With Clang 8.0 due out by month's end and GCC 9 due for release not long after that point, this week we've been running a number of GCC and Clang compiler benchmarks on Phoronix. At the start of the month was the large Linux x86_64 GCC vs. Clang compiler benchmarks on twelve different Intel/AMD systems while last week was also a look at the POWER9 compiler performance on the Raptor Talos II. In this article we are checking out these open-source compilers' performance on 64-bit ARM (AArch64) using an Ampere eMAG 32-core server.

Earlier this week I delivered the results of our largest-ever GCC vs. LLVM Clang Linux x86_64 compiler comparison with a dozen systems from various generations of Intel and AMD CPUs and using 62 benchmarks tested on GCC 8/9 and Clang 7/8 releases. In this article the compiler performance is being looked at for the IBM POWER9 architecture with the benchmarks done on a Raptor Computing Systems Talos II workstation running Ubuntu Linux.

After nearly two weeks of benchmarking, here is a look at our most extensive Linux x86_64 compiler comparison yet between the latest stable and development releases of the GCC and LLVM Clang C/C++ compilers. Tested with GCC 8, GCC 9.0.1 development, LLVM Clang 7.0.1, and LLVM Clang 8.0 SVN were tests on 12 distinct 64-bit systems and a total of 62 benchmarks run on each system with each of the four compilers... Here's a look at this massive data set for seeing the current GCC vs. Clang performance.

Glibc 2.29 was released a few days back and like most GNU C Library releases -- particularly in recent times -- does offer up more CPU performance optimizations... Some early benchmarks done this weekend do show some nice performance improvements in select workloads at least out of our initial benchmarking.

Since receiving the powerful NVIDIA Jetson AGX Xavier with its ARMv8 Carmel cores on this Tegra194 SoC a while back, it's been quite a fun developer board for benchmarking and various Linux tests. One of the areas I was curious about was whether GCC or Clang would generate faster code for this high performance ARM SoC, so here are some benchmarks.

With the mention earlier this week of GCC potentially enabling the vectorize options at the -O2 optimization level, I carried out some fresh GCC 9 development benchmarks at various optimization levels for reference.

Linus Torvalds just released Linux 5.0-rc1, what was formerly known as Linux 4.21 over the past two weeks. While the bumping was rather arbitrary as opposed to a major change necessitating the big version bump, this next version of the Linux kernel does come with some exciting changes and new features (of course, our Twitter followers already have known Linux was thinking of the 5.0 re-brand from 4.21). Here is our original feature overview of the new material to find in this kernel.

With the release earlier this month of Oracle VirtualBox 6.0, besides running some benchmarks of its VMSVGA 3D graphics support, I also ran some basic benchmarks to see how a similarly configured VM under both VirtualBox 6.0 with Linux KVM setup via virt-manager would compare for performance as we hit the end of 2018. This quick round of Linux virtualization tests was done on the AMD Ryzen Threadripper 2990WX system.

In early 2019 we will see the first stable release of GCC 9 as the annual update to the GNU Compiler Collection that is bringing the D language front-end, more C2X and C++ additions, various microarchitecture optimizations from better Znver1 support to Icelake, and a range of other additions we'll provide a convenient recap of shortly. But for those wondering how the GCC 9 performance is looking, here are some fresh benchmarks when benchmarking the latest daily GCC 9.0 compiler against GCC 7.4 and GCC 8.2 atop Clear Linux using an Intel Core i9 7980XE Skylake-X system.

Given the recently release of the PGI 18.10 Community Edition compiler by NVIDIA, I was curious to see how the performance on the CPU is looking for this proprietary compiler on Linux. For those curious as well, here are some benchmarks of the PGI 18.10 C/C++ compiler against the GCC 8.2.0 and LLVM Clang 7.0 open-source compilers.

With yesterday's release of Oracle VM VirtualBox 6.0, one of the most pressing changes for Linux guests is the use of the new VMSVGA 3D graphics device emulation by default. VMSVGA is the SVGA II graphics adapter from virtualization competitor VMware, but allows for the mature SVGA Linux graphics driver stack to be used. Here are some benchmarks looking at the OpenGL performance on VirtualBox 6.0.

Earlier this week I posted some benchmarks looking at the Linux kernel performance from the start to end of 2018 using an Intel Core i9 7980XE system. Here is the second part of that testing in looking at the same Linux 4.14 vs. 4.20 kernel benchmarking while putting the i9-7980XE performance side-by-side against the AMD Ryzen Threadripper 2990WX for seeing how its performance was impacted under the same kernel tests.

Here is a look at how the Linux kernel performance has evolved since Linux 4.10, which was released back in February of 2017, up through the current Linux 4.20 development cycle ahead of its debut at the end of December or early January. All of the Linux kernel benchmarks were done on the same venerable Intel Core i7 5960X system.

Due to the performance fallout from the introduction of STIBP for cross-hyperthread Spectre Variant Two mitigation in the Linux 4.20 kernel, the stable Linux kernels are reverting those patches after originally being quickly back-ported to those branches. For Linux 4.20, STIBP on by default for all processes remain in place until the revised STIBP code is ready for merging that is still expected to happen before the stable Linux 4.20 debut in about one month's time. Here are some initial benchmarks of those preliminary improvements.

