Andrew Waterman
|
29da1405c4
|
Fix C/C++ thread-local linkage differently
Just admit Mac OS is broken, so explicitly special-case it.
See #1689 and #1703
|
2 years ago |
|
Andrew Waterman
|
fe47d091e1
|
Add several BF16 ops to SoftFloat
|
2 years ago |
|
Andrew Waterman
|
4a884e684c
|
Consistently order BF16 routines in Makefile and softfloat.h
|
2 years ago |
|
Andrew Waterman
|
6c008e990c
|
Make softfloat's rounding mode thread-local
This has no effect on Spike itself, but it might matter for anyone who's
using Spike as a library in a multithreaded program.
|
2 years ago |
Weiwei Li
|
afe3987685
|
Add convertion function between binary float16 and float32 in softfloat
|
3 years ago |
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
|
b96463c921
|
rvv: extend softfloat to support 16-64 min/max function
Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
|
7 years ago |
|
Andrew Waterman
|
bd85811c35
|
Update SoftFloat
|
9 years ago |
Andrew Waterman
|
a95b44df9d
|
Upgrade to latest SoftFloat
|
10 years ago |
Andrew Waterman
|
ab14719919
|
Add fclass.{s|d} instructions
|
12 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
|
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 |
