diff --git a/llvm/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp b/llvm/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
--- a/llvm/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
+++ b/llvm/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
@@ -124,6 +124,10 @@
   void emitLoadStoreSymbol(MCInst &Inst, unsigned Opcode, SMLoc IDLoc,
                            MCStreamer &Out, bool HasTmpReg);
 
+  // Helper to emit pseudo sign/zero extend instruction.
+  void emitPseudoExtend(MCInst &Inst, bool SignExtend, int64_t Width,
+                        SMLoc IDLoc, MCStreamer &Out);
+
   // Checks that a PseudoAddTPRel is using x4/tp in its second input operand.
   // Enforcing this using a restricted register class for the second input
   // operand of PseudoAddTPRel results in a poor diagnostic due to the fact
@@ -2299,6 +2303,35 @@
                     Opcode, IDLoc, Out);
 }
 
+void RISCVAsmParser::emitPseudoExtend(MCInst &Inst, bool SignExtend,
+                                      int64_t Width, SMLoc IDLoc,
+                                      MCStreamer &Out) {
+  // The sign/zero extend pseudo-instruction does two shifts, with the shift
+  // amounts dependent on the XLEN.
+  //
+  // The expansion looks like this
+  //
+  //    SLLI rd, rs, XLEN - Width
+  //    SR[A|R]I rd, rd, XLEN - Width
+  MCOperand DestReg = Inst.getOperand(0);
+  MCOperand SourceReg = Inst.getOperand(1);
+
+  unsigned SecondOpcode = SignExtend ? RISCV::SRAI : RISCV::SRLI;
+  int64_t ShAmt = (isRV64() ? 64 : 32) - Width;
+
+  assert(ShAmt > 0 && "Shift amount must be non-zero.");
+
+  emitToStreamer(Out, MCInstBuilder(RISCV::SLLI)
+                          .addOperand(DestReg)
+                          .addOperand(SourceReg)
+                          .addImm(ShAmt));
+
+  emitToStreamer(Out, MCInstBuilder(SecondOpcode)
+                          .addOperand(DestReg)
+                          .addOperand(DestReg)
+                          .addImm(ShAmt));
+}
+
 bool RISCVAsmParser::checkPseudoAddTPRel(MCInst &Inst,
                                          OperandVector &Operands) {
   assert(Inst.getOpcode() == RISCV::PseudoAddTPRel && "Invalid instruction");
@@ -2461,6 +2494,18 @@
     if (checkPseudoAddTPRel(Inst, Operands))
       return true;
     break;
+  case RISCV::PseudoSEXT_B:
+    emitPseudoExtend(Inst, /*SignExtend=*/true, /*Width=*/8, IDLoc, Out);
+    return false;
+  case RISCV::PseudoSEXT_H:
+    emitPseudoExtend(Inst, /*SignExtend=*/true, /*Width=*/16, IDLoc, Out);
+    return false;
+  case RISCV::PseudoZEXT_H:
+    emitPseudoExtend(Inst, /*SignExtend=*/false, /*Width=*/16, IDLoc, Out);
+    return false;
+  case RISCV::PseudoZEXT_W:
+    emitPseudoExtend(Inst, /*SignExtend=*/false, /*Width=*/32, IDLoc, Out);
+    return false;
   }
 
   emitToStreamer(Out, Inst);
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.td b/llvm/lib/Target/RISCV/RISCVInstrInfo.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfo.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfo.td
@@ -803,6 +803,8 @@
 def : MnemonicAlias<"scall", "ecall">;
 def : MnemonicAlias<"sbreak", "ebreak">;
 
+def : InstAlias<"zext.b $rd, $rs", (ANDI GPR:$rd, GPR:$rs, 255)>;
+
 //===----------------------------------------------------------------------===//
 // Pseudo-instructions and codegen patterns
 //
@@ -1049,6 +1051,22 @@
 def PseudoLA_TLS_GD : Pseudo<(outs GPR:$dst), (ins bare_symbol:$src), [],
                              "la.tls.gd", "$dst, $src">;
 
+
+let hasSideEffects = 0, mayLoad = 0, mayStore = 0, isCodeGenOnly = 0,
+    isAsmParserOnly = 1 in {
+def PseudoSEXT_B : Pseudo<(outs GPR:$rd), (ins GPR:$rs), [], "sext.b", "$rd, $rs">;
+def PseudoSEXT_H : Pseudo<(outs GPR:$rd), (ins GPR:$rs), [], "sext.h", "$rd, $rs">;
+// rv64's sext.w is defined above, using InstAlias<"sext.w ...
+
+// zext.b is defined above, using InstAlias<"zext.b ...
