diff options
author | konglin1 <lingling.kong@intel.com> | 2022-09-05 14:38:03 +0800 |
---|---|---|
committer | konglin1 <lingling.kong@intel.com> | 2022-09-05 14:38:06 +0800 |
commit | 092763fd0c069f3a7c05a65238d3815e8daab76b (patch) | |
tree | 53b73708a9c8dff667af3dc525dd987485232923 /gcc/config | |
parent | 5f3228935e27780430a8a1504c2fa4a1ff978594 (diff) | |
download | gcc-092763fd0c069f3a7c05a65238d3815e8daab76b.zip gcc-092763fd0c069f3a7c05a65238d3815e8daab76b.tar.gz gcc-092763fd0c069f3a7c05a65238d3815e8daab76b.tar.bz2 |
x86: Handle V8BF in expand_vec_perm_broadcast_1
gcc/ChangeLog:
PR target/106742
* config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate):
Handle V8BF mode.
(expand_vec_perm_broadcast_1): Ditto.
* config/i386/sse.md (avx512fmaskhalfmode): Add BF vector mode.
(vec_set<mode>_0): Add @ to it.
(@vec_set<mode>_0): Ditto.
(vec_interleave_high<mode><mask_name>): Ditto.
(@vec_interleave_high<mode><mask_name>): Ditto.
(vec_interleave_low<mode><mask_name>): Ditto.
(@vec_interleave_low<mode><mask_name>): Ditto.
* config/i386/subst.md (SUBST_V): Add BF vector mode.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr106742.c: New test.
Diffstat (limited to 'gcc/config')
-rw-r--r-- | gcc/config/i386/i386-expand.cc | 15 | ||||
-rw-r--r-- | gcc/config/i386/sse.md | 7 | ||||
-rw-r--r-- | gcc/config/i386/subst.md | 1 |
3 files changed, 14 insertions, 9 deletions
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 836ebc8..d7b49c9 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -15034,11 +15034,12 @@ ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, dperm.op0 = dperm.op1 = gen_reg_rtx (mode); dperm.one_operand_p = true; - if (mode == V8HFmode) + if (mode == V8HFmode || mode == V8BFmode) { - tmp1 = force_reg (HFmode, val); + tmp1 = force_reg (GET_MODE_INNER (mode), val); tmp2 = gen_reg_rtx (mode); - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); + emit_insn (maybe_gen_vec_set_0 (mode, tmp2, + CONST0_RTX (mode), tmp1)); tmp1 = gen_lowpart (mode, tmp2); } else @@ -21826,21 +21827,23 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d) return true; case E_V8HFmode: + case E_V8BFmode: /* This can be implemented via interleave and pshufd. */ if (d->testing_p) return true; + rtx (*maybe_gen) (machine_mode, int, rtx, rtx, rtx); if (elt >= nelt2) { - gen = gen_vec_interleave_highv8hf; + maybe_gen = maybe_gen_vec_interleave_high; elt -= nelt2; } else - gen = gen_vec_interleave_lowv8hf; + maybe_gen = maybe_gen_vec_interleave_low; nelt2 /= 2; dest = gen_reg_rtx (vmode); - emit_insn (gen (dest, op0, op0)); + emit_insn (maybe_gen (vmode, 1, dest, op0, op0)); vmode = V4SImode; op0 = gen_lowpart (vmode, dest); diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 2590484..72acf0b 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -984,6 +984,7 @@ (V16SI "QI") (V8SI "QI") (V4SI "QI") (V8DI "QI") (V4DI "QI") (V2DI "QI") (V32HF "HI") (V16HF "QI") (V8HF "QI") + (V32BF "HI") (V16BF "QI") (V8BF "QI") (V16SF "QI") (V8SF "QI") (V4SF "QI") (V8DF "QI") (V4DF "QI") (V2DF "QI")]) @@ -10712,7 +10713,7 @@ ] (symbol_ref "true")))]) -(define_insn "vec_set<mode>_0" +(define_insn "@vec_set<mode>_0" [(set (match_operand:V8_128 0 "register_operand" "=v,v,v,x,x,Yr,*x,x,x,x,v,v") (vec_merge:V8_128 @@ -17895,7 +17896,7 @@ (set_attr "prefix" "maybe_evex") (set_attr "mode" "OI")]) -(define_insn "vec_interleave_high<mode><mask_name>" +(define_insn "@vec_interleave_high<mode><mask_name>" [(set (match_operand:V8_128 0 "register_operand" "=x,Yw") (vec_select:V8_128 (vec_concat:<ssedoublevecmode> @@ -17963,7 +17964,7 @@ (set_attr "prefix" "maybe_evex") (set_attr "mode" "OI")]) -(define_insn "vec_interleave_low<mode><mask_name>" +(define_insn "@vec_interleave_low<mode><mask_name>" [(set (match_operand:V8_128 0 "register_operand" "=x,Yw") (vec_select:V8_128 (vec_concat:<ssedoublevecmode> diff --git a/gcc/config/i386/subst.md b/gcc/config/i386/subst.md index 0b75882..e169282 100644 --- a/gcc/config/i386/subst.md +++ b/gcc/config/i386/subst.md @@ -25,6 +25,7 @@ V16SI V8SI V4SI V8DI V4DI V2DI V32HF V16HF V8HF + V32BF V16BF V8BF V16SF V8SF V4SF V8DF V4DF V2DF]) |