[DAG] Fold rem(rem(A, BCst), Op1Cst) -> rem(A, Op1Cst)

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -5442,6 +5442,24 @@ SDValue DAGCombiner::visitREM(SDNode *N) {
   if (SDValue DivRem = useDivRem(N))
     return DivRem.getValue(1);
 
+  // fold urem(urem(A, BCst), Op1Cst) -> urem(A, Op1Cst)
+  // iff urem(BCst, Op1Cst) == 0
+  SDValue A;
+  APInt Op1Cst, BCst;
+  if (sd_match(N, m_URem(m_URem(m_Value(A), m_ConstInt(BCst)),
+                         m_ConstInt(Op1Cst))) &&
+      BCst.urem(Op1Cst).isZero()) {
+    return DAG.getNode(ISD::UREM, DL, VT, A, DAG.getConstant(Op1Cst, DL, VT));
+  }
+
+  // fold srem(srem(A, BCst), Op1Cst) -> srem(A, Op1Cst)
+  // iff srem(BCst, Op1Cst) == 0 && Op1Cst != 1
+  if (sd_match(N, m_SRem(m_SRem(m_Value(A), m_ConstInt(BCst)),
+                         m_ConstInt(Op1Cst))) &&
+      BCst.srem(Op1Cst).isZero() && !Op1Cst.isAllOnes()) {
+    return DAG.getNode(ISD::SREM, DL, VT, A, DAG.getConstant(Op1Cst, DL, VT));
+  }
+
   return SDValue();
 }
 

llvm/test/CodeGen/RISCV/srem.ll

@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefixes=CHECK,RV32I %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefixes=CHECK,RV64I %s
+
+define i32 @fold_srem_constants(i32 %v0) nounwind {
+; RV32I-LABEL: fold_srem_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    li a1, 5
+; RV32I-NEXT:    tail __modsi3
+;
+; RV64I-LABEL: fold_srem_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    li a1, 5
+; RV64I-NEXT:    call __moddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = srem i32 %v0, 25
+  %v2 = srem i32 %v1, 5
+  ret i32 %v2
+}
+
+define i32 @dont_fold_srem_constants(i32 %v0) nounwind {
+; RV32I-LABEL: dont_fold_srem_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi sp, sp, -16
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    li a1, 25
+; RV32I-NEXT:    call __modsi3
+; RV32I-NEXT:    li a1, 3
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT:    addi sp, sp, 16
+; RV32I-NEXT:    tail __modsi3
+;
+; RV64I-LABEL: dont_fold_srem_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    li a1, 25
+; RV64I-NEXT:    call __moddi3
+; RV64I-NEXT:    li a1, 3
+; RV64I-NEXT:    call __moddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = srem i32 %v0, 25
+  %v2 = srem i32 %v1, 3
+  ret i32 %v2
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK: {{.*}}

llvm/test/CodeGen/RISCV/urem.ll

@@ -0,0 +1,120 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefixes=CHECK,RV32I %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefixes=CHECK,RV64I %s
+
+define i32 @fold_urem_constants(i32 %v0) nounwind {
+; RV32I-LABEL: fold_urem_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    li a1, 5
+; RV32I-NEXT:    tail __umodsi3
+;
+; RV64I-LABEL: fold_urem_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    li a1, 5
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = urem i32 %v0, 25
+  %v2 = urem i32 %v1, 5
+  ret i32 %v2
+}
+
+define i32 @dont_fold_urem_constants(i32 %v0) nounwind {
+; RV32I-LABEL: dont_fold_urem_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi sp, sp, -16
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    li a1, 25
+; RV32I-NEXT:    call __umodsi3
+; RV32I-NEXT:    li a1, 3
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT:    addi sp, sp, 16
+; RV32I-NEXT:    tail __umodsi3
+;
+; RV64I-LABEL: dont_fold_urem_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    li a1, 25
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    li a1, 3
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = urem i32 %v0, 25
+  %v2 = urem i32 %v1, 3
+  ret i32 %v2
+}
+
+define i32 @dont_fold_urem_srem_mixed_constants(i32 %v0) nounwind {
+; RV32I-LABEL: dont_fold_urem_srem_mixed_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi sp, sp, -16
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    li a1, 25
+; RV32I-NEXT:    call __umodsi3
+; RV32I-NEXT:    li a1, 3
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT:    addi sp, sp, 16
+; RV32I-NEXT:    tail __umodsi3
+;
+; RV64I-LABEL: dont_fold_urem_srem_mixed_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    li a1, 25
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    li a1, 3
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = urem i32 %v0, 25
+  %v2 = srem i32 %v1, 3
+  ret i32 %v2
+}
+
+define i32 @dont_fold_srem_urem_mixed_constants(i32 %v0) nounwind {
+; RV32I-LABEL: dont_fold_srem_urem_mixed_constants:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi sp, sp, -16
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    li a1, 25
+; RV32I-NEXT:    call __modsi3
+; RV32I-NEXT:    li a1, 3
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT:    addi sp, sp, 16
+; RV32I-NEXT:    tail __umodsi3
+;
+; RV64I-LABEL: dont_fold_srem_urem_mixed_constants:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    li a1, 25
+; RV64I-NEXT:    call __moddi3
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    li a1, 3
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %v1 = srem i32 %v0, 25
+  %v2 = urem i32 %v1, 3
+  ret i32 %v2
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK: {{.*}}