+// def PseudoZEXT_B : Pseudo<(outs GPR:$rd), (ins GPR:$rs), [], "zext.b", "$rd, $rs">;
+def PseudoZEXT_H : Pseudo<(outs GPR:$rd), (ins GPR:$rs), [], "zext.h", "$rd, $rs">;
+
+let Predicates = [IsRV64] in {
+def PseudoZEXT_W : Pseudo<(outs GPR:$rd), (ins GPR:$rs), [], "zext.w", "$rd, $rs">;
+} // Predicates = [IsRV64]
+}
+
 /// Loads
 
 multiclass LdPat<PatFrag LoadOp, RVInst Inst> {
diff --git a/llvm/test/CodeGen/RISCV/alu8.ll b/llvm/test/CodeGen/RISCV/alu8.ll
--- a/llvm/test/CodeGen/RISCV/alu8.ll
+++ b/llvm/test/CodeGen/RISCV/alu8.ll
@@ -44,13 +44,13 @@
 define i8 @sltiu(i8 %a) nounwind {
 ; RV32I-LABEL: sltiu:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    sltiu a0, a0, 3
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: sltiu:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    sltiu a0, a0, 3
 ; RV64I-NEXT:    ret
   %1 = icmp ult i8 %a, 3
@@ -215,15 +215,15 @@
 define i8 @sltu(i8 %a, i8 %b) nounwind {
 ; RV32I-LABEL: sltu:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a1, a1, 255
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a1, a1
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    sltu a0, a0, a1
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: sltu:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a1, a1, 255
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a1, a1
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    sltu a0, a0, a1
 ; RV64I-NEXT:    ret
   %1 = icmp ult i8 %a, %b
@@ -248,13 +248,13 @@
 define i8 @srl(i8 %a, i8 %b) nounwind {
 ; RV32I-LABEL: srl:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    srl a0, a0, a1
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: srl:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    srl a0, a0, a1
 ; RV64I-NEXT:    ret
   %1 = lshr i8 %a, %b
diff --git a/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll b/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
--- a/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
+++ b/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
@@ -29,9 +29,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a2, (a3)
@@ -66,9 +66,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a2, (a3)
@@ -107,9 +107,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB1_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a2, (a3)
@@ -144,9 +144,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB1_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a2, (a3)
@@ -185,9 +185,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB2_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a2, (a3)
@@ -222,9 +222,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB2_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a2, (a3)
@@ -263,9 +263,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a2, (a3)
@@ -300,9 +300,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a2, (a3)
@@ -341,9 +341,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a2, (a3)
@@ -378,9 +378,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a2, (a3)
@@ -419,9 +419,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a2, (a3)
@@ -456,9 +456,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a2, (a3)
@@ -497,9 +497,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a2, (a3)
@@ -534,9 +534,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a2, (a3)
@@ -575,9 +575,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a2, (a3)
@@ -612,9 +612,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a2, (a3)
@@ -653,9 +653,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB8_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a2, (a3)
@@ -690,9 +690,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB8_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a2, (a3)
@@ -731,9 +731,9 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a4, zero, 255
 ; RV32IA-NEXT:    sll a4, a4, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
-; RV32IA-NEXT:    andi a2, a2, 255
+; RV32IA-NEXT:    zext.b a2, a2
 ; RV32IA-NEXT:    sll a0, a2, a0
 ; RV32IA-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a2, (a3)
@@ -768,9 +768,9 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a4, zero, 255
 ; RV64IA-NEXT:    sllw a4, a4, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
-; RV64IA-NEXT:    andi a2, a2, 255
+; RV64IA-NEXT:    zext.b a2, a2
 ; RV64IA-NEXT:    sllw a0, a2, a0
 ; RV64IA-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a2, (a3)
diff --git a/llvm/test/CodeGen/RISCV/atomic-rmw.ll b/llvm/test/CodeGen/RISCV/atomic-rmw.ll
--- a/llvm/test/CodeGen/RISCV/atomic-rmw.ll
+++ b/llvm/test/CodeGen/RISCV/atomic-rmw.ll
