Message ID | 20190501050536.15580-20-richard.henderson@linaro.org |
---|---|
State | Superseded |
Headers | show |
Series | tcg vector improvements | expand |
Richard Henderson <richard.henderson@linaro.org> writes: > Remove a function of the same name from target/arm/. > Use a branchless implementation of abs gleaned from gcc. > > Reviewed-by: David Hildenbrand <david@redhat.com> > Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> > --- > tcg/tcg-op.h | 5 +++++ > target/arm/translate.c | 10 ---------- > tcg/tcg-op.c | 20 ++++++++++++++++++++ > 3 files changed, 25 insertions(+), 10 deletions(-) > > diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h > index 472b73cb38..660fe205d0 100644 > --- a/tcg/tcg-op.h > +++ b/tcg/tcg-op.h > @@ -335,6 +335,7 @@ void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); > void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); > void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); > void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); > +void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); > > static inline void tcg_gen_discard_i32(TCGv_i32 arg) > { > @@ -534,6 +535,7 @@ void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); > void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); > void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); > void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); > +void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); > > #if TCG_TARGET_REG_BITS == 64 > static inline void tcg_gen_discard_i64(TCGv_i64 arg) > @@ -973,6 +975,7 @@ void tcg_gen_nor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); > void tcg_gen_eqv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); > void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a); > void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a); > +void tcg_gen_abs_vec(unsigned vece, TCGv_vec r, TCGv_vec a); > void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); > void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); > void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); > @@ -1019,6 +1022,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); > #define tcg_gen_addi_tl tcg_gen_addi_i64 > #define tcg_gen_sub_tl tcg_gen_sub_i64 > #define tcg_gen_neg_tl tcg_gen_neg_i64 > +#define tcg_gen_abs_tl tcg_gen_abs_i64 > #define tcg_gen_subfi_tl tcg_gen_subfi_i64 > #define tcg_gen_subi_tl tcg_gen_subi_i64 > #define tcg_gen_and_tl tcg_gen_and_i64 > @@ -1131,6 +1135,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); > #define tcg_gen_addi_tl tcg_gen_addi_i32 > #define tcg_gen_sub_tl tcg_gen_sub_i32 > #define tcg_gen_neg_tl tcg_gen_neg_i32 > +#define tcg_gen_abs_tl tcg_gen_abs_i32 > #define tcg_gen_subfi_tl tcg_gen_subfi_i32 > #define tcg_gen_subi_tl tcg_gen_subi_i32 > #define tcg_gen_and_tl tcg_gen_and_i32 > diff --git a/target/arm/translate.c b/target/arm/translate.c > index 35bd426a3d..b25781554f 100644 > --- a/target/arm/translate.c > +++ b/target/arm/translate.c > @@ -604,16 +604,6 @@ static void gen_sar(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) > tcg_temp_free_i32(tmp1); > } > > -static void tcg_gen_abs_i32(TCGv_i32 dest, TCGv_i32 src) > -{ > - TCGv_i32 c0 = tcg_const_i32(0); > - TCGv_i32 tmp = tcg_temp_new_i32(); > - tcg_gen_neg_i32(tmp, src); > - tcg_gen_movcond_i32(TCG_COND_GT, dest, src, c0, src, tmp); > - tcg_temp_free_i32(c0); > - tcg_temp_free_i32(tmp); > -} > - > static void shifter_out_im(TCGv_i32 var, int shift) > { > if (shift == 0) { > diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c > index a00d1df37e..0ac291f1c4 100644 > --- a/tcg/tcg-op.c > +++ b/tcg/tcg-op.c > @@ -1091,6 +1091,16 @@ void tcg_gen_umax_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b) > tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, b, a); > } > > +void tcg_gen_abs_i32(TCGv_i32 