| [eigen-commits] commit/eigen: rmlarsen: [Eigen] Vectorize evaluation of coefficient-wise functions over tensor blocks if the strides are known to be 1. Provides up to 20-25% speedup of the TF cross entropy op with AVX. |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen-commits Archives
]
- To: eigen-commits@xxxxxxxxxxxxxxxxxxx
- Subject: [eigen-commits] commit/eigen: rmlarsen: [Eigen] Vectorize evaluation of coefficient-wise functions over tensor blocks if the strides are known to be 1. Provides up to 20-25% speedup of the TF cross entropy op with AVX.
- From: Bitbucket <commits-noreply@xxxxxxxxxxxxx>
- Date: Wed, 07 Aug 2019 19:57:57 +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=RXkqULKo6JlUbEe2sLeH+7j7rvk=; b=cEsBWPG5ZFcOyF4sXbA0tfn C+Nz/GPQMaljkcFVMkqV5s1CanYKpkbxt48Zv0sxpoQiD6kXL/r7+t/AewdQqAM4 aPi+COcyg05ZKkM1/F75FM0+z+km5azDGEqeUzxuaO2/Rm6Qw41lmKwZbHRGkKG6 wJq/LBE94Zdh1RjKUQK0=
1 new commit in eigen:
https://bitbucket.org/eigen/eigen/commits/38ac14721e69/
Changeset: 38ac14721e69
User: rmlarsen
Date: 2019-08-07 19:57:42+00:00
Summary: [Eigen] Vectorize evaluation of coefficient-wise functions over tensor blocks if the strides are known to be 1. Provides up to 20-25% speedup of the TF cross entropy op with AVX.
A few benchmark numbers:
name old time/op new time/op delta
BM_Xent_16_10000_cpu 448µs ± 3% 389µs ± 2% -13.21%
(p=0.008 n=5+5)
BM_Xent_32_10000_cpu 575µs ± 6% 454µs ± 3% -21.00% (p=0.008 n=5+5)
BM_Xent_64_10000_cpu 933µs ± 4% 712µs ± 1% -23.71% (p=0.008 n=5+5)
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.