@@ -26,7 +26,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -57,7 +57,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -92,7 +92,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB1_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -123,7 +123,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB1_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -158,7 +158,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB2_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -189,7 +189,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB2_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -224,7 +224,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -255,7 +255,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -290,7 +290,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -321,7 +321,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -356,7 +356,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -387,7 +387,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -422,7 +422,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -453,7 +453,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -488,7 +488,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -519,7 +519,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -554,7 +554,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB8_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -585,7 +585,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB8_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -620,7 +620,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -651,7 +651,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -686,7 +686,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -717,7 +717,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -752,7 +752,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -783,7 +783,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -818,7 +818,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -849,7 +849,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -884,7 +884,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB13_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -915,7 +915,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB13_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -950,7 +950,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB14_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -981,7 +981,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB14_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -1017,7 +1017,7 @@
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
 ; RV32IA-NEXT:    not a3, a3
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    or a1, a3, a1
 ; RV32IA-NEXT:    amoand.w a1, a1, (a2)
@@ -1042,7 +1042,7 @@
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
 ; RV64IA-NEXT:    not a3, a3
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    or a1, a3, a1
 ; RV64IA-NEXT:    amoand.w a1, a1, (a2)
@@ -1071,7 +1071,7 @@
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
 ; RV32IA-NEXT:    not a3, a3
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    or a1, a3, a1
 ; RV32IA-NEXT:    amoand.w.aq a1, a1, (a2)
@@ -1096,7 +1096,7 @@
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
 ; RV64IA-NEXT:    not a3, a3
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    or a1, a3, a1
 ; RV64IA-NEXT:    amoand.w.aq a1, a1, (a2)
@@ -1125,7 +1125,7 @@
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
 ; RV32IA-NEXT:    not a3, a3
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    or a1, a3, a1
 ; RV32IA-NEXT:    amoand.w.rl a1, a1, (a2)
@@ -1150,7 +1150,7 @@
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
 ; RV64IA-NEXT:    not a3, a3
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    or a1, a3, a1
 ; RV64IA-NEXT:    amoand.w.rl a1, a1, (a2)
@@ -1179,7 +1179,7 @@
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
 ; RV32IA-NEXT:    not a3, a3
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    or a1, a3, a1
 ; RV32IA-NEXT:    amoand.w.aqrl a1, a1, (a2)
@@ -1204,7 +1204,7 @@
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
 ; RV64IA-NEXT:    not a3, a3
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    or a1, a3, a1
 ; RV64IA-NEXT:    amoand.w.aqrl a1, a1, (a2)
@@ -1233,7 +1233,7 @@
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
 ; RV32IA-NEXT:    not a3, a3
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    or a1, a3, a1
 ; RV32IA-NEXT:    amoand.w.aqrl a1, a1, (a2)
@@ -1258,7 +1258,7 @@
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
 ; RV64IA-NEXT:    not a3, a3
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    or a1, a3, a1
 ; RV64IA-NEXT:    amoand.w.aqrl a1, a1, (a2)
@@ -1286,7 +1286,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB20_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -1318,7 +1318,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB20_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -1354,7 +1354,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB21_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -1386,7 +1386,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB21_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -1422,7 +1422,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB22_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a2)