ret, TCGv_i32 a) > +{ > + TCGv_i32 t = tcg_temp_new_i32(); > + > + tcg_gen_sari_i32(t, a, 31); > + tcg_gen_xor_i32(ret, a, t); > + tcg_gen_sub_i32(ret, ret, t); > + tcg_temp_free_i32(t); > +} > + > /* 64-bit ops */ > > #if TCG_TARGET_REG_BITS == 32 > @@ -2548,6 +2558,16 @@ void tcg_gen_umax_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b) > tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, b, a); > } > > +void tcg_gen_abs_i64(TCGv_i64 ret, TCGv_i64 a) > +{ > + TCGv_i64 t = tcg_temp_new_i64(); > + > + tcg_gen_sari_i64(t, a, 63); > + tcg_gen_xor_i64(ret, a, t); > + tcg_gen_sub_i64(ret, ret, t); > + tcg_temp_free_i64(t); > +} > + > /* Size changing operations. */ > > void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg) -- Alex Bennée
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h index 472b73cb38..660fe205d0 100644 --- a/tcg/tcg-op.h +++ b/tcg/tcg-op.h @@ -335,6 +335,7 @@ void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); static inline void tcg_gen_discard_i32(TCGv_i32 arg) { @@ -534,6 +535,7 @@ void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); #if TCG_TARGET_REG_BITS == 64 static inline void tcg_gen_discard_i64(TCGv_i64 arg) @@ -973,6 +975,7 @@ void tcg_gen_nor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_eqv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a); void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a); +void tcg_gen_abs_vec(unsigned vece, TCGv_vec r, TCGv_vec a); void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); @@ -1019,6 +1022,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_addi_tl tcg_gen_addi_i64 #define tcg_gen_sub_tl tcg_gen_sub_i64 #define tcg_gen_neg_tl tcg_gen_neg_i64 +#define tcg_gen_abs_tl tcg_gen_abs_i64 #define tcg_gen_subfi_tl tcg_gen_subfi_i64 #define tcg_gen_subi_tl tcg_gen_subi_i64 #define tcg_gen_and_tl tcg_gen_and_i64 @@ -1131,6 +1135,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_addi_tl tcg_gen_addi_i32 #define tcg_gen_sub_tl tcg_gen_sub_i32 #define tcg_gen_neg_tl tcg_gen_neg_i32 +#define tcg_gen_abs_tl tcg_gen_abs_i32 #define tcg_gen_subfi_tl tcg_gen_subfi_i32 #define tcg_gen_subi_tl tcg_gen_subi_i32 #define tcg_gen_and_tl tcg_gen_and_i32 diff --git a/target/arm/translate.c b/target/arm/translate.c index 35bd426a3d..b25781554f 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -604,16 +604,6 @@ static void gen_sar(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) tcg_temp_free_i32(tmp1); } -static void tcg_gen_abs_i32(TCGv_i32 dest, TCGv_i32 src) -{ - TCGv_i32 c0 = tcg_const_i32(0); - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_neg_i32(tmp, src); - tcg_gen_movcond_i32(TCG_COND_GT, dest, src, c0, src, tmp); - tcg_temp_free_i32(c0); - tcg_temp_free_i32(tmp); -} - static void shifter_out_im(TCGv_i32 var, int shift) { if (shift == 0) { diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index a00d1df37e..0ac291f1c4 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -1091,6 +1091,16 @@ void tcg_gen_umax_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b) tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, b, a); } +void tcg_gen_abs_i32(TCGv_i32 ret, TCGv_i32 a) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_sari_i32(t, a, 31); + tcg_gen_xor_i32(ret, a, t); + tcg_gen_sub_i32(ret, ret, t); + tcg_temp_free_i32(t); +} + /* 64-bit ops */ #if TCG_TARGET_REG_BITS == 32 @@ -2548,6 +2558,16 @@ void tcg_gen_umax_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b) tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, b, a); } +void tcg_gen_abs_i64(TCGv_i64 ret, TCGv_i64 a) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sari_i64(t, a, 63); + tcg_gen_xor_i64(ret, a, t); + tcg_gen_sub_i64(ret, ret, t); + tcg_temp_free_i64(t); +} + /* Size changing operations. */ void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg)