[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[RFC PATCH 0/3] Floating-point OE/UE exception bug
From: |
Lucas Mateus Castro(alqotel) |
Subject: |
[RFC PATCH 0/3] Floating-point OE/UE exception bug |
Date: |
Wed, 3 Aug 2022 09:22:14 -0300 |
From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>
The PowerISA defines that if an overflow exception happen with FPSCR.OE
set, the exponent of the intermediate result is subtracted 1536 in
double precision operations and is added 1536 in an underflow exception,
currently this behavior is not QEMU's behavior, this patch series fixes
that.
Currently there's no test in this patch series as there's no way to
disable MSR.FE0 and MSR.FE1 in linux user, so any overflow/underflow
exception with OE/UE set causes a trapping exception.
This patch series is not complete as it's still missing many other
instructions (including all single precision ones), so I'd just like to
request comment on the approach used here.
Thanks.
Lucas Mateus Castro (alqotel) (3):
target/ppc: Bugfix fadd/fsub result with OE/UE set
target/ppc: Bugfix fmul result with OE/UE set
target/ppc: Bugfix fdiv result with OE/UE set
fpu/softfloat.c | 135 ++++++++++++++++++++++++++++++++++++++++
include/fpu/softfloat.h | 4 ++
target/ppc/fpu_helper.c | 20 ++++--
3 files changed, 155 insertions(+), 4 deletions(-)
--
2.31.1
- [RFC PATCH 0/3] Floating-point OE/UE exception bug,
Lucas Mateus Castro(alqotel) <=
[RFC PATCH 2/3] target/ppc: Bugfix fmul result with OE/UE set, Lucas Mateus Castro(alqotel), 2022/08/03
[RFC PATCH 3/3] target/ppc: Bugfix fdiv result with OE/UE set, Lucas Mateus Castro(alqotel), 2022/08/03
[PATCH] tests/tcg/ppc64le: Added OE/UE enabled exception test, Lucas Mateus Castro(alqotel), 2022/08/03