| Message ID | 20210819090502.428068-3-richard.henderson@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | target/riscv: Use tcg_constant_* | expand |
On Thu, Aug 19, 2021 at 5:07 PM Richard Henderson <richard.henderson@linaro.org> wrote: > > Utilize the condition in the movcond more; this allows some of > the setcond that were feeding into movcond to be removed. > Do not write into source1 and source2. Re-name "condN" to "tempN" > and use the temporaries for more than holding conditions. > > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > target/riscv/translate.c | 146 +++++++++++++++++++-------------------- > 1 file changed, 71 insertions(+), 75 deletions(-) > > diff --git a/target/riscv/translate.c b/target/riscv/translate.c > index 20a55c92fb..b52181538f 100644 > --- a/target/riscv/translate.c > +++ b/target/riscv/translate.c > @@ -213,106 +213,102 @@ static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) > > static void gen_div(TCGv ret, TCGv source1, TCGv source2) > { > - TCGv cond1, cond2, zeroreg, resultopt1; > + TCGv temp1, temp2, zero, one, mone, min; > + > /* > * Handle by altering args to tcg_gen_div to produce req'd results: > - * For overflow: want source1 in source1 and 1 in source2 > - * For div by zero: want -1 in source1 and 1 in source2 -> -1 result > + * For overflow: want source1 in temp1 and 1 in temp2 > + * For div by zero: want -1 in temp1 and 1 in temp2 -> -1 result > */ > - cond1 = tcg_temp_new(); > - cond2 = tcg_temp_new(); > - zeroreg = tcg_constant_tl(0); > - resultopt1 = tcg_temp_new(); > + temp1 = tcg_temp_new(); > + temp2 = tcg_temp_new(); > + zero = tcg_constant_tl(0); > + one = tcg_constant_tl(1); > + mone = tcg_constant_tl(-1); > + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); > > - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L)); > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, > - ((target_ulong)1) << (TARGET_LONG_BITS - 1)); > - tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */ > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */ > - /* if div by zero, set source1 to -1, otherwise don't change */ > - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1, > - resultopt1); > - /* if overflow or div by zero, set source2 to 1, else don't change */ > - tcg_gen_or_tl(cond1, cond1, cond2); > - tcg_gen_movi_tl(resultopt1, (target_ulong)1); > - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, > - resultopt1); > - tcg_gen_div_tl(ret, source1, source2); > + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); > + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); > + tcg_gen_and_tl(temp1, temp1, temp2); /* temp1 = overflow */ > + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, zero); /* temp2 = div0 */ > + tcg_gen_or_tl(temp2, temp2, temp1); /* temp2 = overflow | div0 */ > > - tcg_temp_free(cond1); > - tcg_temp_free(cond2); > - tcg_temp_free(resultopt1); > + /* if div by zero, set temp1 to -1, else source1. */ > + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1); > + > + /* if overflow or div by zero, set temp2 to 1, else source2 */ > + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp2, zero, one, source2); > + > + tcg_gen_div_tl(ret, temp1, temp2); > + > + tcg_temp_free(temp1); > + tcg_temp_free(temp2); > } > > static void gen_divu(TCGv ret, TCGv source1, TCGv source2) > { > - TCGv cond1, zeroreg, resultopt1; > - cond1 = tcg_temp_new(); > + TCGv temp1, temp2, zero, one, max; > > - zeroreg = tcg_constant_tl(0); > - resultopt1 = tcg_temp_new(); > + temp1 = tcg_temp_new(); > + temp2 = tcg_temp_new(); > + zero = tcg_constant_tl(0); > + one = tcg_constant_tl(1); > + max = tcg_constant_tl(~0); > > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); > - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); > - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1, > - resultopt1); > - tcg_gen_movi_tl(resultopt1, (target_ulong)1); > - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, > - resultopt1); > - tcg_gen_divu_tl(ret, source1, source2); > + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1); > + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); > + tcg_gen_divu_tl(ret, temp1, temp2); > > - tcg_temp_free(cond1); > - tcg_temp_free(resultopt1); > + tcg_temp_free(temp1); > + tcg_temp_free(temp2); > } > > static void gen_rem(TCGv ret, TCGv source1, TCGv source2) > { > - TCGv cond1, cond2, zeroreg, resultopt1; > + TCGv temp1, temp2, zero, one, mone, min; > > - cond1 = tcg_temp_new(); > - cond2 = tcg_temp_new(); > - zeroreg = tcg_constant_tl(0); > - resultopt1 = tcg_temp_new(); > + temp1 = tcg_temp_new(); > + temp2 = tcg_temp_new(); > + zero = tcg_constant_tl(0); > + one = tcg_constant_tl(1); > + mone = tcg_constant_tl(-1); > + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); > > - tcg_gen_movi_tl(resultopt1, 