@@ -1454,7 +1454,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB22_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a2)
@@ -1490,7 +1490,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB23_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a2)
@@ -1522,7 +1522,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB23_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a2)
@@ -1558,7 +1558,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB24_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -1590,7 +1590,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB24_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a2)
@@ -1624,7 +1624,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoor.w a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1645,7 +1645,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoor.w a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1670,7 +1670,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoor.w.aq a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1691,7 +1691,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoor.w.aq a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1716,7 +1716,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoor.w.rl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1737,7 +1737,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoor.w.rl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1762,7 +1762,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoor.w.aqrl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1783,7 +1783,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoor.w.aqrl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1808,7 +1808,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoor.w.aqrl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1829,7 +1829,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoor.w.aqrl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1854,7 +1854,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoxor.w a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1875,7 +1875,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoxor.w a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1900,7 +1900,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoxor.w.aq a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1921,7 +1921,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoxor.w.aq a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1946,7 +1946,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoxor.w.rl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -1967,7 +1967,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoxor.w.rl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -1992,7 +1992,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoxor.w.aqrl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -2013,7 +2013,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoxor.w.aqrl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -2038,7 +2038,7 @@
 ; RV32IA-NEXT:    andi a2, a0, -4
 ; RV32IA-NEXT:    slli a0, a0, 3
 ; RV32IA-NEXT:    andi a0, a0, 24
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:    amoxor.w.aqrl a1, a1, (a2)
 ; RV32IA-NEXT:    srl a0, a1, a0
@@ -2059,7 +2059,7 @@
 ; RV64IA-NEXT:    andi a2, a0, -4
 ; RV64IA-NEXT:    slli a0, a0, 3
 ; RV64IA-NEXT:    andi a0, a0, 24
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:    amoxor.w.aqrl a1, a1, (a2)
 ; RV64IA-NEXT:    srlw a0, a1, a0
@@ -3559,7 +3559,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB45_2
 ; RV32I-NEXT:  .LBB45_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB45_2 Depth=1
@@ -3573,7 +3573,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB45_4
 ; RV32I-NEXT:  .LBB45_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bltu s1, a0, .LBB45_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3596,7 +3596,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB45_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a6)
@@ -3624,7 +3624,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB45_2
 ; RV64I-NEXT:  .LBB45_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB45_2 Depth=1
@@ -3638,7 +3638,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB45_4
 ; RV64I-NEXT:  .LBB45_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bltu s1, a0, .LBB45_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3661,7 +3661,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB45_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a6)
@@ -3693,7 +3693,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB46_2
 ; RV32I-NEXT:  .LBB46_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB46_2 Depth=1
