Comments (4)
That... was a different bug! 🤕 Will teach me to write descriptions in my tickets...
The bug which I am actually observing is that when running "make/ninja xbenchmark" on my Haswell-based machine, a pair of "neon" rows is present in the table of timings, even though this CPU certainly has no neon instructions available.
It is not fixed by the patch which you have merged today.
from xsimd.
I am curious about this issue too, but there is still no answer after 1 year?
Here is xsimd_benchmark
's output, which shows neon rows, even though it is on x86 machine.
============================
fdim
scalar float : 0.166787ms
sse float : 0.006347ms
sse float unr : 0.005641ms
avx float : 0.004584ms
avx float unr : 0.003526ms
neon float : 0.008462ms
neon float unr : 0.007757ms
scalar double : 0.171724ms
sse double : 0.016573ms
sse double unr : 0.020451ms
avx double : 0.017278ms
avx double unr : 0.015162ms
neon double : 0.018689ms
neon double unr: 0.014457ms
============================
from xsimd.
Yep, this is very strange. This isssue fell between the cracks as it was closed by mistake.
from xsimd.
We no longer have the issue, and I took this issue as an opportunity to cleanup becnhmark display a bit, cf. #876
from xsimd.
Related Issues (20)
- Build failure on ARM v8 with SVE (`neoverse_v1`) architecture HOT 4
- Obsolete the `version()` method from register description
- Change representation of instruction set extensions HOT 1
- error: no member named 'bitwise_rshift' in namespace 'xsimd' HOT 4
- Any plans to add support for element-wise max? HOT 2
- When would xsimd has next new Release? HOT 4
- xsimd::available_architectures() fails to skip CPU features when they are explicitly disabled by OS HOT 2
- Doc for Conditional Expression malformed
- On Darwin systems only: `test_error_gamma.cpp:150: ERROR: CHECK_EQ( diff, 0 ) is NOT correct` HOT 1
- __builtin_shufflevector seems to be never enabled
- Warning from CMake HOT 1
- Build fail on windows with MSVC (v13)
- load_unaligned seems to segfault
- `xsimd::exp` broken on aarch64 and GCC 10.2.1 with `--fast-math` HOT 1
- How to implement an expand function / scatter for masks? HOT 9
- Build failure on armv7l-linux and riscv64-linux (11.2.0, 12.0.0) (`error: 'batch_bool_cast' was not declared in this scope`) HOT 2
- Build failure on armv7a-linux with >=xsimd-11.2.0 HOT 2
- pow broken for 0^(-x) HOT 1
- scalar implementation without code duplication HOT 4
- ppc64el fails with clang : too few template arguments for class template 'batch' HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from xsimd.