diff options
author | liuhongt <hongtao.liu@intel.com> | 2022-12-02 09:54:06 +0800 |
---|---|---|
committer | liuhongt <hongtao.liu@intel.com> | 2022-12-02 20:30:22 +0800 |
commit | e55251f3d3598ca6e001c4afa51b2ec913b4cac1 (patch) | |
tree | 0842ff5362b228bc64d3348690d7ae3ebc307c83 | |
parent | 71e800747e42d91888a0533ce797ce8e4a8c2baf (diff) | |
download | gcc-e55251f3d3598ca6e001c4afa51b2ec913b4cac1.zip gcc-e55251f3d3598ca6e001c4afa51b2ec913b4cac1.tar.gz gcc-e55251f3d3598ca6e001c4afa51b2ec913b4cac1.tar.bz2 |
Improve ix86_expand_fast_convert_bf_to_sf with new extendbfsf2_1.
After supporting extendbfsf2_1, ix86_expand_fast_convert_bf_to_sf can
be improved with pslld either.
CONST_INT_P is not handled since constant shift can be optimized off.
gcc/ChangeLog:
* config/i386/i386-expand.cc
(ix86_expand_fast_convert_bf_to_sf): Use extendbfsf2_1 for
nonimmediate operand.
gcc/testsuite/ChangeLog:
* gcc.target/i386/cbranchbf4.c: New test.
-rw-r--r-- | gcc/config/i386/i386-expand.cc | 13 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/i386/cbranchbf4.c | 15 |
2 files changed, 21 insertions, 7 deletions
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 04aadda..b920cfb 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -24187,14 +24187,13 @@ ix86_expand_fast_convert_bf_to_sf (rtx val) /* FLOAT_EXTEND simplification will fail if VAL is a sNaN. */ ret = gen_reg_rtx (SImode); emit_move_insn (ret, GEN_INT (INTVAL (op) & 0xffff)); + emit_insn (gen_ashlsi3 (ret, ret, GEN_INT (16))); + return gen_lowpart (SFmode, ret); } - 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); + + ret = gen_reg_rtx (SFmode); + emit_insn (gen_extendbfsf2_1 (ret, force_reg (BFmode, val))); + return ret; } #include "gt-i386-expand.h" diff --git a/gcc/testsuite/gcc.target/i386/cbranchbf4.c b/gcc/testsuite/gcc.target/i386/cbranchbf4.c new file mode 100644 index 0000000..8241a0c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/cbranchbf4.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-fexcess-precision=16 -O -msse2 -mfpmath=sse" } */ +/* { dg-final { scan-assembler-times "pslld" 4 } } */ + +char +foo (__bf16 a, __bf16 b) +{ + return a > b; +} + +float +foo1 (__bf16 a, __bf16 b, float c, float d) +{ + return a > b ? c : d; +} |