@@ -3707,7 +3707,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB46_4
 ; RV32I-NEXT:  .LBB46_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bltu s1, a0, .LBB46_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3730,7 +3730,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB46_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a6)
@@ -3758,7 +3758,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB46_2
 ; RV64I-NEXT:  .LBB46_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB46_2 Depth=1
@@ -3772,7 +3772,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB46_4
 ; RV64I-NEXT:  .LBB46_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bltu s1, a0, .LBB46_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3795,7 +3795,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB46_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a6)
@@ -3827,7 +3827,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB47_2
 ; RV32I-NEXT:  .LBB47_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB47_2 Depth=1
@@ -3841,7 +3841,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB47_4
 ; RV32I-NEXT:  .LBB47_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bltu s1, a0, .LBB47_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3864,7 +3864,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB47_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a6)
@@ -3892,7 +3892,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB47_2
 ; RV64I-NEXT:  .LBB47_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB47_2 Depth=1
@@ -3906,7 +3906,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB47_4
 ; RV64I-NEXT:  .LBB47_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bltu s1, a0, .LBB47_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3929,7 +3929,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB47_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a6)
@@ -3961,7 +3961,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB48_2
 ; RV32I-NEXT:  .LBB48_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB48_2 Depth=1
@@ -3975,7 +3975,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB48_4
 ; RV32I-NEXT:  .LBB48_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bltu s1, a0, .LBB48_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -3998,7 +3998,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB48_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a6)
@@ -4026,7 +4026,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB48_2
 ; RV64I-NEXT:  .LBB48_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB48_2 Depth=1
@@ -4040,7 +4040,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB48_4
 ; RV64I-NEXT:  .LBB48_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bltu s1, a0, .LBB48_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4063,7 +4063,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB48_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a6)
@@ -4095,7 +4095,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB49_2
 ; RV32I-NEXT:  .LBB49_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB49_2 Depth=1
@@ -4109,7 +4109,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB49_4
 ; RV32I-NEXT:  .LBB49_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bltu s1, a0, .LBB49_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4132,7 +4132,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB49_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a6)
@@ -4160,7 +4160,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB49_2
 ; RV64I-NEXT:  .LBB49_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB49_2 Depth=1
@@ -4174,7 +4174,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB49_4
 ; RV64I-NEXT:  .LBB49_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bltu s1, a0, .LBB49_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4197,7 +4197,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB49_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a6)
@@ -4229,7 +4229,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB50_2
 ; RV32I-NEXT:  .LBB50_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB50_2 Depth=1
@@ -4243,7 +4243,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB50_4
 ; RV32I-NEXT:  .LBB50_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bgeu s1, a0, .LBB50_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4266,7 +4266,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB50_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a6)
@@ -4294,7 +4294,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB50_2
 ; RV64I-NEXT:  .LBB50_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB50_2 Depth=1
@@ -4308,7 +4308,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB50_4
 ; RV64I-NEXT:  .LBB50_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bgeu s1, a0, .LBB50_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4331,7 +4331,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB50_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a6)
@@ -4363,7 +4363,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB51_2
 ; RV32I-NEXT:  .LBB51_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB51_2 Depth=1
@@ -4377,7 +4377,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB51_4
 ; RV32I-NEXT:  .LBB51_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bgeu s1, a0, .LBB51_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4400,7 +4400,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB51_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a6)
@@ -4428,7 +4428,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB51_2
 ; RV64I-NEXT:  .LBB51_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB51_2 Depth=1
@@ -4442,7 +4442,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB51_4
 ; RV64I-NEXT:  .LBB51_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bgeu s1, a0, .LBB51_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4465,7 +4465,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB51_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a6)
@@ -4497,7 +4497,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB52_2
 ; RV32I-NEXT:  .LBB52_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB52_2 Depth=1
@@ -4511,7 +4511,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB52_4
 ; RV32I-NEXT:  .LBB52_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bgeu s1, a0, .LBB52_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4534,7 +4534,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB52_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w a4, (a6)
@@ -4562,7 +4562,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB52_2
 ; RV64I-NEXT:  .LBB52_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB52_2 Depth=1
@@ -4576,7 +4576,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB52_4
 ; RV64I-NEXT:  .LBB52_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bgeu s1, a0, .LBB52_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4599,7 +4599,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB52_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w a4, (a6)
@@ -4631,7 +4631,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB53_2
 ; RV32I-NEXT:  .LBB53_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB53_2 Depth=1
@@ -4645,7 +4645,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB53_4
 ; RV32I-NEXT:  .LBB53_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bgeu s1, a0, .LBB53_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4668,7 +4668,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB53_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aq a4, (a6)
@@ -4696,7 +4696,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB53_2
 ; RV64I-NEXT:  .LBB53_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB53_2 Depth=1
@@ -4710,7 +4710,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB53_4
 ; RV64I-NEXT:  .LBB53_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bgeu s1, a0, .LBB53_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4733,7 +4733,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB53_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aq a4, (a6)
@@ -4765,7 +4765,7 @@
 ; RV32I-NEXT:    mv s0, a0
 ; RV32I-NEXT:    lbu a3, 0(a0)
 ; RV32I-NEXT:    mv s2, a1
-; RV32I-NEXT:    andi s1, a1, 255
+; RV32I-NEXT:    zext.b s1, a1
 ; RV32I-NEXT:    j .LBB54_2
 ; RV32I-NEXT:  .LBB54_1: # %atomicrmw.start
 ; RV32I-NEXT:    # in Loop: Header=BB54_2 Depth=1
@@ -4779,7 +4779,7 @@
 ; RV32I-NEXT:    bnez a0, .LBB54_4
 ; RV32I-NEXT:  .LBB54_2: # %atomicrmw.start
 ; RV32I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV32I-NEXT:    andi a0, a3, 255
+; RV32I-NEXT:    zext.b a0, a3
 ; RV32I-NEXT:    mv a2, a3
 ; RV32I-NEXT:    bgeu s1, a0, .LBB54_1
 ; RV32I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4802,7 +4802,7 @@
 ; RV32IA-NEXT:    andi a0, a0, 24
 ; RV32IA-NEXT:    addi a3, zero, 255
 ; RV32IA-NEXT:    sll a3, a3, a0
-; RV32IA-NEXT:    andi a1, a1, 255
+; RV32IA-NEXT:    zext.b a1, a1
 ; RV32IA-NEXT:    sll a1, a1, a0
 ; RV32IA-NEXT:  .LBB54_1: # =>This Inner Loop Header: Depth=1
 ; RV32IA-NEXT:    lr.w.aqrl a4, (a6)
@@ -4830,7 +4830,7 @@
 ; RV64I-NEXT:    mv s0, a0
 ; RV64I-NEXT:    lbu a3, 0(a0)
 ; RV64I-NEXT:    mv s2, a1
-; RV64I-NEXT:    andi s1, a1, 255
+; RV64I-NEXT:    zext.b s1, a1
 ; RV64I-NEXT:    j .LBB54_2
 ; RV64I-NEXT:  .LBB54_1: # %atomicrmw.start
 ; RV64I-NEXT:    # in Loop: Header=BB54_2 Depth=1
@@ -4844,7 +4844,7 @@
 ; RV64I-NEXT:    bnez a0, .LBB54_4
 ; RV64I-NEXT:  .LBB54_2: # %atomicrmw.start
 ; RV64I-NEXT:    # =>This Inner Loop Header: Depth=1
-; RV64I-NEXT:    andi a0, a3, 255
+; RV64I-NEXT:    zext.b a0, a3
 ; RV64I-NEXT:    mv a2, a3
 ; RV64I-NEXT:    bgeu s1, a0, .LBB54_1
