Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2023-11-06 | add typedef for exceptionflags enumeration | Yanqi Yang | 1 | -2/+2 | |
2023-10-12 | adding two empty placeholder source file required for RISCV specialization ↵ | Nicolas Brunie | 2 | -0/+10 | |
on Linux-x86_64-GCC | |||||
2023-09-30 | review feedback: 16-bit floating-point -> BF16 | Nicolas Brunie | 2 | -3/+3 | |
2023-09-22 | fixing bf16_to_f32 for subnormal numbers | Nicolas Brunie | 1 | -11/+5 | |
2023-09-19 | Adding support for BF16 / BF16 <-> conversions in 8086-SSE | Nicolas Brunie | 3 | -0/+131 | |
2023-09-17 | Fixing bf32_to_bf16 conversions | Nicolas Brunie | 3 | -3/+68 | |
2023-08-12 | Fixing dummy bf16_to_f32 conversion | Nicolas Brunie | 3 | -2/+51 | |
2023-08-12 | Continuing f32_to_bf16 development | Nicolas Brunie | 3 | -12/+14 | |
2023-08-12 | Adding more bf16 support function + skeleton for f32_to_bf16 | Nicolas Brunie | 5 | -0/+229 | |
2023-08-12 | adding initial bf16 support | Nicolas Brunie | 6 | -0/+123 | |
2018-07-26 | Fix typo in function 'softfloat_propagateNaNF128M' for RISC-V. | John Hauser | 1 | -6/+6 | |
2018-01-26 | Release 3e. See "doc/SoftFloat-history.html". | John Hauser | 442 | -778/+4229 | |
2017-08-10 | Release 3d. See "doc/SoftFloat-history.html". | John Hauser | 391 | -446/+476 | |
2017-02-10 | Release 3c. See "doc/SoftFloat-history.html". | John Hauser | 401 | -822/+1049 | |
2016-07-22 | Release 3b. See "doc/SoftFloat-history.html". | John Hauser | 393 | -1476/+6844 | |
2016-02-22 | Added the ability to specify the result values delivered when conversions | John Hauser | 57 | -707/+1285 | |
from floating-point to an integer format raise an invalid exception. For the provided specializations (8086 and RISC-V), changed the result of converting a negative floating-point value to an unsigned integer format to now be zero. (Also renamed `shiftCount' inside functions to `shiftDist'.) | |||||
2016-01-23 | For "source/RISCV/specialize.h", updated year in copyright notice to 2016. | John Hauser | 1 | -1/+1 | |
2016-01-16 | Employ new RISC-V NaN encoding | Andrew Waterman | 1 | -6/+6 | |
2015-11-03 | Release 3a. | John Hauser | 336 | -8073/+9081 | |
2015-03-12 | Corrected the name of the subdirectory for RISC-V specialization from | John Hauser | 22 | -0/+0 | |
"RISC-V" to "RISCV". (In the names of machines, compilers, targets, etc., hyphens are intended for specifying variations and for forming compound names from multiple such components. While some arbitrariness in the application of this rule is inevitable, clearly RISC-V is not a "V" variation of an existing "RISC" architecture but rather an entirely new architecture.) | |||||
2015-02-19 | Fixed some bugs affecting a few processors. Reboot the official release | John Hauser | 12 | -65/+72 | |
date (for the last time) to be 2015 Feb 16. | |||||
2015-01-29 | Added specialization support for U.C. Berkeley's RISC-V. | John Hauser | 22 | -0/+1119 | |
2015-01-15 | Fixed conflicts over definitions of inline functions for non-GCC compilers. | John Hauser | 46 | -230/+234 | |
Reboot official release date to be 2015 Jan 9. | |||||
2014-12-11 | Fixed issues with specialization for x86, with and without SSE. | John Hauser | 26 | -34/+1648 | |
2014-12-11 | Update in RC for Release 3, fixing some bugs and adding to the documentation. | John Hauser | 15 | -10/+129 | |
2014-11-28 | First draft of RC for Release 3, to start review process. | John Hauser | 300 | -0/+28778 | |