| commit | b9057925955f066c1c88719f6bbff29cfc5fe666 | |
| author | Erik Lindahl <erik@kth.se> | |
| Thu, 25 May 2017 18:01:57 +0000 (25 20:01 +0200) | ||
| committer | Roland Schulz <roland.schulz@intel.com> | |
| Mon, 28 Aug 2017 20:17:57 +0000 (28 22:17 +0200) | ||
| tree | a7638f72707a5c7b55418950ff52b92b75e69fd5 | treesnapshot (tar.gz zip) |
| parent | a3502742b47b00cc1436511eaa7b8c355cdab757 | commitdiff |
Improved SIMD test data to use all bits
The SIMD test data now uses all available bits in the
current precision floating-point numbers, to catch errors
where we lose precision or have mistakes in single/double
conversions (e.g. return values). Since some operations now
depend on the least significant bit, a few tests have been
relaxed to allow a tolerance rather than require exact
binary matching.
The new tests caught a precision loss in a reduction
function for the SIMD-mimicking scalar functions, but this
has never been used apart from testing, and should be harmless.
Fixes #2163.
Change-Id: I6d8f19d2aafeee8f42a2034c6100fcb10f6d2e81
The SIMD test data now uses all available bits in the
current precision floating-point numbers, to catch errors
where we lose precision or have mistakes in single/double
conversions (e.g. return values). Since some operations now
depend on the least significant bit, a few tests have been
relaxed to allow a tolerance rather than require exact
binary matching.
The new tests caught a precision loss in a reduction
function for the SIMD-mimicking scalar functions, but this
has never been used apart from testing, and should be harmless.
Fixes #2163.
Change-Id: I6d8f19d2aafeee8f42a2034c6100fcb10f6d2e81
18 files changed: