mbox series

[00/11] softfloat: Improve denormal handling

Message ID 20210527041405.391567-1-richard.henderson@linaro.org
Headers show
Series softfloat: Improve denormal handling | expand

Message

Richard Henderson May 27, 2021, 4:13 a.m. UTC 
This attempts to fix the x86 denormal-exception flag, which is the
inverse of the existing float_flag_input_denormal flag.  I have not
created a new test case for this yet, fwiw.

While auditing all uses of float_flag_*_denormal, I found some errors
in target/rx and target/mips.

This is based on my current softfloat conversion for floatx80:
Based-on: <20210525150706.294968-1-richard.henderson@linaro.org>

The complete tree may be found at
https://gitlab.com/rth7680/qemu/-/commits/fpu-test-5


r~


Richard Henderson (11):
  softfloat: Rename float_flag_input_denormal to
    float_flag_iflush_denormal
  softfloat: Rename float_flag_output_denormal to
    float_flag_oflush_denormal
  softfloat: Introduce float_flag_inorm_denormal
  softfloat: Introduce float_flag_result_denormal
  target/i386: Use float_flag_inorm_denormal
  target/rx: Handle the FPSW.DN bit in helper_set_fpsw
  target/rx: Use FloatRoundMode in helper_set_fpsw
  target/rx: Fix setting of FPSW.CE
  target/mips: Drop inline markers from msa_helper.c
  target/mips: Do not check MSACSR_FS_MASK in update_msacsr
  target/mips: Drop denormal operand to update_msacsr

 include/fpu/softfloat-types.h |  18 +-
 fpu/softfloat.c               |  88 ++++------
 target/arm/sve_helper.c       |   6 +-
 target/arm/vfp_helper.c       |  12 +-
 target/i386/tcg/fpu_helper.c  |  18 +-
 target/mips/tcg/msa_helper.c  | 298 +++++++++++++++-------------------
 target/rx/op_helper.c         |  19 ++-
 target/tricore/fpu_helper.c   |   6 +-
 fpu/softfloat-parts.c.inc     |  13 +-
 9 files changed, 212 insertions(+), 266 deletions(-)

-- 
2.25.1

Comments

Alex Bennée June 7, 2021, 4:31 p.m. UTC | #1 
Richard Henderson <richard.henderson@linaro.org> writes:

> This attempts to fix the x86 denormal-exception flag, which is the

> inverse of the existing float_flag_input_denormal flag.  I have not

> created a new test case for this yet, fwiw.

>

> While auditing all uses of float_flag_*_denormal, I found some errors

> in target/rx and target/mips.


Softfloat code looks good to me, I'm leaving the target specific stuff
to the arch maintainers as I have a hard enough time with just one
architectures FP vagaries ;-)

-- 
Alex Bennée