| Message ID | 20190808202616.13782-7-richard.henderson@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | target/arm: Misc cleanups | expand |
Hi Richard, On Thu, Aug 8, 2019 at 10:28 PM Richard Henderson <richard.henderson@linaro.org> wrote: > > All of the inputs to these instructions are 32-bits. Rather than > extend each input to 64-bits and then extract the high 32-bits of > the output, use tcg_gen_muls2_i32 and other 32-bit generator functions. > > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > target/arm/translate.c | 72 +++++++++++++++--------------------------- > 1 file changed, 26 insertions(+), 46 deletions(-) > > diff --git a/target/arm/translate.c b/target/arm/translate.c > index ddc54e77e4..77154be743 100644 > --- a/target/arm/translate.c > +++ b/target/arm/translate.c > @@ -391,34 +391,6 @@ static void gen_revsh(TCGv_i32 var) > tcg_gen_ext16s_i32(var, var); > } > > -/* Return (b << 32) + a. Mark inputs as dead */ > -static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv_i32 b) > -{ > - TCGv_i64 tmp64 = tcg_temp_new_i64(); > - > - tcg_gen_extu_i32_i64(tmp64, b); > - tcg_temp_free_i32(b); > - tcg_gen_shli_i64(tmp64, tmp64, 32); > - tcg_gen_add_i64(a, tmp64, a); > - > - tcg_temp_free_i64(tmp64); > - return a; > -} > - > -/* Return (b << 32) - a. Mark inputs as dead. */ > -static TCGv_i64 gen_subq_msw(TCGv_i64 a, TCGv_i32 b) > -{ > - TCGv_i64 tmp64 = tcg_temp_new_i64(); > - > - tcg_gen_extu_i32_i64(tmp64, b); > - tcg_temp_free_i32(b); > - tcg_gen_shli_i64(tmp64, tmp64, 32); > - tcg_gen_sub_i64(a, tmp64, a); > - > - tcg_temp_free_i64(tmp64); > - return a; > -} > - > /* 32x32->64 multiply. Marks inputs as dead. */ > static TCGv_i64 gen_mulu_i64_i32(TCGv_i32 a, TCGv_i32 b) > { > @@ -8872,23 +8844,27 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) > (SMMUL, SMMLA, SMMLS) */ > tmp = load_reg(s, rm); > tmp2 = load_reg(s, rs); > - tmp64 = gen_muls_i64_i32(tmp, tmp2); > + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); > > if (rd != 15) { > - tmp = load_reg(s, rd); > + tmp3 = load_reg(s, rd); > if (insn & (1 << 6)) { > - tmp64 = gen_subq_msw(tmp64, tmp); > + tcg_gen_sub_i32(tmp, tmp, tmp3); Shouldn't you subtract tmp from tmp3? > } else { > - tmp64 = gen_addq_msw(tmp64, tmp); > + tcg_gen_add_i32(tmp, tmp, tmp3); > } > + tcg_temp_free_i32(tmp3); > } > if (insn & (1 << 5)) { > - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); > + /* > + * Adding 0x80000000 to the 64-bit quantity > + * means that we have carry in to the high > + * word when the low word has the high bit set. > + */ > + tcg_gen_shri_i32(tmp2, tmp2, 31); > + tcg_gen_add_i32(tmp, tmp, tmp2); > } > - tcg_gen_shri_i64(tmp64, tmp64, 32); > - tmp = tcg_temp_new_i32(); > - tcg_gen_extrl_i64_i32(tmp, tmp64); > - tcg_temp_free_i64(tmp64); > + tcg_temp_free_i32(tmp2); > store_reg(s, rn, tmp); > break; > case 0: > @@ -10114,22 +10090,26 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) > } > break; > case 5: case 6: /* 32 * 32 -> 32msb (SMMUL, SMMLA, SMMLS) */ > - tmp64 = gen_muls_i64_i32(tmp, tmp2); > + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); > if (rs != 15) { > - tmp = load_reg(s, rs); > + tmp3 = load_reg(s, rs); > if (insn & (1 << 20)) { > - tmp64 = gen_addq_msw(tmp64, tmp); > + tcg_gen_add_i32(tmp, tmp, tmp3); > } else { > - tmp64 = gen_subq_msw(tmp64, tmp); > + tcg_gen_sub_i32(tmp, tmp, tmp3); Same here. Also the way you do the computation means you don't propagate the borrow from the lower 32-bit of the 64-bit product when doing the subtraction. Thanks, Laurent > } > + tcg_temp_free_i32(tmp3); > } > if (insn & (1 << 4)) { > - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); > + /* > + * Adding 0x80000000 to the 64-bit quantity > + * means that we have carry in to the high > + * word when the low word has the high bit set. > + */ > + tcg_gen_shri_i32(tmp2, tmp2, 31); > + tcg_gen_add_i32(tmp, tmp, tmp2); > } > - tcg_gen_shri_i64(tmp64, tmp64, 32); > - tmp = tcg_temp_new_i32(); > - tcg_gen_extrl_i64_i32(tmp, tmp64); > - tcg_temp_free_i64(tmp64); > + tcg_temp_free_i32(tmp2); > break; > case 7: /* Unsigned sum of absolute differences. */ > gen_helper_usad8(tmp, tmp, tmp2); > -- > 2.17.1 > >