Earlier this month marked the release of the AMD Optimizing C/C++ Compiler 1.3 (AOCC 1.3) with a re-base to the LLVM 7.0 code-base, enhanced loop optimizations, better vectorization, code generation, integration of the optimized AMD Math Library, and other enhancements. Here are some fresh benchmarks against AMD AOCC 1.3 against LLVM Clang 7.0 upstream as well as GCC 8.2.0.

As outlined yesterday, significant slowdowns with the Linux 4.20 kernel turned out to be due to the addition of the kernel-side bits for STIBP (Single Thread Indirect Branch Predictors) for cross-HyperThread Spectre Variant Two mitigation. This has incurred significant performance penalties with the STIBP support in its current state with Linux 4.20 Git and is enabled by default at least for Intel systems with up-to-date microcode. Here are some follow-up benchmarks looking at the performance hit with the Linux 4.20 development kernel as well as the overall Spectre and Meltdown mitigation impact on this latest version of the Linux kernel.

After running a lot of tests and then bisecting the Linux 4.20 kernel merge window, the reason for the significant slowdowns in the Linux 4.20 kernel for many real-world workloads is now known...

With GCC 9 embarking upon its third stage of development where the focus ships to working on bug/regression fixes in preparation for releasing the GCC 9.1 stable compiler likely around the end of Q1'2019, here is a fresh look at the GCC 9 performance with its latest development code as of this week compared to GCC 8.2.0 stable while using an Intel Core i9 7980XE test system running Ubuntu Linux. For good measure are also fresh results from LLVM Clang 7.0 stable as well as LLVM Clang 8.0 SVN for the latest development state of that competing C/C++ open-source compiler.

Over the past year we have looked extensively at the performance impact of Spectre mitigations on x86_64 CPUs but now with having the Raptor Talos II in our labs, here are some benchmarks to see the performance impact of IBM's varying levels of Spectre mitigation for POWER9.

Of the announcements from yesterday's AMD Next Horizon event, one that came as a surprise was the rolling out of current-generation EPYC processors to the Amazon Elastic Compute Cloud (EC2). Available so far are the AMD-powered M5a and R5a instance types to offer Amazon cloud customers more choice as well as being priced 10% lower than comparable instances. Here are some initial benchmarks of the AMD performance in the Amazon cloud.

With Linus Torvalds having just released Linux 4.20-rc1, here is our original feature overview looking at the major changes merged over the past two weeks for this new kernel. The Linux kernel will be ending 2018 on a high note with this kernel bringing more than 350 thousand lines of new code!

One of the benefits with the recently launched Core i9 9900K is hardware-based mitigations for Meltdown and L1TF/Foreshadow vulnerabilities. but mitigations are still needed for the other Spectre vulnerabilities. In this article is a look at the performance impact of still needing generic Retpolines via IBPB IBRS firmware for Spectre V2 and Speculative Store Bypass disabling (SSBD) for Spectre V4.

Now that WebRender has reached beta within Firefox Nightly, I decided to run some fresh web-browser benchmarks to see how this GPU-accelerated web rendering is working out for Firefox and how it compares to that of Google Chrome in some popular browser benchmarks.

Phoronix Test Suite 8.2.0-Rakkestad is officially shipping today as the latest quarterly feature release to our open-source, cross-platform automated benchmarking software. In addition to the Phoronix Test Suite 8.2 itself, there is the first official release of the newly-introduced "phoronix/pts" Docker image on Docker Hub for easily carrying out the benchmarks with the pre-seeded image.

Given last week's big GNOME 3.30 release I was eager to test the updated desktop environment with its Mutter compositor improvements on Wayland as well as seeing how its performance under the conventional X.Org Server. Here are some of these benchmarks of various graphics applications and games tested under both GNOME 3.28.3 and GNOME 3.30.0 with both Wayland and X.Org sessions.

There is a new public cloud provider that exited beta this past weekend and is exclusively offering Linux instances from Arch Linux to CentOS to Debian and Fedora. In addition to the usual assortment of Intel Xeon powered clouds/VPS instances, they also offer a range of AMD EPYC powered systems too.

With many of our other initially planned Threadripper 2 Linux benchmarks out of the way, recently I carried out a compiler benchmarking comparison on the Zen+ Ryzen Threadripper 2990WX between GCC and Clang.

One of the most frequent test requests recently has been to look at the overall performance cost of Meltdown/Spectre mitigations on the latest Linux kernel and now with L1TF/Foreshadow work tossed into the mix. With the Linux 4.19 kernel that just kicked off development this month has been continued churn in the Spectre/Meltdown space, just not for x86_64 but also for POWER/s390/ARM where applicable. For getting an overall look at the performance impact of these mitigation techniques I tested three Intel Xeon systems and two AMD EPYC systems as well as a virtual machine on each side for seeing how the default Linux 4.19 kernel performance -- with relevant mitigations applied -- to that of an unmitigated kernel.

With all of the confusion last week over Intel's short-lived CPU microcode license change that forbid benchmarking only for them to change it a short time later -- to a much nicer license in that the microcode files can be easily redistributed and don't curtail it in other manners (and also re-licensing their FSP too), here are some performance benchmarks when trying out this latest Intel microcode on Linux.

The Linux 4.19-rc1 kernel is expected to be released today and with that marks the end of feature development on this next kernel version. Here is a look at the new and improved features to be found in Linux 4.19.