- Apr 22, 2020
-
-
Jim Lawson authored
-
- Apr 07, 2020
-
-
Jerry Zhao authored
-
- Mar 26, 2020
-
-
Andrew Waterman authored
-
Andrew Waterman authored
-
- Mar 10, 2020
-
-
Jim Lawson authored
Support publishing
-
- Feb 29, 2020
-
-
Jim Lawson authored
Restore project (with sbt version) Add required publishing information.
-
- Feb 20, 2020
-
-
Jim Lawson authored
Restore SNAPSHOT version.
-
Jim Lawson authored
-
Jim Lawson authored
1.2.x mergewithmaster
-
- Feb 07, 2020
-
-
Jim Lawson authored
-
Jim Lawson authored
-
- Dec 20, 2019
-
-
Andrew Waterman authored
-
Andrew Waterman authored
One-hot-encode the cycle number, so that the trial remainder doesn't depend on the output of a decoder. For a single-precision divider, this increases the FF count from 100 to 122, but for a moderate frequency target, it's roughly area-neutral and leaks less.
-
- Dec 19, 2019
-
-
Jim Lawson authored
-
- Nov 26, 2019
-
-
Jim Lawson authored
Bump build.sbt for next release.
-
- Nov 15, 2019
-
-
Andrew Waterman authored
Might do this for other HardFloat modules over time, but this is the one I need for the time being.
-
- Nov 07, 2019
-
-
Jim Lawson authored
Bump for 1.2-20191106-SNAPSHOT.
-
- Nov 06, 2019
-
-
Jim Lawson authored
Bump master SNAPSHOT version.
-
Jim Lawson authored
-
- Nov 02, 2019
-
-
Jim Lawson authored
-
- Oct 31, 2019
-
-
Jim Lawson authored
-
- Oct 24, 2019
-
-
Jim Lawson authored
-
- Oct 22, 2019
-
-
Andrew Waterman authored
Sometimes using the RawFloat version directly is more useful.
-
- Oct 16, 2019
-
-
Jim Lawson authored
-
- Oct 03, 2019
-
-
Jim Lawson authored
-
- Sep 21, 2019
-
-
Jim Lawson authored
-
- Sep 18, 2019
-
-
Jim Lawson authored
-
- Sep 11, 2019
-
-
Jim Lawson authored
-
- Jul 23, 2019
-
-
Andrew Waterman authored
For example, when converting from uint128 to float32 (whose max exponent is 2^127), the unit fails to detect overflow for numbers just under 2^128. The bug only manifests when the ranges are that close. If the float has greater range, or has much smaller range, the bug does not manifest. Existing RV32 and RV64 cores are unaffected by this bug, because no such conversions exist in the ISA.
-
Andrew Waterman authored
-
- Feb 23, 2019
-
-
Paul Rigge authored
* Update testing infrastructure from chisel 2 to 3. This requires updates to the test harness, as well as to the driver. Use verilator for tests. Tests run but are currently failing and I'm not sure why. * Use strtoull instead of strtoll * Fix incorrect outputs
-
Murali Vijayaraghavan authored
* added detailed algorithm used for sqrt * fixed wording * added explanation for division
-
- Jan 29, 2019
-
-
Andrew Waterman authored
This reverts commit ca89a808. See this discussion for an explanation: https://github.com/ucb-bar/berkeley-hardfloat/pull/28
-
- Jan 26, 2019
-
-
Paul Rigge authored
-
- Feb 10, 2018
-
-
John Hauser authored
SoftFloat/TestFloat Release 3e. First, the rounding mode code for 'odd' rounding is changed from 5 to 6. Second, conversions to integer now round to the nearest odd integer instead of rounding to minimum magnitude.
-
- Jan 31, 2018
-
-
Richard Xia authored
-
- May 30, 2017
-
-
Yunsup Lee authored
* add small div/sqrt unit * Chisel3 doesn't permit mixed UInt/SInt muxing/assignment * Fix control bug in DivSqrtRecFN_small After an uncommon-case operation, outValid would remain high until another inValid was presented, instead of going low after one cycle.
-
- May 19, 2017
-
-
jhauser-ucberkeley authored
integers.
-
- Apr 27, 2017
-
-
John Hauser authored
'RoundAnyRawFNToRecFN'.
-
John Hauser authored
integer values in module 'DivSqrtRecF64_mulAddZ31'.
-