[RISCV] Fold (X & (7 << 29)) == 0 -> (srliw X, 29) == 0 for RV64. (#156769)

This is similar to the recently added (X & -4096) == 0 -> (X >> 12) ==
0,
but operating only on the lower 32 bits.
    
This also removes the (X & (1 << 31)) == 0 -> (xor (srliw X, 31), 1)
isel pattern. seqz and xori 1 should have similar cost and encoding
size.

Author: topperc

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -16726,10 +16726,6 @@ combineVectorSizedSetCCEquality(EVT VT, SDValue X, SDValue Y, ISD::CondCode CC,
                       DAG.getConstant(0, DL, XLenVT), CC);
 }
 
-// Replace (seteq (i64 (and X, 0xffffffff)), C1) with
-// (seteq (i64 (sext_inreg (X, i32)), C1')) where C1' is C1 sign extended from
-// bit 31. Same for setne. C1' may be cheaper to materialize and the sext_inreg
-// can become a sext.w instead of a shift pair.
 static SDValue performSETCCCombine(SDNode *N,
                                    TargetLowering::DAGCombinerInfo &DCI,
                                    const RISCVSubtarget &Subtarget) {
@@ -16749,20 +16745,36 @@ static SDValue performSETCCCombine(SDNode *N,
           combineVectorSizedSetCCEquality(VT, N0, N1, Cond, dl, DAG, Subtarget))
     return V;
 
-  // (X & -4096) == 0 -> (X >> 12) == 0 if the AND constant can't use ANDI.
   if (DCI.isAfterLegalizeDAG() && isNullConstant(N1) &&
       N0.getOpcode() == ISD::AND && N0.hasOneUse() &&
       isa<ConstantSDNode>(N0.getOperand(1))) {
     const APInt &AndRHSC =
         cast<ConstantSDNode>(N0.getOperand(1))->getAPIntValue();
+    // (X & -(1 << C)) == 0 -> (X >> C) == 0 if the AND constant can't use ANDI.
     if (!isInt<12>(AndRHSC.getSExtValue()) && AndRHSC.isNegatedPowerOf2()) {
       unsigned ShiftBits = AndRHSC.countr_zero();
-      SDValue Shift = DAG.getNode(ISD::SRL, dl, VT, N0.getOperand(0),
-                                  DAG.getConstant(ShiftBits, dl, VT));
+      SDValue Shift = DAG.getNode(ISD::SRL, dl, OpVT, N0.getOperand(0),
+                                  DAG.getConstant(ShiftBits, dl, OpVT));
+      return DAG.getSetCC(dl, VT, Shift, N1, Cond);
+    }
+
+    // Similar to above but handling the lower 32 bits by using srliw.
+    // FIXME: Handle the case where N1 is non-zero.
+    if (OpVT == MVT::i64 && AndRHSC.getZExtValue() <= 0xffffffff &&
+        isPowerOf2_32(-uint32_t(AndRHSC.getZExtValue()))) {
+      unsigned ShiftBits = llvm::countr_zero(AndRHSC.getZExtValue());
+      SDValue And = DAG.getNode(ISD::AND, dl, OpVT, N0.getOperand(0),
+                                DAG.getConstant(0xffffffff, dl, OpVT));
+      SDValue Shift = DAG.getNode(ISD::SRL, dl, OpVT, And,
+                                  DAG.getConstant(ShiftBits, dl, OpVT));
       return DAG.getSetCC(dl, VT, Shift, N1, Cond);
     }
   }
 
+  // Replace (seteq (i64 (and X, 0xffffffff)), C1) with
+  // (seteq (i64 (sext_inreg (X, i32)), C1')) where C1' is C1 sign extended from
+  // bit 31. Same for setne. C1' may be cheaper to materialize and the
+  // sext_inreg can become a sext.w instead of a shift pair.
   if (OpVT != MVT::i64 || !Subtarget.is64Bit())
     return SDValue();
 

llvm/lib/Target/RISCV/RISCVInstrInfo.td

@@ -1698,8 +1698,6 @@ let Predicates = [IsRV32] in {
 def : Pat<(i32 (setlt (i32 GPR:$rs1), 0)), (SRLI GPR:$rs1, 31)>; // compressible
 }
 let Predicates = [IsRV64] in {
-def : Pat<(i64 (seteq (i64 (and GPR:$rs1, 0x0000000080000000)), 0)),
-          (XORI (i64 (SRLIW GPR:$rs1, 31)), 1)>;
 def : Pat<(i64 (setlt (i64 GPR:$rs1), 0)), (SRLI GPR:$rs1, 63)>; // compressible
 def : Pat<(i64 (setlt (sext_inreg GPR:$rs1, i32), 0)), (SRLIW GPR:$rs1, 31)>;
 }

llvm/test/CodeGen/RISCV/and-negpow2-cmp.ll

@@ -64,3 +64,37 @@ define i1 @test4(i64 %x) {
   %b = icmp eq i64 %a, 0
   ret i1 %b
 }
+
+define i1 @test5(i64 %x) {
+; RV32-LABEL: test5:
+; RV32:       # %bb.0:
+; RV32-NEXT:    srli a0, a0, 29
+; RV32-NEXT:    seqz a0, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: test5:
+; RV64:       # %bb.0:
+; RV64-NEXT:    srliw a0, a0, 29
+; RV64-NEXT:    seqz a0, a0
+; RV64-NEXT:    ret
+  %a = and i64 %x, u0xE0000000
+  %b = icmp eq i64 %a, 0
+  ret i1 %b
+}
+
+define i1 @test6(i64 %x) {
+; RV32-LABEL: test6:
+; RV32:       # %bb.0:
+; RV32-NEXT:    srli a0, a0, 29
+; RV32-NEXT:    snez a0, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: test6:
+; RV64:       # %bb.0:
+; RV64-NEXT:    srliw a0, a0, 29
+; RV64-NEXT:    snez a0, a0
+; RV64-NEXT:    ret
+  %a = and i64 %x, u0xE0000000
+  %b = icmp ne i64 %a, 0
+  ret i1 %b
+}

llvm/test/CodeGen/RISCV/bittest.ll

@@ -188,13 +188,13 @@ define i64 @bittest_31_i64(i64 %a) nounwind {
 ; RV64ZBS-LABEL: bittest_31_i64:
 ; RV64ZBS:       # %bb.0:
 ; RV64ZBS-NEXT:    srliw a0, a0, 31
-; RV64ZBS-NEXT:    xori a0, a0, 1
+; RV64ZBS-NEXT:    seqz a0, a0
 ; RV64ZBS-NEXT:    ret
 ;
 ; RV64XTHEADBS-LABEL: bittest_31_i64:
 ; RV64XTHEADBS:       # %bb.0:
 ; RV64XTHEADBS-NEXT:    srliw a0, a0, 31
-; RV64XTHEADBS-NEXT:    xori a0, a0, 1
+; RV64XTHEADBS-NEXT:    seqz a0, a0
 ; RV64XTHEADBS-NEXT:    ret
   %shr = lshr i64 %a, 31
   %not = xor i64 %shr, -1
@@ -3518,7 +3518,7 @@ define i32 @bittest_31_andeq0_i64(i64 %x) {
 ; RV64-LABEL: bittest_31_andeq0_i64:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    srliw a0, a0, 31
-; RV64-NEXT:    xori a0, a0, 1
+; RV64-NEXT:    seqz a0, a0
 ; RV64-NEXT:    ret
   %and = and i64 %x, 2147483648
   %cmp = icmp eq i64 %and, 0