diff options
| author | jakub <jakub@138bc75d-0d04-0410-961f-82ee72b054a4> | 2016-05-26 08:43:17 +0000 |
|---|---|---|
| committer | jakub <jakub@138bc75d-0d04-0410-961f-82ee72b054a4> | 2016-05-26 08:43:17 +0000 |
| commit | c5e8b3e288dc2eee7081df0c3eee40dbc7b66202 (patch) | |
| tree | 44ddf7f88963394ad8a528b0a0365b2dfd4765ac /gcc/config/i386 | |
| parent | e9bcea2f570e3851cc8e0b1fe53345aaf37d47cf (diff) | |
| download | gcc-c5e8b3e288dc2eee7081df0c3eee40dbc7b66202.tar.gz | |
* config/i386/sse.md
(<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>): Rename
to ...
(avx512vl_shuf_<shuffletype>32x4_1<mask_name>): ... this.
(*avx_vperm_broadcast_v4sf): Use v constraint instead of x. Use
maybe_evex prefix instead of vex.
(*avx_vperm_broadcast_<mode>): Use v constraint instead of x. Handle
EXT_REX_SSE_REG_P (op0) case in the splitter.
* gcc.target/i386/avx512vl-vbroadcast-3.c: New test.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@236763 138bc75d-0d04-0410-961f-82ee72b054a4
Diffstat (limited to 'gcc/config/i386')
| -rw-r--r-- | gcc/config/i386/sse.md | 29 |
1 files changed, 23 insertions, 6 deletions
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 2297ca2fd77..c681098469c 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -12399,7 +12399,7 @@ DONE; }) -(define_insn "<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>" +(define_insn "avx512vl_shuf_<shuffletype>32x4_1<mask_name>" [(set (match_operand:VI4F_256 0 "register_operand" "=v") (vec_select:VI4F_256 (vec_concat:<ssedoublemode> @@ -17283,9 +17283,9 @@ ;; If it so happens that the input is in memory, use vbroadcast. ;; Otherwise use vpermilp (and in the case of 256-bit modes, vperm2f128). (define_insn "*avx_vperm_broadcast_v4sf" - [(set (match_operand:V4SF 0 "register_operand" "=x,x,x") + [(set (match_operand:V4SF 0 "register_operand" "=v,v,v") (vec_select:V4SF - (match_operand:V4SF 1 "nonimmediate_operand" "m,o,x") + (match_operand:V4SF 1 "nonimmediate_operand" "m,o,v") (match_parallel 2 "avx_vbroadcast_operand" [(match_operand 3 "const_int_operand" "C,n,n")])))] "TARGET_AVX" @@ -17307,13 +17307,13 @@ [(set_attr "type" "ssemov,ssemov,sselog1") (set_attr "prefix_extra" "1") (set_attr "length_immediate" "0,0,1") - (set_attr "prefix" "vex") + (set_attr "prefix" "maybe_evex") (set_attr "mode" "SF,SF,V4SF")]) (define_insn_and_split "*avx_vperm_broadcast_<mode>" - [(set (match_operand:VF_256 0 "register_operand" "=x,x,x") + [(set (match_operand:VF_256 0 "register_operand" "=v,v,v") (vec_select:VF_256 - (match_operand:VF_256 1 "nonimmediate_operand" "m,o,?x") + (match_operand:VF_256 1 "nonimmediate_operand" "m,o,?v") (match_parallel 2 "avx_vbroadcast_operand" [(match_operand 3 "const_int_operand" "C,n,n")])))] "TARGET_AVX" @@ -17345,6 +17345,23 @@ /* Shuffle the lane we care about into both lanes of the dest. */ mask = (elt / (<ssescalarnum> / 2)) * 0x11; + if (EXT_REX_SSE_REG_P (op0)) + { + /* There is no EVEX VPERM2F128, but we can use either VBROADCASTSS + or VSHUFF128. */ + gcc_assert (<MODE>mode == V8SFmode); + if ((mask & 1) == 0) + emit_insn (gen_avx2_vec_dupv8sf (op0, + gen_lowpart (V4SFmode, op0))); + else + emit_insn (gen_avx512vl_shuf_f32x4_1 (op0, op0, op0, + GEN_INT (4), GEN_INT (5), + GEN_INT (6), GEN_INT (7), + GEN_INT (12), GEN_INT (13), + GEN_INT (14), GEN_INT (15))); + DONE; + } + emit_insn (gen_avx_vperm2f128<mode>3 (op0, op0, op0, GEN_INT (mask))); DONE; } |