| Message ID | 1362443590-28191-8-git-send-email-rth@twiddle.net |
|---|---|
| State | New |
| Headers | show |
On Mon, Mar 04, 2013 at 04:32:50PM -0800, Richard Henderson wrote: > The test for using movi32 was sub-optimal for TCG_TYPE_I32, comparing > a signed 32-bit quantity against an unsigned 32-bit quantity. > > When possible, use addi+oris for 32-bit unsigned constants. Otherwise, > standardize on addi+oris+ori instead of addis+ori+rldicl. > > Signed-off-by: Richard Henderson <rth@twiddle.net> > --- > tcg/ppc64/tcg-target.c | 36 ++++++++++++++++-------------------- > 1 file changed, 16 insertions(+), 20 deletions(-) > > diff --git a/tcg/ppc64/tcg-target.c b/tcg/ppc64/tcg-target.c > index 82e1da7..a4951c5 100644 > --- a/tcg/ppc64/tcg-target.c > +++ b/tcg/ppc64/tcg-target.c > @@ -477,29 +477,25 @@ static void tcg_out_movi32(TCGContext *s, TCGReg ret, int32_t arg) > } > } > > -static void tcg_out_movi (TCGContext *s, TCGType type, > - TCGReg ret, tcg_target_long arg) > +static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret, > + tcg_target_long arg) > { > - int32_t arg32 = arg; > - arg = type == TCG_TYPE_I32 ? arg & 0xffffffff : arg; > - > - if (arg == arg32) { > - tcg_out_movi32 (s, ret, arg32); > - } > - else { > - if ((uint64_t) arg >> 32) { > - uint16_t h16 = arg >> 16; > - uint16_t l16 = arg; > - > - tcg_out_movi32 (s, ret, arg >> 32); > + if (type == TCG_TYPE_I32 || arg == (int32_t)arg) { > + tcg_out_movi32(s, ret, arg); > + } else if (arg == (uint32_t)arg && !(arg & 0x8000)) { > + tcg_out32(s, ADDI | RT(ret) | RA(0) | (arg & 0xffff)); > + tcg_out32(s, ORIS | RT(ret) | RA(ret) | ((arg >> 16) & 0xffff)); > + } else { > + int32_t high = arg >> 32; > + tcg_out_movi32(s, ret, high); > + if (high) { > tcg_out_shli64(s, ret, ret, 32); > - if (h16) tcg_out32 (s, ORIS | RS (ret) | RA (ret) | h16); > - if (l16) tcg_out32 (s, ORI | RS (ret) | RA (ret) | l16); > } > - else { > - tcg_out_movi32 (s, ret, arg32); > - if (arg32 < 0) > - tcg_out_ext32u(s, ret, ret); > + if (arg & 0xffff0000) { > + tcg_out32(s, ORIS | RS(ret) | RA(ret) | ((arg >> 16) & 0xffff)); > + } > + if (arg & 0xffff) { > + tcg_out32(s, ORI | RS(ret) | RA(ret) | (arg & 0xffff)); > } > } > } Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
diff --git a/tcg/ppc64/tcg-target.c b/tcg/ppc64/tcg-target.c index 82e1da7..a4951c5 100644 --- a/tcg/ppc64/tcg-target.c +++ b/tcg/ppc64/tcg-target.c @@ -477,29 +477,25 @@ static void tcg_out_movi32(TCGContext *s, TCGReg ret, int32_t arg) } } -static void tcg_out_movi (TCGContext *s, TCGType type, - TCGReg ret, tcg_target_long arg) +static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret, + tcg_target_long arg) { - int32_t arg32 = arg; - arg = type == TCG_TYPE_I32 ? arg & 0xffffffff : arg; - - if (arg == arg32) { - tcg_out_movi32 (s, ret, arg32); - } - else { - if ((uint64_t) arg >> 32) { - uint16_t h16 = arg >> 16; - uint16_t l16 = arg; - - tcg_out_movi32 (s, ret, arg >> 32); + if (type == TCG_TYPE_I32 || arg == (int32_t)arg) { + tcg_out_movi32(s, ret, arg); + } else if (arg == (uint32_t)arg && !(arg & 0x8000)) { + tcg_out32(s, ADDI | RT(ret) | RA(0) | (arg & 0xffff)); + tcg_out32(s, ORIS | RT(ret) | RA(ret) | ((arg >> 16) & 0xffff)); + } else { + int32_t high = arg >> 32; + tcg_out_movi32(s, ret, high); + if (high) { tcg_out_shli64(s, ret, ret, 32); - if (h16) tcg_out32 (s, ORIS | RS (ret) | RA (ret) | h16); - if (l16) tcg_out32 (s, ORI | RS (ret) | RA (ret) | l16); } - else { - tcg_out_movi32 (s, ret, arg32); - if (arg32 < 0) - tcg_out_ext32u(s, ret, ret); + if (arg & 0xffff0000) { + tcg_out32(s, ORIS | RS(ret) | RA(ret) | ((arg >> 16) & 0xffff)); + } + if (arg & 0xffff) { + tcg_out32(s, ORI | RS(ret) | RA(ret) | (arg & 0xffff)); } } }
The test for using movi32 was sub-optimal for TCG_TYPE_I32, comparing a signed 32-bit quantity against an unsigned 32-bit quantity. When possible, use addi+oris for 32-bit unsigned constants. Otherwise, standardize on addi+oris+ori instead of addis+ori+rldicl. Signed-off-by: Richard Henderson <rth@twiddle.net> --- tcg/ppc64/tcg-target.c | 36 ++++++++++++++++-------------------- 1 file changed, 16 insertions(+), 20 deletions(-)