In this article are some benchmarks using the Jetson TX1 when running open-source tests using the stock GCC 4.8.4 compiler and then trying out GCC 4.9.3 and GCC 5.2.1. The same compiler flags were used each time when building the benchmarks under each of the different compilers using the automated Phoronix Test Suite. GCC 4.9 and GCC 5.2 were obtained from the Ubuntu Toolchain PPA. All tests are built on the Jetson TX1 without any cross-compilation or other steps.
As some extra benchmarks to toss out there this weekend are some Clang 3.8 SVN compiler benchmarks when trying out different optimization levels.
LLVM Clang 3.8 SVN was tested as of a few days ago atop an Ubuntu 15.10 x86_64 system. The Clang 3.8 tests were done when the CFLAGS/CXXFLAGS set separately to -O3 -march=native, -O3, -O2, -O1- and -O0. These numbers are just being put out there for reference purposes and using just a random selection of tests... Basically there was free time on one of the test systems and I was just running some extra benchmarks for testing some different code paths of the Phoronix Test Suite prior to its Hammerfest release.
With PHP 7.0 RC7 being the final development version of PHP 7, which is expected to be officially release at the end of the month, I've carried out some fresh benchmarks of PHP using our in-house benchmarking software. Compared in this latest PHP 7 benchmarking comparison is PHP 5.5 as packaged on Ubuntu 14.04 LTS and then comparing fresh builds of PHP 5.6.15 and PHP 7.0.0 RC7. On the HHVM side was using Facebook's HHVM 3.10.1 release as packaged for Ubuntu 14.04 LTS.
Yesterday AMD finally posted power management support for the AMDGPU DRM kernel driver when it comes to supported discrete graphics cards like Tonga and Fiji. I've been testing these PowerPlay Linux patches since yesterday to great success. In this article are results from a Radeon R9 285 and Radeon R9 Fury when testing these kernel patches along with the latest Mesa 11.1-devel Git drivers.
These AMDGPU PowerPlay patches are working out well so far in my tests. See the two aforementioned articles for more details on this AMDGPU power management code that lands more than 45000 lines of new code into this Direct Rendering Manager driver for the latest AMD graphics processors. It's just a pity that the code is too late for making it into the Linux 4.4 kernel merge window and thus won't be mainlined for a few months until the Linux 4.5 kernel. Up to now, the newer AMD graphics cards on the open-source AMD Linux driver have been limited to whatever (low) frequencies the core and memory clocks are initialized to at boot time. With PowerPlay, they can finally (and dynamically) ramp up when to their rated specifications.
AMD has finally published patches for providing preliminary PowerPlay support for the AMDGPU DRM driver, which will eventually replace the current DPM (Dynamic Power Management) support for Volcanic Islands hardware. This PowerPlay support comes with compatibility for Tonga, Fiji, and the rest of the VI line-up!
Here's the third installment of our Windows vs. Linux OpenGL benchmarking this week... This is a look at how the AMD Catalyst closed-source driver on Windows compares to AMD's latest open-source driver code on Linux.
Following the Intel Skylake Graphics: Windows 10 vs. Ubuntu Linux Performance and NVIDIA OpenGL: Windows 10 Pro vs. Ubuntu Linux Benchmarks is now a fresh look at the cross-platform performance for AMD Radeon graphics cards. This testing today is with the closed-source driver on Windows 10 Pro x64 and the open-source driver on Ubuntu 15.10 Linux.
Nvidia is hoping to attract machine learning developers with the Jetson TX1, an ARM-based development board powered by the top-end Tegra X1 SoC. The company claims that in certain deep learning tasks that rely on dynamic input and computations—autonomous drones, facial recognition and behavioural analysis, and computer vision—the Jetson TX1 will beat out an Intel Core i7 6700K Skylake CPU in performance.