVT::i1)

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll

 ; LMULMAX8-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
 ; LMULMAX8-NEXT:    vcpop.m a0, v0
 ; LMULMAX8-NEXT:    snez a0, a0
 ; LMULMAX8-NEXT:    neg a0, a0
 ; LMULMAX8-NEXT:    ret
   %red = call i1 @llvm.vector.reduce.smin.v64i1(<64 x i1> %v)
   ret i1 %red
 }
+
+declare i1 @llvm.vector.reduce.add.v1i1(<1 x i1>)
+
+define signext i1 @vreduce_add_v1i1(<1 x i1> %v) {
+; CHECK-LABEL: vreduce_add_v1i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vmv.v.i v8, 0
+; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
+; CHECK-NEXT:    vmv.x.s a0, v8
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v1i1(<1 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v2i1(<2 x i1>)
+
+define signext i1 @vreduce_add_v2i1(<2 x i1> %v) {
+; CHECK-LABEL: vreduce_add_v2i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v2i1(<2 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v4i1(<4 x i1>)
+
+define signext i1 @vreduce_add_v4i1(<4 x i1> %v) {
+; CHECK-LABEL: vreduce_add_v4i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v4i1(<4 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v8i1(<8 x i1>)
+
+define signext i1 @vreduce_add_v8i1(<8 x i1> %v) {
+; CHECK-LABEL: vreduce_add_v8i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v8i1(<8 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v16i1(<16 x i1>)
+
+define signext i1 @vreduce_add_v16i1(<16 x i1> %v) {
+; CHECK-LABEL: vreduce_add_v16i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v16i1(<16 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v32i1(<32 x i1>)
+
+define signext i1 @vreduce_add_v32i1(<32 x i1> %v) {
+; LMULMAX1-LABEL: vreduce_add_v32i1:
+; LMULMAX1:       # %bb.0:
+; LMULMAX1-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; LMULMAX1-NEXT:    vmxor.mm v8, v0, v8
+; LMULMAX1-NEXT:    vcpop.m a0, v8
+; LMULMAX1-NEXT:    andi a0, a0, 1
+; LMULMAX1-NEXT:    neg a0, a0
+; LMULMAX1-NEXT:    ret
+;
+; LMULMAX8-LABEL: vreduce_add_v32i1:
+; LMULMAX8:       # %bb.0:
+; LMULMAX8-NEXT:    li a0, 32
+; LMULMAX8-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; LMULMAX8-NEXT:    vcpop.m a0, v0
+; LMULMAX8-NEXT:    andi a0, a0, 1
+; LMULMAX8-NEXT:    neg a0, a0
+; LMULMAX8-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v32i1(<32 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.v64i1(<64 x i1>)
+
+define signext i1 @vreduce_add_v64i1(<64 x i1> %v) {
+; LMULMAX1-LABEL: vreduce_add_v64i1:
+; LMULMAX1:       # %bb.0:
+; LMULMAX1-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; LMULMAX1-NEXT:    vmxor.mm v8, v8, v10
+; LMULMAX1-NEXT:    vmxor.mm v9, v0, v9
+; LMULMAX1-NEXT:    vmxor.mm v8, v9, v8
+; LMULMAX1-NEXT:    vcpop.m a0, v8
+; LMULMAX1-NEXT:    andi a0, a0, 1
+; LMULMAX1-NEXT:    neg a0, a0
+; LMULMAX1-NEXT:    ret
+;
+; LMULMAX8-LABEL: vreduce_add_v64i1:
+; LMULMAX8:       # %bb.0:
+; LMULMAX8-NEXT:    li a0, 64
+; LMULMAX8-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; LMULMAX8-NEXT:    vcpop.m a0, v0
+; LMULMAX8-NEXT:    andi a0, a0, 1
+; LMULMAX8-NEXT:    neg a0, a0
+; LMULMAX8-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.v64i1(<64 x i1> %v)
+  ret i1 %red
+}

llvm/test/CodeGen/RISCV/rvv/vreductions-mask.ll

 ; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, mu
 ; CHECK-NEXT:    vcpop.m a0, v0
 ; CHECK-NEXT:    snez a0, a0
 ; CHECK-NEXT:    neg a0, a0
 ; CHECK-NEXT:    ret
   %red = call i1 @llvm.vector.reduce.smin.nxv64i1(<vscale x 64 x i1> %v)
   ret i1 %red
 }
+
+declare i1 @llvm.vector.reduce.add.nxv1i1(<vscale x 1 x i1>)
+
+define signext i1 @vreduce_add_nxv1i1(<vscale x 1 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv1i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv1i1(<vscale x 1 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv2i1(<vscale x 2 x i1>)
+
+define signext i1 @vreduce_add_nxv2i1(<vscale x 2 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv2i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv2i1(<vscale x 2 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv4i1(<vscale x 4 x i1>)
+
+define signext i1 @vreduce_add_nxv4i1(<vscale x 4 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv4i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv4i1(<vscale x 4 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv8i1(<vscale x 8 x i1>)
+
+define signext i1 @vreduce_add_nxv8i1(<vscale x 8 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv8i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv8i1(<vscale x 8 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv16i1(<vscale x 16 x i1>)
+
+define signext i1 @vreduce_add_nxv16i1(<vscale x 16 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv16i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv16i1(<vscale x 16 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv32i1(<vscale x 32 x i1>)
+
+define signext i1 @vreduce_add_nxv32i1(<vscale x 32 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv32i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv32i1(<vscale x 32 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.add.nxv64i1(<vscale x 64 x i1>)
+
+define signext i1 @vreduce_add_nxv64i1(<vscale x 64 x i1> %v) {
+; CHECK-LABEL: vreduce_add_nxv64i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.add.nxv64i1(<vscale x 64 x i1> %v)
+  ret i1 %red
+}