1L); > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1); > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, > - (target_ulong)1 << (TARGET_LONG_BITS - 1)); > - tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */ > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */ > - /* if overflow or div by zero, set source2 to 1, else don't change */ > - tcg_gen_or_tl(cond2, cond1, cond2); > - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2, > - resultopt1); > - tcg_gen_rem_tl(resultopt1, source1, source2); > - /* if div by zero, just return the original dividend */ > - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, > - source1); > + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); > + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); > + tcg_gen_and_tl(temp1, temp1, temp2); /* temp1 = overflow */ > + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, zero); /* temp2 = div0 */ > + tcg_gen_or_tl(temp2, temp2, temp1); /* temp2 = overflow | div0 */ > > - tcg_temp_free(cond1); > - tcg_temp_free(cond2); > - tcg_temp_free(resultopt1); > + /* > + * if overflow or div by zero, set temp2 to 1, else source2 > + * this automatically takes care of returning the original > + * dividend for div by zero. > + */ > + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp2, zero, one, source2); What about the overflow case? The return value should be 0. > + > + tcg_gen_rem_tl(ret, source1, temp2); > + > + tcg_temp_free(temp1); > + tcg_temp_free(temp2); > } > > static void gen_remu(TCGv ret, TCGv source1, TCGv source2) > { > - TCGv cond1, zeroreg, resultopt1; > - cond1 = tcg_temp_new(); > - zeroreg = tcg_constant_tl(0); > - resultopt1 = tcg_temp_new(); > + TCGv temp2, zero, one; > > - tcg_gen_movi_tl(resultopt1, (target_ulong)1); > - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); > - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, > - resultopt1); > - tcg_gen_remu_tl(resultopt1, source1, source2); > - /* if div by zero, just return the original dividend */ > - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, > - source1); > + temp2 = tcg_temp_new(); > + zero = tcg_constant_tl(0); > + one = tcg_constant_tl(1); > > - tcg_temp_free(cond1); > - tcg_temp_free(resultopt1); > + /* > + * if div by zero, set temp2 to 1, else source2 > + * this automatically takes care of returning the original dividend. > + */ > + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); > + tcg_gen_remu_tl(ret, source1, temp2); > + > + tcg_temp_free(temp2); > } > > static void gen_jal(DisasContext *ctx, int rd, target_ulong imm) Regards, Bin
On 8/19/21 1:00 AM, Bin Meng wrote: >> static void gen_rem(TCGv ret, TCGv source1, TCGv source2) >> { >> - TCGv cond1, cond2, zeroreg, resultopt1; >> + TCGv temp1, temp2, zero, one, mone, min; >> >> - cond1 = tcg_temp_new(); >> - cond2 = tcg_temp_new(); >> - zeroreg = tcg_constant_tl(0); >> - resultopt1 = tcg_temp_new(); >> + temp1 = tcg_temp_new(); >> + temp2 = tcg_temp_new(); >> + zero = tcg_constant_tl(0); >> + one = tcg_constant_tl(1); >> + mone = tcg_constant_tl(-1); >> + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); >> >> - tcg_gen_movi_tl(resultopt1, 1L); >> - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1); >> - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, >> - (target_ulong)1 << (TARGET_LONG_BITS - 1)); >> - tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */ >> - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */ >> - /* if overflow or div by zero, set source2 to 1, else don't change */ >> - tcg_gen_or_tl(cond2, cond1, cond2); >> - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2, >> - resultopt1); >> - tcg_gen_rem_tl(resultopt1, source1, source2); >> - /* if div by zero, just return the original dividend */ >> - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, >> - source1); >> + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); >> + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); >> + tcg_gen_and_tl(temp1, temp1, temp2); /* temp1 = overflow */ >> + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, zero); /* temp2 = div0 */ >> + tcg_gen_or_tl(temp2, temp2, temp1); /* temp2 = overflow | div0 */ >> >> - tcg_temp_free(cond1); >> - tcg_temp_free(cond2); >> - tcg_temp_free(resultopt1); >> + /* >> + * if overflow or div by zero, set temp2 to 1, else source2 >> + * this automatically takes care of returning the original >> + * dividend for div by zero. >> + */ >> + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp2, zero, one, source2); > > What about the overflow case? The return value should be 0. Hmm. I see that in the table, yes, but I don't see that the original code got that correct either. I'll send a follow-up patch. r~
