public inbox for gcc-cvs@sourceware.org help / color / mirror / Atom feed
From: Jakub Jelinek <jakub@gcc.gnu.org> To: gcc-cvs@gcc.gnu.org Subject: [gcc r13-4162] i386: Outline fast BF -> SF conversion and fix up sNaN handling in it [PR107628] Date: Sat, 19 Nov 2022 09:17:39 +0000 (GMT) [thread overview] Message-ID: <20221119091739.7BEC1385840E@sourceware.org> (raw) https://gcc.gnu.org/g:b1115dbfea4d6df51d608cece7416d658d2e2822 commit r13-4162-gb1115dbfea4d6df51d608cece7416d658d2e2822 Author: Jakub Jelinek <jakub@redhat.com> Date: Sat Nov 19 10:17:01 2022 +0100 i386: Outline fast BF -> SF conversion and fix up sNaN handling in it [PR107628] On Fri, Oct 21, 2022 at 10:23:14AM +0200, Uros Bizjak wrote: > OK, but now we have two more copies of a function that effectively > extends BF to SF. Can you please split this utility function out and > use it here and in cbranchbf4/cstorebf4? I'm talking about this part: > > + op = gen_lowpart (HImode, op1); > + if (CONST_INT_P (op)) > + op = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, > + op1, BFmode); > + else > + { > + rtx t1 = gen_reg_rtx (SImode); > + emit_insn (gen_zero_extendhisi2 (t1, op)); > + emit_insn (gen_ashlsi3 (t1, t1, GEN_INT (16))); > + op = gen_lowpart (SFmode, t1); > + } > > Taking this a bit further, it looks like a generic function to extend > BF to SF, when extendbfsf2 named function is not defined. > > The above could be a follow-up patch, the proposed patch is OK. Sorry for the delay, only got to this now. And I'm fixing the sNaN handling in it too. If the argument is a BFmode sNaN constant, we want in this case just a SFmode sNaN constant, but simplify_const_unary_operation (FLOAT_EXTEND, ...) in that case returns NULL (as normally conversions of a sNaN to some other float type should raise an exception). In this case we want to bypass that, as we know the sNaN will be used immediately in the SFmode comparison a few instructions later. The patch fixes it by just simplifying the lowpart to HImode and its zero extension to SImode, then force into a pseudo and do the left shift and subreg to SFmode on the pseudo. CSE or combine can handle it later. 2022-11-19 Jakub Jelinek <jakub@redhat.com> PR target/107628 * config/i386/i386-protos.h (ix86_expand_fast_convert_bf_to_sf): Declare. * config/i386/i386-expand.cc (ix86_expand_fast_convert_bf_to_sf): New function. * config/i386/i386.md (cbranchbf4, cstorebf4): Use it. * gcc.target/i386/pr107628.c: New test. Diff: --- gcc/config/i386/i386-expand.cc | 26 +++++++++++++++++ gcc/config/i386/i386-protos.h | 1 + gcc/config/i386/i386.md | 48 +++----------------------------- gcc/testsuite/gcc.target/i386/pr107628.c | 11 ++++++++ 4 files changed, 42 insertions(+), 44 deletions(-) diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index a166395db45..0373c3614a4 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -24138,4 +24138,30 @@ ix86_expand_cmpxchg_loop (rtx *ptarget_bool, rtx target_val, *ptarget_bool = target_bool; } +/* Convert a BFmode VAL to SFmode without signaling sNaNs. + This is done by returning SF SUBREG of ((HI SUBREG) (VAL)) << 16. */ + +rtx +ix86_expand_fast_convert_bf_to_sf (rtx val) +{ + rtx op = gen_lowpart (HImode, val), ret; + if (CONST_INT_P (op)) + { + ret = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, + val, BFmode); + if (ret) + return ret; + /* FLOAT_EXTEND simplification will fail if VAL is a sNaN. */ + ret = gen_reg_rtx (SImode); + emit_move_insn (ret, GEN_INT (INTVAL (op) & 