| [eigen-commits] commit/eigen: markdryan: Fix the Packet16h version of ptranspose |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen-commits Archives
]
- To: eigen-commits@xxxxxxxxxxxxxxxxxxx
- Subject: [eigen-commits] commit/eigen: markdryan: Fix the Packet16h version of ptranspose
- From: Bitbucket <commits-noreply@xxxxxxxxxxxxx>
- Date: Fri, 06 Jul 2018 22:38:35 +0000 (UTC)
- Dkim-signature: v=1; a=rsa-sha1; c=relaxed/relaxed; d=bitbucket.org; h=mime-version:content-type:content-transfer-encoding:subject:from:to; s=s1; bh=sFvEk+vfJ34nkSrO6VzoPndfmj8=; b=P5bhOsqR8ui5DZCZln33fuV fmUZXtH9/aFdKAUIBqtpyKPsRP/Hk8awFZ13nbeykBlRbdBVOdgrLdn1Ax8uoFxM UH0XLbk475AD6vt5Cro+FNSL3uL6dsatJmFWTuwUDNCVcvSXZ0Nk5A/76EMBHp41 1VkW8l3nZ+dkHqgyzsbo=
1 new commit in eigen:
https://bitbucket.org/eigen/eigen/commits/35cdaf72cf97/
Changeset: 35cdaf72cf97
User: markdryan
Date: 2018-06-16 22:13:06+00:00
Summary: Fix the Packet16h version of ptranspose
The AVX512 version of ptranpose for PacketBlock<Packet16h,16> was
reordering the PacketBlock argument incorrectly. This lead to errors in
the multiplication of matrices composed of 16 bit floats on AVX512
machines, if at least of the matrices was using RowMajor order. This
error is responsible for one tensorflow unit test failure on AVX512
machines:
//tensorflow/python/kernel_tests:batch_matmul_op_test
Affected #: 1 file
Repository URL: https://bitbucket.org/eigen/eigen/
--
This is a commit notification from bitbucket.org. You are receiving
this because you have the service enabled, addressing the recipient of
this email.