 ; RV64I-NEXT:  # %bb.3: # %atomicrmw.start
@@ -4867,7 +4867,7 @@
 ; RV64IA-NEXT:    andi a0, a0, 24
 ; RV64IA-NEXT:    addi a3, zero, 255
 ; RV64IA-NEXT:    sllw a3, a3, a0
-; RV64IA-NEXT:    andi a1, a1, 255
+; RV64IA-NEXT:    zext.b a1, a1
 ; RV64IA-NEXT:    sllw a1, a1, a0
 ; RV64IA-NEXT:  .LBB54_1: # =>This Inner Loop Header: Depth=1
 ; RV64IA-NEXT:    lr.w.aqrl a4, (a6)
diff --git a/llvm/test/CodeGen/RISCV/bswap-ctlz-cttz-ctpop.ll b/llvm/test/CodeGen/RISCV/bswap-ctlz-cttz-ctpop.ll
--- a/llvm/test/CodeGen/RISCV/bswap-ctlz-cttz-ctpop.ll
+++ b/llvm/test/CodeGen/RISCV/bswap-ctlz-cttz-ctpop.ll
@@ -80,8 +80,8 @@
 ; RV32I-LABEL: test_cttz_i8:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
-; RV32I-NEXT:    sw ra, 12(sp)
-; RV32I-NEXT:    andi a1, a0, 255
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    zext.b a1, a0
 ; RV32I-NEXT:    beqz a1, .LBB3_2
 ; RV32I-NEXT:  # %bb.1: # %cond.false
 ; RV32I-NEXT:    addi a1, a0, -1
diff --git a/llvm/test/CodeGen/RISCV/calling-conv-ilp32-ilp32f-ilp32d-common.ll b/llvm/test/CodeGen/RISCV/calling-conv-ilp32-ilp32f-ilp32d-common.ll
--- a/llvm/test/CodeGen/RISCV/calling-conv-ilp32-ilp32f-ilp32d-common.ll
+++ b/llvm/test/CodeGen/RISCV/calling-conv-ilp32-ilp32f-ilp32d-common.ll
@@ -84,7 +84,7 @@
 ; RV32I-FPELIM:       # %bb.0:
 ; RV32I-FPELIM-NEXT:    lw t0, 4(sp)
 ; RV32I-FPELIM-NEXT:    lw t1, 0(sp)
-; RV32I-FPELIM-NEXT:    andi t2, a0, 255
+; RV32I-FPELIM-NEXT:    zext.b t2, a0
 ; RV32I-FPELIM-NEXT:    lui a0, 16
 ; RV32I-FPELIM-NEXT:    addi a0, a0, -1
 ; RV32I-FPELIM-NEXT:    and a0, a1, a0
@@ -108,7 +108,7 @@
 ; RV32I-WITHFP-NEXT:    addi s0, sp, 16
 ; RV32I-WITHFP-NEXT:    lw t0, 4(s0)
 ; RV32I-WITHFP-NEXT:    lw t1, 0(s0)
-; RV32I-WITHFP-NEXT:    andi t2, a0, 255
+; RV32I-WITHFP-NEXT:    zext.b t2, a0
 ; RV32I-WITHFP-NEXT:    lui a0, 16
 ; RV32I-WITHFP-NEXT:    addi a0, a0, -1
 ; RV32I-WITHFP-NEXT:    and a0, a1, a0
diff --git a/llvm/test/CodeGen/RISCV/calling-conv-lp64-lp64f-lp64d-common.ll b/llvm/test/CodeGen/RISCV/calling-conv-lp64-lp64f-lp64d-common.ll
--- a/llvm/test/CodeGen/RISCV/calling-conv-lp64-lp64f-lp64d-common.ll
+++ b/llvm/test/CodeGen/RISCV/calling-conv-lp64-lp64f-lp64d-common.ll
@@ -50,7 +50,7 @@
 ; RV64I:       # %bb.0:
 ; RV64I-NEXT:    lw t0, 8(sp)
 ; RV64I-NEXT:    ld t1, 0(sp)
-; RV64I-NEXT:    andi t2, a0, 255
+; RV64I-NEXT:    zext.b t2, a0
 ; RV64I-NEXT:    lui a0, 16
 ; RV64I-NEXT:    addiw a0, a0, -1
 ; RV64I-NEXT:    and a0, a1, a0
diff --git a/llvm/test/CodeGen/RISCV/calling-conv-sext-zext.ll b/llvm/test/CodeGen/RISCV/calling-conv-sext-zext.ll
--- a/llvm/test/CodeGen/RISCV/calling-conv-sext-zext.ll
+++ b/llvm/test/CodeGen/RISCV/calling-conv-sext-zext.ll
@@ -122,7 +122,7 @@
 define zeroext i8 @sint8_arg_to_uint8_ret(i8 signext %a) nounwind {
 ; RV32I-LABEL: sint8_arg_to_uint8_ret:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    ret
   ret i8 %a
 }
@@ -131,10 +131,10 @@
 ; RV32I-LABEL: pass_sint8_as_uint8:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
-; RV32I-NEXT:    sw ra, 12(sp)
-; RV32I-NEXT:    andi a0, a0, 255
-; RV32I-NEXT:    call receive_uint8
-; RV32I-NEXT:    lw ra, 12(sp)
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    zext.b a0, a0
+; RV32I-NEXT:    call receive_uint8@plt
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
 ; RV32I-NEXT:    addi sp, sp, 16
 ; RV32I-NEXT:    ret
   call void @receive_uint8(i8 zeroext %a)
@@ -147,10 +147,10 @@
 ; RV32I-LABEL: ret_callresult_sint8_as_uint8:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
-; RV32I-NEXT:    sw ra, 12(sp)
-; RV32I-NEXT:    call return_sint8
-; RV32I-NEXT:    andi a0, a0, 255
-; RV32I-NEXT:    lw ra, 12(sp)
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    call return_sint8@plt
+; RV32I-NEXT:    zext.b a0, a0
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
 ; RV32I-NEXT:    addi sp, sp, 16
 ; RV32I-NEXT:    ret
   %1 = call signext i8 @return_sint8()
@@ -229,7 +229,7 @@
 define zeroext i8 @anyint32_arg_to_uint8_ret(i32 signext %a) nounwind {
 ; RV32I-LABEL: anyint32_arg_to_uint8_ret:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    ret
   %1 = trunc i32 %a to i8
   ret i8 %1
@@ -239,10 +239,10 @@
 ; RV32I-LABEL: pass_anyint32_as_uint8:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
-; RV32I-NEXT:    sw ra, 12(sp)
-; RV32I-NEXT:    andi a0, a0, 255
-; RV32I-NEXT:    call receive_uint8
-; RV32I-NEXT:    lw ra, 12(sp)
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    zext.b a0, a0
+; RV32I-NEXT:    call receive_uint8@plt
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
 ; RV32I-NEXT:    addi sp, sp, 16
 ; RV32I-NEXT:    ret
   %1 = trunc i32 %a to i8
@@ -256,10 +256,10 @@
 ; RV32I-LABEL: ret_callresult_anyint32_as_uint8:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
-; RV32I-NEXT:    sw ra, 12(sp)
-; RV32I-NEXT:    call return_anyint32
