diff options
| author | liuhongt <hongtao.liu@intel.com> | 2023-11-23 13:10:41 +0800 |
|---|---|---|
| committer | liuhongt <hongtao.liu@intel.com> | 2023-11-30 15:39:38 +0800 |
| commit | b4a7c1c8c59d191bff64a720cca61d1d308af531 (patch) | |
| tree | 0cb24e85acd7f8b637316095a268fa4f7ac467c9 /gcc/ada | |
| parent | a1a3939bea5b0d9cbd3465d96e7e4a5222ae6c48 (diff) | |
| download | gcc-b4a7c1c8c59d191bff64a720cca61d1d308af531.zip gcc-b4a7c1c8c59d191bff64a720cca61d1d308af531.tar.gz gcc-b4a7c1c8c59d191bff64a720cca61d1d308af531.tar.bz2 | |
Support sdot_prodv*qi with emulation of sdot_prodv*hi.
Currently sdot_prodv*qi is available under TARGET_AVXVNNIINT8, but it
can be emulated by
vec_unpacks_lo_v32qi
vec_unpacks_lo_v32qi
vec_unpacks_hi_v32qi
vec_unpacks_hi_v32qi
sdot_prodv16hi
sdot_prodv16hi
add3v8si
which is faster than original
vect_patt_39.11_48 = WIDEN_MULT_LO_EXPR <vect__3.7_44, vect__7.10_47>;
vect_patt_39.11_49 = WIDEN_MULT_HI_EXPR <vect__3.7_44, vect__7.10_47>;
vect_patt_38.14_54 = [vec_unpack_lo_expr] vect_patt_39.11_48;
vect_patt_38.14_55 = [vec_unpack_hi_expr] vect_patt_39.11_48;
vect_patt_38.14_56 = [vec_unpack_lo_expr] vect_patt_39.11_49;
vect_patt_38.14_57 = [vec_unpack_hi_expr] vect_patt_39.11_49;
vect_sum_15.15_59 = vect_patt_38.14_54 + vect_patt_38.14_55;
vect_sum_15.15_60 = vect_patt_38.14_56 + vect_sum_15.15_59;
vect_sum_15.15_61 = vect_patt_38.14_57 + vect_sum_15.15_60;
gcc/ChangeLog:
* config/i386/sse.md (sdot_prodv64qi): New expander.
(sseunpackmodelower): New mode attr.
(sdot_prod<mode>): Emulate sdot_prodv*qi with sodt_prov*hi
when TARGET_VNNIINT8 is not available.
gcc/testsuite/ChangeLog:
* gcc.target/i386/sdotprodint8_emulate.c: New test.
Diffstat (limited to 'gcc/ada')
0 files changed, 0 insertions, 0 deletions