diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index ce4c56c179..d7552dc377 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -39,15 +39,25 @@ static TCGv load_val;
 
 #include "exec/gen-icount.h"
 
+/*
+ * If an operation is being performed on less than TARGET_LONG_BITS,
+ * it may require the inputs to be sign- or zero-extended; which will
+ * depend on the exact operation being performed.
+ */
+typedef enum {
+    EXT_NONE,
+    EXT_SIGN,
+    EXT_ZERO,
+} DisasExtend;
+
 typedef struct DisasContext {
     DisasContextBase base;
     /* pc_succ_insn points to the instruction following base.pc_next */
     target_ulong pc_succ_insn;
     target_ulong priv_ver;
-    bool virt_enabled;
+    target_ulong misa;
     uint32_t opcode;
     uint32_t mstatus_fs;
-    target_ulong misa;
     uint32_t mem_idx;
     /* Remember the rounding mode encoded in the previous fp instruction,
        which we have already installed into env->fp_status.  Or -1 for
@@ -55,6 +65,8 @@ typedef struct DisasContext {
        to any system register, which includes CSR_FRM, so we do not have
        to reset this known value.  */
     int frm;
+    bool w;
+    bool virt_enabled;
     bool ext_ifencei;
     bool hlsx;
     /* vector extension */
@@ -64,7 +76,11 @@ typedef struct DisasContext {
     uint16_t vlen;
     uint16_t mlen;
     bool vl_eq_vlmax;
+    uint8_t ntemp;
     CPUState *cs;
+    TCGv zero;
+    /* Space for 3 operands plus 1 extra for address computation. */
+    TCGv temp[4];
 } DisasContext;
 
 static inline bool has_ext(DisasContext *ctx, uint32_t ext)
@@ -172,27 +188,64 @@ static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest)
     }
 }
 
-/* Wrapper for getting reg values - need to check of reg is zero since
- * cpu_gpr[0] is not actually allocated
+/*
+ * Wrappers for getting reg values.
+ *
+ * The $zero register does not have cpu_gpr[0] allocated -- we supply the
+ * constant zero as a source, and an uninitialized sink as destination.
+ *
+ * Further, we may provide an extension for word operations.
  */
-static void gen_get_gpr(DisasContext *ctx, TCGv t, int reg_num)
+static TCGv temp_new(DisasContext *ctx)
 {
-    if (reg_num == 0) {
-        tcg_gen_movi_tl(t, 0);
-    } else {
-        tcg_gen_mov_tl(t, cpu_gpr[reg_num]);
-    }
+    assert(ctx->ntemp < ARRAY_SIZE(ctx->temp));
+    return ctx->temp[ctx->ntemp++] = tcg_temp_new();
 }
 
-/* Wrapper for setting reg values - need to check of reg is zero since
- * cpu_gpr[0] is not actually allocated. this is more for safety purposes,
- * since we usually avoid calling the OP_TYPE_gen function if we see a write to
- * $zero
- */
-static void gen_set_gpr(DisasContext *ctx, int reg_num_dst, TCGv t)
+static TCGv get_gpr(DisasContext *ctx, int reg_num, DisasExtend ext)
 {
-    if (reg_num_dst != 0) {
-        tcg_gen_mov_tl(cpu_gpr[reg_num_dst], t);
+    TCGv t;
+
+    if (reg_num == 0) {
+        return ctx->zero;
+    }
+
+    switch (ctx->w ? ext : EXT_NONE) {
+    case EXT_NONE:
+        return cpu_gpr[reg_num];
+    case EXT_SIGN:
+        t = temp_new(ctx);
+        tcg_gen_ext32s_tl(t, cpu_gpr[reg_num]);
+        return t;
+    case EXT_ZERO:
+        t = temp_new(ctx);
+        tcg_gen_ext32u_tl(t, cpu_gpr[reg_num]);
+        return t;
+    }
+    g_assert_not_reached();
+}
+
+static void gen_get_gpr(DisasContext *ctx, TCGv t, int reg_num)
+{
+    tcg_gen_mov_tl(t, get_gpr(ctx, reg_num, EXT_NONE));
+}
+
+static TCGv __attribute__((unused)) dest_gpr(DisasContext *ctx, int reg_num)
+{
+    if (reg_num == 0 || ctx->w) {
+        return temp_new(ctx);
+    }
+    return cpu_gpr[reg_num];
+}
+
+static void gen_set_gpr(DisasContext *ctx, int reg_num, TCGv t)
+{
+    if (reg_num != 0) {
+        if (ctx->w) {
+            tcg_gen_ext32s_tl(cpu_gpr[reg_num], t);
+        } else {
+            tcg_gen_mov_tl(cpu_gpr[reg_num], t);
+        }
     }
 }
 
@@ -940,6 +993,11 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     ctx->mlen = 1 << (ctx->sew  + 3 - ctx->lmul);
     ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
     ctx->cs = cs;
+    ctx->w = false;
+    ctx->ntemp = 0;
+    memset(ctx->temp, 0, sizeof(ctx->temp));
+
+    ctx->zero = tcg_constant_tl(0);
 }
 
 static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu)
@@ -961,6 +1019,13 @@ static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
 
     decode_opc(env, ctx, opcode16);
     ctx->base.pc_next = ctx->pc_succ_insn;
+    ctx->w = false;
+
+    for (int i = ctx->ntemp - 1; i >= 0; --i) {
+        tcg_temp_free(ctx->temp[i]);
+        ctx->temp[i] = NULL;
+    }
+    ctx->ntemp = 0;
 
     if (ctx->base.is_jmp == DISAS_NEXT) {
         target_ulong page_start;