Re: [Qemu-devel] [RFC 4/6] target-ppc: add cmprb instruction

[Richard Henderson]

On 07/12/2016 11:33 PM, Nikunj A Dadhania wrote:
> +/* cmprb - range comparison: isupper, isaplha, islower*/
> +static void gen_cmprb(DisasContext *ctx)
> +{
> +    TCGLabel *lab1 = gen_new_label();
> +    TCGLabel *lab2 = gen_new_label();
> +    TCGv src1 = tcg_temp_local_new();
> +    TCGv src2 = tcg_temp_local_new();
> +    TCGv src2lo = tcg_temp_local_new();
> +    TCGv src2hi = tcg_temp_local_new();
> +
> +    tcg_gen_andi_tl(src1, cpu_gpr[rA(ctx->opcode)], 0xFF);
> +    tcg_gen_andi_tl(src2, cpu_gpr[rB(ctx->opcode)], 0xFFFFFFFF);

There's no point in this mask, since it's covered by

> +
> +    tcg_gen_andi_tl(src2lo, src2, 0xFF);
> +    tcg_gen_shri_tl(src2hi, src2, 8);
> +    tcg_gen_andi_tl(src2hi, src2hi, 0xFF);

these ones.

> +
> +    tcg_gen_brcond_tl(TCG_COND_GTU, src1, src2hi, lab1);
> +    tcg_gen_brcond_tl(TCG_COND_LTU, src1, src2lo, lab1);
> +    tcg_gen_movi_i32(cpu_crf[crfD(ctx->opcode)], 1 << CRF_GT);
> +    tcg_gen_br(lab2);
> +    gen_set_label(lab1);
> +
> +    if (ctx->opcode & 0x00200000) {
> +        tcg_gen_shri_tl(src2hi, src2, 24);
> +        tcg_gen_andi_tl(src2hi, src2hi, 0xFF);
> +        tcg_gen_shri_tl(src2lo, src2, 16);
> +        tcg_gen_andi_tl(src2lo, src2lo, 0xFF);
> +        tcg_gen_brcond_tl(TCG_COND_GTU, src1, src2hi, lab2);
> +        tcg_gen_brcond_tl(TCG_COND_LTU, src1, src2lo, lab2);
> +        tcg_gen_movi_i32(cpu_crf[crfD(ctx->opcode)], 1 << CRF_GT);
> +    }
> +    gen_set_label(lab2);
> +    tcg_temp_free(src1);
> +    tcg_temp_free(src2);
> +    tcg_temp_free(src2lo);
> +    tcg_temp_free(src2hi);
> +}

You've forgotten to clear crf in the false case.

This is better implemented without branches, like

  TCGv_i32 src1, src2, src2lo, src2hi;
  TCGv_i32 crf = cpu_crf[cdfD(ctx->opcode)];

  // allocate all 4 "src" temps

  tcg_gen_trunc_tl_i32(src1, cpu_gpr[rA(ctx->opcode)]);
  tcg_gen_trunc_tl_i32(src2, cpu_gpr[rB(ctx->opcode)]);

  tcg_gen_ext8u_i32(src2lo, src2);
  tcg_gen_shri_i32(src2, src2, 8);
  tcg_gen_extu8_i32(src2hi, src2hi);

  tcg_gen_setcond_tl(TCG_COND_LEU, src2lo, src2lo, src1);
  tcg_gen_setcond_tl(TCG_COND_LEU, src2hi, src1, src2hi);
  tcg_gen_and_tl(crf, src2lo, src2hi);

  if (ctx->opcode & 0x00200000) {
    tcg_gen_shri_i32(src2, src2, 8);
    tcg_gen_ext8u_i32(src2lo, src2);
    tcg_gen_shri_i32(src2, src2, 8);
    tcg_gen_ext8u_i32(src2hi, src2);
    tcg_gen_setcond_i32(TCG_COND_LEU, src2lo, src2lo, src1);
    tcg_gen_setcond_i32(TCG_COND_LEU, src2hi, src1, src2hi);
    tcg_gen_and_i32(src2lo, src2lo, src2hi);
    tcg_gen_or_i32(crf, crf, src2lo);
  }

  tcg_gen_shli_i32(crf, crf, CRF_GT);

  // free all 4 "src" temps


r~