This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[PATCH, i386]: Fix PR target/40811: unsigned int to float isn't vectorized

Hello!

As shown by H.J. in the PR, ICC is able to vectorize unsigned int -> float conversion. This patch implements the same approach (using masked compare) for gcc.

2009-07-21 Uros Bizjak <ubizjak@gmail.com>

    PR target/40811
    * config/i386/sse.md (sse2_cvtudq2ps): New expander.
    (enum ix86_builtins): Add IX86_BUILTIN_CVTUDQ2PS.
    (builtin_description): Add __builtin_ia32_cvtudq2ps.
    (ix86_vectorize_builtin_conversion): Handle IX86_BUILTIN_CVTUDQ2PS.

testsuite/ChangeLog:

2009-07-21 Uros Bizjak <ubizjak@gmail.com>

    PR target/40811
    * lib/target-supports.exp (check_effective_target_vect_uintfloat_cvt):
    Add i?86 and x86_64 targets.
    * gcc.target/i386/vectorize7.c: New test.

    PR target/40809
    * gcc.target/i386/pr40809.c: New test.

Patch was bootstrapped and regression tested on x86_64-pc-linux-gnu. Patch was committed to mainline.

Uros.

Attachment: p.diff.txt
Description: Text document

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]