-; RV32I-NEXT:    andi a0, a0, 255
-; RV32I-NEXT:    lw ra, 12(sp)
+; RV32I-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT:    call return_anyint32@plt
+; RV32I-NEXT:    zext.b a0, a0
+; RV32I-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
 ; RV32I-NEXT:    addi sp, sp, 16
 ; RV32I-NEXT:    ret
   %1 = call signext i32 @return_anyint32()
diff --git a/llvm/test/CodeGen/RISCV/rv32Zbbp.ll b/llvm/test/CodeGen/RISCV/rv32Zbbp.ll
--- a/llvm/test/CodeGen/RISCV/rv32Zbbp.ll
+++ b/llvm/test/CodeGen/RISCV/rv32Zbbp.ll
@@ -895,7 +895,7 @@
 define i32 @packh_i32(i32 %a, i32 %b) nounwind {
 ; RV32I-LABEL: packh_i32:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    slli a1, a1, 8
 ; RV32I-NEXT:    lui a2, 16
 ; RV32I-NEXT:    addi a2, a2, -256
@@ -927,7 +927,7 @@
 define i64 @packh_i64(i64 %a, i64 %b) nounwind {
 ; RV32I-LABEL: packh_i64:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    slli a1, a2, 8
 ; RV32I-NEXT:    lui a2, 16
 ; RV32I-NEXT:    addi a2, a2, -256
diff --git a/llvm/test/CodeGen/RISCV/rv64Zbbp.ll b/llvm/test/CodeGen/RISCV/rv64Zbbp.ll
--- a/llvm/test/CodeGen/RISCV/rv64Zbbp.ll
+++ b/llvm/test/CodeGen/RISCV/rv64Zbbp.ll
@@ -732,7 +732,7 @@
 define signext i32 @packh_i32(i32 signext %a, i32 signext %b) nounwind {
 ; RV64I-LABEL: packh_i32:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    slli a1, a1, 8
 ; RV64I-NEXT:    lui a2, 16
 ; RV64I-NEXT:    addiw a2, a2, -256
@@ -764,7 +764,7 @@
 define i64 @packh_i64(i64 %a, i64 %b) nounwind {
 ; RV64I-LABEL: packh_i64:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    slli a1, a1, 8
 ; RV64I-NEXT:    lui a2, 16
 ; RV64I-NEXT:    addiw a2, a2, -256
diff --git a/llvm/test/CodeGen/RISCV/sext-zext-trunc.ll b/llvm/test/CodeGen/RISCV/sext-zext-trunc.ll
--- a/llvm/test/CodeGen/RISCV/sext-zext-trunc.ll
+++ b/llvm/test/CodeGen/RISCV/sext-zext-trunc.ll
@@ -225,12 +225,12 @@
 define i16 @zext_i8_to_i16(i8 %a) nounwind {
 ; RV32I-LABEL: zext_i8_to_i16:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: zext_i8_to_i16:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    ret
   %1 = zext i8 %a to i16
   ret i16 %1
@@ -239,12 +239,12 @@
 define i32 @zext_i8_to_i32(i8 %a) nounwind {
 ; RV32I-LABEL: zext_i8_to_i32:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: zext_i8_to_i32:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    ret
   %1 = zext i8 %a to i32
   ret i32 %1
@@ -253,13 +253,13 @@
 define i64 @zext_i8_to_i64(i8 %a) nounwind {
 ; RV32I-LABEL: zext_i8_to_i64:
 ; RV32I:       # %bb.0:
-; RV32I-NEXT:    andi a0, a0, 255
+; RV32I-NEXT:    zext.b a0, a0
 ; RV32I-NEXT:    mv a1, zero
 ; RV32I-NEXT:    ret
 ;
 ; RV64I-LABEL: zext_i8_to_i64:
 ; RV64I:       # %bb.0:
-; RV64I-NEXT:    andi a0, a0, 255
+; RV64I-NEXT:    zext.b a0, a0
 ; RV64I-NEXT:    ret
   %1 = zext i8 %a to i64
   ret i64 %1
diff --git a/llvm/test/MC/RISCV/rv32i-aliases-invalid.s b/llvm/test/MC/RISCV/rv32i-aliases-invalid.s
--- a/llvm/test/MC/RISCV/rv32i-aliases-invalid.s
+++ b/llvm/test/MC/RISCV/rv32i-aliases-invalid.s
@@ -11,6 +11,7 @@
 
 negw x1, x2   # CHECK: :[[@LINE]]:1: error: instruction requires the following: RV64I Base Instruction Set
 sext.w x3, x4 # CHECK: :[[@LINE]]:1: error: instruction requires the following: RV64I Base Instruction Set
+zext.w x3, x4 # CHECK: :[[@LINE]]:1: error: instruction requires the following: RV64I Base Instruction Set
 
 sll x2, x3, 32  # CHECK: :[[@LINE]]:13: error: immediate must be an integer in the range [0, 31]
 srl x2, x3, 32  # CHECK: :[[@LINE]]:13: error: immediate must be an integer in the range [0, 31]
diff --git a/llvm/test/MC/RISCV/rv32i-aliases-valid.s b/llvm/test/MC/RISCV/rv32i-aliases-valid.s
--- a/llvm/test/MC/RISCV/rv32i-aliases-valid.s
+++ b/llvm/test/MC/RISCV/rv32i-aliases-valid.s
@@ -121,3 +121,19 @@
 sh x10, (x11)
 # CHECK-EXPAND: sw a0, 0(a1)
 sw x10, (x11)
+
+# CHECK-EXPAND: slli a0, a1, 24
+# CHECK-EXPAND: srai a0, a0, 24
+sext.b x10, x11
+
+# CHECK-EXPAND: slli a0, a1, 16
+# CHECK-EXPAND: srai a0, a0, 16
+sext.h x10, x11
+
+# CHECK-INST: andi a0, a1, 255
+# CHECK-ALIAS: zext.b a0, a1
+zext.b x10, x11
+
+# CHECK-EXPAND: slli a0, a1, 16
+# CHECK-EXPAND: srli a0, a0, 16
+zext.h x10, x11
diff --git a/llvm/test/MC/RISCV/rv64i-aliases-valid.s b/llvm/test/MC/RISCV/rv64i-aliases-valid.s
--- a/llvm/test/MC/RISCV/rv64i-aliases-valid.s
+++ b/llvm/test/MC/RISCV/rv64i-aliases-valid.s
@@ -199,3 +199,23 @@
 ld x10, (x11)
 # CHECK-EXPAND: sd a0, 0(a1)
 sd x10, (x11)
+
+# CHECK-EXPAND: slli a0, a1, 56
+# CHECK-EXPAND: srai a0, a0, 56
+sext.b x10, x11
+
+# CHECK-EXPAND: slli a0, a1, 48
+# CHECK-EXPAND: srai a0, a0, 48
+sext.h x10, x11
+
+# CHECK-INST: andi a0, a1, 255
+# CHECK-ALIAS: zext.b a0, a1
+zext.b x10, x11
+
+# CHECK-EXPAND: slli a0, a1, 48
+# CHECK-EXPAND: srli a0, a0, 48
+zext.h x10, x11
+
+# CHECK-EXPAND: slli a0, a1, 32
+# CHECK-EXPAND: srli a0, a0, 32
+zext.w x10, x11