diff --git a/target/riscv/translate.c b/target/riscv/translate.c index 20a55c92fb..b52181538f 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -213,106 +213,102 @@ static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) static void gen_div(TCGv ret, TCGv source1, TCGv source2) { - TCGv cond1, cond2, zeroreg, resultopt1; + TCGv temp1, temp2, zero, one, mone, min; + /* * Handle by altering args to tcg_gen_div to produce req'd results: - * For overflow: want source1 in source1 and 1 in source2 - * For div by zero: want -1 in source1 and 1 in source2 -> -1 result + * For overflow: want source1 in temp1 and 1 in temp2 + * For div by zero: want -1 in temp1 and 1 in temp2 -> -1 result */ - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_constant_tl(0); - resultopt1 = tcg_temp_new(); + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L)); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - ((target_ulong)1) << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */ - /* if div by zero, set source1 to -1, otherwise don't change */ - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1, - resultopt1); - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond1, cond1, cond2); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_div_tl(ret, source1, source2); + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); /* temp1 = overflow */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, zero); /* temp2 = div0 */ + tcg_gen_or_tl(temp2, temp2, temp1); /* temp2 = overflow | div0 */ - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(resultopt1); + /* if div by zero, set temp1 to -1, else source1. */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1); + + /* if overflow or div by zero, set temp2 to 1, else source2 */ + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp2, zero, one, source2); + + tcg_gen_div_tl(ret, temp1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static void gen_divu(TCGv ret, TCGv source1, TCGv source2) { - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); + TCGv temp1, temp2, zero, one, max; - zeroreg = tcg_constant_tl(0); - resultopt1 = tcg_temp_new(); + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + max = tcg_constant_tl(~0); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1, - resultopt1); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_divu_tl(ret, source1, source2); + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1); + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + tcg_gen_divu_tl(ret, temp1, temp2); - tcg_temp_free(cond1); - tcg_temp_free(resultopt1); + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static void gen_rem(TCGv ret, TCGv source1, TCGv source2) { - TCGv cond1, cond2, zeroreg, resultopt1; + TCGv temp1, temp2, zero, one, mone, min; - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_constant_tl(0); - resultopt1 = tcg_temp_new(); + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); - tcg_gen_movi_tl(resultopt1, 1L); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - (target_ulong)1 << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */ - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond2, cond1, cond2); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2, - resultopt1); - tcg_gen_rem_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); /* temp1 = overflow */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, zero); /* temp2 = div0 */ + tcg_gen_or_tl(temp2, temp2, temp1); /* temp2 = overflow | div0 */ - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(resultopt1); + /* + * if overflow or div by zero, set temp2 to 1, else source2 + * this automatically takes care of returning the original + * dividend for div by zero. + */ + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp2, zero, one, source2); + + tcg_gen_rem_tl(ret, source1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static void gen_remu(TCGv ret, TCGv source1, TCGv source2) { - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); - zeroreg = tcg_constant_tl(0); - resultopt1 = tcg_temp_new(); + TCGv temp2, zero, one; - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_remu_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); - tcg_temp_free(cond1); - tcg_temp_free(resultopt1); + /* + * if div by zero, set temp2 to 1, else source2 + * this automatically takes care of returning the original dividend. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + tcg_gen_remu_tl(ret, source1, temp2); + + tcg_temp_free(temp2); } static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
Utilize the condition in the movcond more; this allows some of the setcond that were feeding into movcond to be removed. Do not write into source1 and source2. Re-name "condN" to "tempN" and use the temporaries for more than holding conditions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/riscv/translate.c | 146 +++++++++++++++++++-------------------- 1 file changed, 71 insertions(+), 75 deletions(-)