0xffff)); + } + else + { + ret = gen_reg_rtx (SImode); + emit_insn (gen_zero_extendhisi2 (ret, op)); + } + emit_insn (gen_ashlsi3 (ret, ret, GEN_INT (16))); + return gen_lowpart (SFmode, ret); +} + #include "gt-i386-expand.h" diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h index 5318fc7fddf..e136f6ec175 100644 --- a/gcc/config/i386/i386-protos.h +++ b/gcc/config/i386/i386-protos.h @@ -227,6 +227,7 @@ extern void ix86_expand_atomic_fetch_op_loop (rtx, rtx, rtx, enum rtx_code, bool, bool); extern void ix86_expand_cmpxchg_loop (rtx *, rtx, rtx, rtx, rtx, rtx, bool, rtx_code_label *); +extern rtx ix86_expand_fast_convert_bf_to_sf (rtx); #ifdef TREE_CODE extern void init_cumulative_args (CUMULATIVE_ARGS *, tree, rtx, tree, int); diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index a2b8f26714a..01faa911b77 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -1668,28 +1668,8 @@ (pc)))] "" { - rtx op1 = gen_lowpart (HImode, operands[1]); - if (CONST_INT_P (op1)) - op1 = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, - operands[1], BFmode); - else - { - rtx t1 = gen_reg_rtx (SImode); - emit_insn (gen_zero_extendhisi2 (t1, op1)); - emit_insn (gen_ashlsi3 (t1, t1, GEN_INT (16))); - op1 = gen_lowpart (SFmode, t1); - } - rtx op2 = gen_lowpart (HImode, operands[2]); - if (CONST_INT_P (op2)) - op2 = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, - operands[2], BFmode); - else - { - rtx t2 = gen_reg_rtx (SImode); - emit_insn (gen_zero_extendhisi2 (t2, op2)); - emit_insn (gen_ashlsi3 (t2, t2, GEN_INT (16))); - op2 = gen_lowpart (SFmode, t2); - } + rtx op1 = ix86_expand_fast_convert_bf_to_sf (operands[1]); + rtx op2 = ix86_expand_fast_convert_bf_to_sf (operands[2]); do_compare_rtx_and_jump (op1, op2, GET_CODE (operands[0]), 0, SFmode, NULL_RTX, NULL, as_a <rtx_code_label *> (operands[3]), @@ -1723,28 +1703,8 @@ (const_int 0)]))] "" { - rtx op1 = gen_lowpart (HImode, operands[2]); - if (CONST_INT_P (op1)) - op1 = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, - operands[2], BFmode); - else - { - rtx t1 = gen_reg_rtx (SImode); - emit_insn (gen_zero_extendhisi2 (t1, op1)); - emit_insn (gen_ashlsi3 (t1, t1, GEN_INT (16))); - op1 = gen_lowpart (SFmode, t1); - } - rtx op2 = gen_lowpart (HImode, operands[3]); - if (CONST_INT_P (op2)) - op2 = simplify_const_unary_operation (FLOAT_EXTEND, SFmode, - operands[3], BFmode); - else - { - rtx t2 = gen_reg_rtx (SImode); - emit_insn (gen_zero_extendhisi2 (t2, op2)); - emit_insn (gen_ashlsi3 (t2, t2, GEN_INT (16))); - op2 = gen_lowpart (SFmode, t2); - } + rtx op1 = ix86_expand_fast_convert_bf_to_sf (operands[2]); + rtx op2 = ix86_expand_fast_convert_bf_to_sf (operands[3]); rtx res = emit_store_flag_force (operands[0], GET_CODE (operands[1]), op1, op2, SFmode, 0, 1); if (!rtx_equal_p (res, operands[0])) diff --git a/gcc/testsuite/gcc.target/i386/pr107628.c b/gcc/testsuite/gcc.target/i386/pr107628.c new file mode 100644 index 00000000000..a0de1179e67 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr107628.c @@ -0,0 +1,11 @@ +/* PR target/107628 */ +/* { dg-do compile } */ +/* { dg-options "-fsignaling-nans -msse2" } */ + +typedef __bf16 __attribute__((__vector_size__ (2))) V; + +void +foo (V v) +{ + v < (V) (short) 65436; +}
reply other threads:[~2022-11-19 9:17 UTC|newest] Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20221119091739.7BEC1385840E@sourceware.org \ --to=jakub@gcc.gnu.org \ --cc=gcc-cvs@gcc.gnu.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).