Chih-Min Chao
|
eceda60356
|
softfloat: add reciprocal api
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
6 years ago |
|
Chih-Min Chao
|
4ece06558c
|
sf: add f16_to_[u]i8 APIs
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
6 years ago |
Han-Kuan Chen
|
2b38341691
|
sf: fp16: add missing APIs
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
6 years ago |
|
Chih-Min Chao
|
8663f6494e
|
rvv: sf: handle signaling NaN for fmax/fmin
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
6 years ago |
Andrew Waterman
|
7dfd3525c8
|
Enable SOFTFLOAT_ROUND_ODD for vfncvt.rod.f.f.w
|
6 years ago |
Marcus Comstedt
|
f437e6a4e9
|
Implement support for big-endian hosts
|
7 years ago |
|
Chih-Min Chao
|
b96463c921
|
rvv: extend softfloat to support 16-64 min/max function
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
7 years ago |
|
Chih-Min Chao
|
df54c7a905
|
build: build softfloat with pic and provide shared library
vector unit tests need identical floating library to generate golden
pattern
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
7 years ago |
Prashanth Mundkur
|
1fb7753da0
|
Fix a missed header file in the softfloat include install.
|
8 years ago |
|
Andrew Waterman
|
bd85811c35
|
Update SoftFloat
|
9 years ago |
Andrew Waterman
|
10ae74e48a
|
Allow configuration of default ISA with --with-isa
|
10 years ago |
|
Andrew Waterman
|
89ba757daf
|
Mark SoftFloat routines static inline
This avoids duplicate definitions on some platforms.
|
10 years ago |
|
Andrew Waterman
|
a95b44df9d
|
Upgrade to latest SoftFloat
|
10 years ago |
|
Andrew Waterman
|
853391c2bb
|
Fix NaN propagation for fcvt
|
10 years ago |
|
Andrew Waterman
|
3face89faf
|
Use new NaN discipline
|
10 years ago |
|
Andrew Waterman
|
c0e63cb0d4
|
Softfloat fcvt.{w/l}.d now returns -MaxInt for -NaN
|
11 years ago |
|
Andrew Waterman
|
7e4df4d518
|
Softfloat fcvt.{w/h}.s now returns -MaxInt for -NaN
Behavior now consistent with RISC-V user spec.
|
11 years ago |
Andrew Waterman
|
ab14719919
|
Add fclass.{s|d} instructions
|
12 years ago |
|
Andrew Waterman
|
017f62ac55
|
Merge softfloat_riscv into softfloat
They really aren't independent libraries.
|
12 years ago |
|
Andrew Waterman
|
b282d6e8c0
|
make NaN behavior consistent with hardfloat
|
14 years ago |
Andrew Waterman
|
77452a26e7
|
temporary undoing of renaming
|
15 years ago |
|
Andrew Waterman
|
740f981cfd
|
[sim] renamed to riscv-isa-run
|
15 years ago |
Andrew Waterman
|
ab928baadb
|
[sim] made softfloat files C instead of C++
|
16 years ago |
|
Andrew Waterman
|
50ec828baf
|
[sim] integrated SoftFloat-3 with ISA sim; removed SoftFloat-2b
|
16 years ago |
|
Andrew Waterman
|
b46f178e58
|
[sim] specialized softfloat for riscv
|
16 years ago |
|
Andrew Waterman
|
9ba7af90cc
|
[sim] added riscv folder to softfloat
|
16 years ago |
|
Andrew Waterman
|
932ec48ad5
|
[sim] added SoftFloat-3 source
|
16 years ago |
|
Andrew Waterman
|
2d75bf71bb
|
[xcc,sim] implement FP using softfloat
The intersection of the Hauser FP and MIPS FP is implemented.
|
16 years ago |
|
Andrew Waterman
|
cf2bb15395
|
[sim] added softfloat
|
16 years ago |
