[llvm] [RISCV] Fold (vslide1up undef, v, (extract_elt x, 0)) into (vslideup x, v, 1) (PR #154847)

[Luke Lau via llvm-commits]

================
@@ -21117,6 +21117,37 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
       return N->getOperand(0);
     break;
   }
+  case RISCVISD::VSLIDE1UP_VL:
+  case RISCVISD::VFSLIDE1UP_VL: {
+    using namespace SDPatternMatch;
+    SDValue SrcVec;
+    SDLoc DL(N);
+    MVT VT = N->getSimpleValueType(0);
+    // If the scalar we're sliding in was extracted from the first element of a
+    // vector, we can use that vector as the passthru in a normal slideup of 1.
+    // This saves us an extract_element instruction (i.e. vfmv.f.s, vmv.x.s).
+    if (N->getOperand(0).isUndef() &&
+        sd_match(
+            N->getOperand(2),
+            m_OneUse(m_AnyOf(m_ExtractElt(m_Value(SrcVec), m_Zero()),
+                             m_Node(RISCVISD::VMV_X_S, m_Value(SrcVec)))))) {
+      MVT SrcVecVT = SrcVec.getSimpleValueType();
+      // Adapt the value type of source vector.
+      if (SrcVecVT.isFixedLengthVector()) {
----------------
lukel97 wrote:

I thought all the RISCVISD nodes had to be in scalable containers to begin with? Is there somewhere where we're creating fixed length vslide1up_vls?

https://github.com/llvm/llvm-project/pull/154847