[RISCV] Fix incorrect codegen for masked vmsge{u}.vx with mask agnostic.

The result was totally wrong.
We could use mask undisturbed result to emulate the mask agnostic result.

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D124684

diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
index de9c151..7fae031 100644 (file)
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
@@ -1121,16 +1121,15 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) {
       SDValue V0 = CurDAG->getRegister(RISCV::V0, VT);
 
       // Otherwise use
-      // vmslt{u}.vx vd, va, x, v0.t; if mask policy is agnostic.
+      // vmslt{u}.vx vd, va, x, v0.t; vmxor.mm vd, vd, v0
+      // The result is mask undisturbed.
+      // We use the same instructions to emulate mask agnostic behavior, because
+      // the agnostic result can be either undisturbed or all 1.
       SDValue Cmp = SDValue(
           CurDAG->getMachineNode(VMSLTMaskOpcode, DL, VT,
                                  {MaskedOff, Src1, Src2, V0, VL, SEW, Glue}),
           0);
-      if (MaskedOff.isUndef()) {
-        ReplaceNode(Node, Cmp.getNode());
-        return;
-      }
-      // Need vmxor.mm vd, vd, v0 to assign inactive value.
+      // vmxor.mm vd, vd, v0 is used to update active value.
       ReplaceNode(Node, CurDAG->getMachineNode(VMXOROpcode, DL, VT,
                                                {Cmp, Mask, VL, MaskSEW}));
       return;

diff --git a/llvm/test/CodeGen/RISCV/rvv/masked-tama.ll b/llvm/test/CodeGen/RISCV/rvv/masked-tama.ll
index deac535..26c7509 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/masked-tama.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/masked-tama.ll
@@ -1431,7 +1431,9 @@ define <vscale x 1 x i1> @intrinsic_vmsge_mask_vx_nxv1i64_i64(<vscale x 1 x i64>
 ; RV64-LABEL: intrinsic_vmsge_mask_vx_nxv1i64_i64:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
-; RV64-NEXT:    vmslt.vx v0, v8, a0, v0.t
+; RV64-NEXT:    vmslt.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
+; RV64-NEXT:    vmxor.mm v0, v8, v0
 ; RV64-NEXT:    ret
 entry:
   %a = call <vscale x 1 x i1> @llvm.riscv.vmsge.mask.nxv1i64.i64(