[RISCV] Select (and (sra x, c2), c1) as (srli (srai x, c2-c3), c3). (#101868)

If c1 is a mask with c3 leading zeros and c3 is larger than c2.

Fixes regression reported in #101751.

Author: topperc

llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp

@@ -1450,6 +1450,31 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) {
       }
     }
 
+    // Turn (and (sra x, c2), c1) -> (srli (srai x, c2-c3), c3) if c1 is a mask
+    // with c3 leading zeros and c2 is larger than c3.
+    if (N0.getOpcode() == ISD::SRA && isa<ConstantSDNode>(N0.getOperand(1)) &&
+        N0.hasOneUse()) {
+      unsigned C2 = N0.getConstantOperandVal(1);
+      unsigned XLen = Subtarget->getXLen();
+      assert((C2 > 0 && C2 < XLen) && "Unexpected shift amount!");
+
+      SDValue X = N0.getOperand(0);
+
+      if (isMask_64(C1)) {
+        unsigned Leading = XLen - llvm::bit_width(C1);
+        if (C2 > Leading) {
+          SDNode *SRAI = CurDAG->getMachineNode(
+              RISCV::SRAI, DL, VT, X,
+              CurDAG->getTargetConstant(C2 - Leading, DL, VT));
+          SDNode *SRLI = CurDAG->getMachineNode(
+              RISCV::SRLI, DL, VT, SDValue(SRAI, 0),
+              CurDAG->getTargetConstant(Leading, DL, VT));
+          ReplaceNode(Node, SRLI);
+          return;
+        }
+      }
+    }
+
     // If C1 masks off the upper bits only (but can't be formed as an
     // ANDI), use an unsigned bitfield extract (e.g., th.extu), if
     // available.

llvm/test/CodeGen/RISCV/lack-of-signed-truncation-check.ll

@@ -24,25 +24,23 @@
 define i1 @shifts_necmp_i16_i8(i16 %x) nounwind {
 ; RV32I-LABEL: shifts_necmp_i16_i8:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    lui a1, 16
-; RV32I-NEXT:    addi a1, a1, -1
-; RV32I-NEXT:    and a2, a0, a1
+; RV32I-NEXT:    slli a1, a0, 16
+; RV32I-NEXT:    srli a1, a1, 16
 ; RV32I-NEXT:    slli a0, a0, 24
-; RV32I-NEXT:    srai a0, a0, 24
-; RV32I-NEXT:    and a0, a0, a1
-; RV32I-NEXT:    xor a0, a0, a2
+; RV32I-NEXT:    srai a0, a0, 8
+; RV32I-NEXT:    srli a0, a0, 16
+; RV32I-NEXT:    xor a0, a0, a1
 ; RV32I-NEXT:    snez a0, a0
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: shifts_necmp_i16_i8:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    lui a1, 16
-; RV64I-NEXT:    addiw a1, a1, -1
-; RV64I-NEXT:    and a2, a0, a1
+; RV64I-NEXT:    slli a1, a0, 48
+; RV64I-NEXT:    srli a1, a1, 48
 ; RV64I-NEXT:    slli a0, a0, 56
-; RV64I-NEXT:    srai a0, a0, 56
-; RV64I-NEXT:    and a0, a0, a1
-; RV64I-NEXT:    xor a0, a0, a2
+; RV64I-NEXT:    srai a0, a0, 8
+; RV64I-NEXT:    srli a0, a0, 48
+; RV64I-NEXT:    xor a0, a0, a1
 ; RV64I-NEXT:    snez a0, a0
 ; RV64I-NEXT:    ret
 ;

llvm/test/CodeGen/RISCV/selectcc-to-shiftand.ll

@@ -262,3 +262,27 @@ define i64 @sel_shift_bool_i64(i1 %t) {
   %shl = select i1 %t, i64 65536, i64 0
   ret i64 %shl
 }
+
+; FIXME: This should use sraiw+and
+define i64 @sraiw_andi(i32 signext %0, i32 signext %1) nounwind {
+; RV32-LABEL: sraiw_andi:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    add a0, a0, a1
+; RV32-NEXT:    srai a0, a0, 2
+; RV32-NEXT:    srli a0, a0, 29
+; RV32-NEXT:    li a1, 0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: sraiw_andi:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    add a0, a0, a1
+; RV64-NEXT:    slli a0, a0, 32
+; RV64-NEXT:    srai a0, a0, 2
+; RV64-NEXT:    srli a0, a0, 61
+; RV64-NEXT:    ret
+entry:
+  %3 = add i32 %0, %1
+  %4 = icmp sgt i32 %3, -1
+  %5 = select i1 %4, i64 0, i64 7
+  ret i64 %5
+}

llvm/test/CodeGen/RISCV/signed-truncation-check.ll

@@ -24,25 +24,23 @@
 define i1 @shifts_eqcmp_i16_i8(i16 %x) nounwind {
 ; RV32I-LABEL: shifts_eqcmp_i16_i8:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    lui a1, 16
-; RV32I-NEXT:    addi a1, a1, -1
-; RV32I-NEXT:    and a2, a0, a1
+; RV32I-NEXT:    slli a1, a0, 16
+; RV32I-NEXT:    srli a1, a1, 16
 ; RV32I-NEXT:    slli a0, a0, 24
-; RV32I-NEXT:    srai a0, a0, 24
-; RV32I-NEXT:    and a0, a0, a1
-; RV32I-NEXT:    xor a0, a0, a2
+; RV32I-NEXT:    srai a0, a0, 8
+; RV32I-NEXT:    srli a0, a0, 16
+; RV32I-NEXT:    xor a0, a0, a1
 ; RV32I-NEXT:    seqz a0, a0
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: shifts_eqcmp_i16_i8:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    lui a1, 16
-; RV64I-NEXT:    addiw a1, a1, -1
-; RV64I-NEXT:    and a2, a0, a1
+; RV64I-NEXT:    slli a1, a0, 48
+; RV64I-NEXT:    srli a1, a1, 48
 ; RV64I-NEXT:    slli a0, a0, 56
-; RV64I-NEXT:    srai a0, a0, 56
-; RV64I-NEXT:    and a0, a0, a1
-; RV64I-NEXT:    xor a0, a0, a2
+; RV64I-NEXT:    srai a0, a0, 8
+; RV64I-NEXT:    srli a0, a0, 48
+; RV64I-NEXT:    xor a0, a0, a1
 ; RV64I-NEXT:    seqz a0, a0
 ; RV64I-NEXT:    ret
 ;