Weiwei Li
afe3987685
Add convertion function between binary float16 and float32 in softfloat
3 years ago
Andrew Waterman
540c3ce056
Remove non-installed header lists from Makefile fragments
It's just dead code. (Dependences on headers are auto-generated as
`.d` files.)
3 years ago
Andrew Waterman
08bac06bfd
Fix unused-variable warnings in softfloat
4 years ago
Andrew Waterman
ae747db810
Suppress unused-paramter warnings in softfloat
4 years ago
Jerin Joy
204a639780
Build and install lib and header dependencies for Hammer
https://github.com/rivosinc/hammer
Signed-off-by: Jerin Joy <joy@rivosinc.com>
4 years ago
Andrew Waterman
c8e510ec65
Significantly speed up compilation with GCC
Precompiled headers were broken because they weren't compiled with
the same -fPIC setting as the rest of the code. Fix by just making
everything use -fPIC.
5 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
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