diff --git a/target/arm/translate.c b/target/arm/translate.c index ddc54e77e4..77154be743 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -391,34 +391,6 @@ static void gen_revsh(TCGv_i32 var) tcg_gen_ext16s_i32(var, var); } -/* Return (b << 32) + a. Mark inputs as dead */ -static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv_i32 b) -{ - TCGv_i64 tmp64 = tcg_temp_new_i64(); - - tcg_gen_extu_i32_i64(tmp64, b); - tcg_temp_free_i32(b); - tcg_gen_shli_i64(tmp64, tmp64, 32); - tcg_gen_add_i64(a, tmp64, a); - - tcg_temp_free_i64(tmp64); - return a; -} - -/* Return (b << 32) - a. Mark inputs as dead. */ -static TCGv_i64 gen_subq_msw(TCGv_i64 a, TCGv_i32 b) -{ - TCGv_i64 tmp64 = tcg_temp_new_i64(); - - tcg_gen_extu_i32_i64(tmp64, b); - tcg_temp_free_i32(b); - tcg_gen_shli_i64(tmp64, tmp64, 32); - tcg_gen_sub_i64(a, tmp64, a); - - tcg_temp_free_i64(tmp64); - return a; -} - /* 32x32->64 multiply. Marks inputs as dead. */ static TCGv_i64 gen_mulu_i64_i32(TCGv_i32 a, TCGv_i32 b) { @@ -8872,23 +8844,27 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) (SMMUL, SMMLA, SMMLS) */ tmp = load_reg(s, rm); tmp2 = load_reg(s, rs); - tmp64 = gen_muls_i64_i32(tmp, tmp2); + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); if (rd != 15) { - tmp = load_reg(s, rd); + tmp3 = load_reg(s, rd); if (insn & (1 << 6)) { - tmp64 = gen_subq_msw(tmp64, tmp); + tcg_gen_sub_i32(tmp, tmp, tmp3); } else { - tmp64 = gen_addq_msw(tmp64, tmp); + tcg_gen_add_i32(tmp, tmp, tmp3); } + tcg_temp_free_i32(tmp3); } if (insn & (1 << 5)) { - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); + /* + * Adding 0x80000000 to the 64-bit quantity + * means that we have carry in to the high + * word when the low word has the high bit set. + */ + tcg_gen_shri_i32(tmp2, tmp2, 31); + tcg_gen_add_i32(tmp, tmp, tmp2); } - tcg_gen_shri_i64(tmp64, tmp64, 32); - tmp = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tmp, tmp64); - tcg_temp_free_i64(tmp64); + tcg_temp_free_i32(tmp2); store_reg(s, rn, tmp); break; case 0: @@ -10114,22 +10090,26 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; case 5: case 6: /* 32 * 32 -> 32msb (SMMUL, SMMLA, SMMLS) */ - tmp64 = gen_muls_i64_i32(tmp, tmp2); + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); if (rs != 15) { - tmp = load_reg(s, rs); + tmp3 = load_reg(s, rs); if (insn & (1 << 20)) { - tmp64 = gen_addq_msw(tmp64, tmp); + tcg_gen_add_i32(tmp, tmp, tmp3); } else { - tmp64 = gen_subq_msw(tmp64, tmp); + tcg_gen_sub_i32(tmp, tmp, tmp3); } + tcg_temp_free_i32(tmp3); } if (insn & (1 << 4)) { - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); + /* + * Adding 0x80000000 to the 64-bit quantity + * means that we have carry in to the high + * word when the low word has the high bit set. + */ + tcg_gen_shri_i32(tmp2, tmp2, 31); + tcg_gen_add_i32(tmp, tmp, tmp2); } - tcg_gen_shri_i64(tmp64, tmp64, 32); - tmp = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tmp, tmp64); - tcg_temp_free_i64(tmp64); + tcg_temp_free_i32(tmp2); break; case 7: /* Unsigned sum of absolute differences. */ gen_helper_usad8(tmp, tmp, tmp2);
All of the inputs to these instructions are 32-bits. Rather than extend each input to 64-bits and then extract the high 32-bits of the output, use tcg_gen_muls2_i32 and other 32-bit generator functions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate.c | 72 +++++++++++++++--------------------------- 1 file changed, 26 insertions(+), 46 deletions(-) -- 2.17.1