While Intel Haswell processors won't even be released to the public until later this year, compiler developers have already been working on supporting the new instruction set extensions of Haswell for more than one year. GCC developers already have early Intel Broadwell support ready for GCC 4.8.
Are there any performance improvements in store for GCC 4.8 as it affects the ARMv7 Cortex-A15 processor on SoCs like the Samsung Exynos 5 Dual? Here's some benchmark results to find out.
LLVM's Clang C/C++ compiler front-end is nearing feature completion for supporting C++11, the latest C++ ISO standard.
While LLVM and Clang (and related LLVM projects) remain in heavy development for the 3.3 cycle, up today are some initial compiler benchmarks of LLVM/Clang 3.3 SVN compared to the current stable release.
Aside from improvements to Link-Time Optimizations, run-time library improvements, and a new optimization level, the coming release of GCC 4.8 also features support for yet-to-be-out AMD hardware. AMD's Steamroller "Bulldozer 3" processor is already supported with compiler optimizations and so is AMD Jaguar, their new low-power APU that's rumoured to be in the next-generation consoles.
The release of LLVM 3.3 is still months away, but one of its features already are notable improvements to its loop vectorizer.
Code Synthesis has released version 2.2 of their ODB C++ Object-Relational Mapping (ORM) code.
CLDOC is a document generator for C and C++ projects to create documentation automatically out of comments as well as creating XML-based descriptions of the API. CLDOC is a new project but already sounds promising and is being powered by LLVM's Clang C/C++ front-end for its parser.
It's going on two years since the release of PCC 1.0, but there hasn't been any follow-on Portable C Compiler release nor is there much public-facing development activity happening.
PathScale, the company that's focused on providing high-performance compiler solutions, is hoping to speed up traditional software packages by automatically leveraging the graphics processor when compiling software with the PathScale ENZO compiler.
GCC 4.8 will feature a few improvements when it comes to LTO, a.k.a. Link-Time Optimization, but will this reflect in any greater performance for the resulting binaries?
The AArch64 back-end to LLVM that provides support for the compiler infrastructure to target ARMv8 64-bit hardware, is now enabled within the default build.
Another interesting open-source project has tipped up that is powered by the LLVM compiler infrastructure.
GCC has had support for 64-bit ARM, a.k.a. AArch64, going back to last summer for using the open-source compiler with next-generation ARMv8 hardware. Being merged today is finally support for the LLVM compiler infrastructure with an experimental 64-bit ARM/AArch64 back-end target.
Back on Tuesday there was a basic email by a developer volleyed on the GCC mailing list, which has since sparked dozens of responses and a rather interesting conversation about the future of the GNU Compiler Collection and its ultimate path and viability moving forward. The initial e-mail was simply an inquiry asking about an estimated time-frame for having full support of the ISO C++11 specification. Diego Novillo, a well known GCC developer and Google employee, has even expressed fear that GCC may be past the tipping point and could die out naturally.
There's been many Phoronix articles already covering features and changes coming to GCC 4.8, the next major compiler update to come out of the Free Software Foundation in March or April. One of the areas that's seen improvements in GCC 4.8 and not talked about much yet is the improvements to its runtime library, libstdc++, with new features being present.
The LLVM compiler infrastructure and the Clang C/C++ compiler front-end are being ported to the GNU/Hurd operating system.
Version 0.7 of POCL, the Portable OpenCL implementation targeting OpenCL 1.2 compliance, has been officially released.
While C++11 is an ISO standard and the Clang C/C++ compiler front-end to LLVM has been supporting C++11, developers behind the LLVM compiler infrastructure are still deciding whether to allow C++11 language features within their code-base.
Since publishing LLVM/Clang 3.2 benchmarks a few days ago that showed the Clang C/C++ compiler competing with -- and in some cases outperforming -- the GCC compiler on Intel x86_64, several Phoronix readers have been asking how things compare on the ARM side.
One of the features sadly not found in the recent release of LLVM/Clang 3.2 is OpenMP support.
While just released on Friday, FreeBSD has already pulled LLVM/Clang 3.2 into its "head" repository and will be pushing it into the FreeBSD 9/Stable series in the weeks ahead.
While the features of LLVM 3.2 and its Clang C/C++ compiler front-end have been talked about in numerous Phoronix articles over the past few months, here's an overview of the new features for this open-source compiler infrastructure update that was released on Friday.
It's a few days late, but LLVM 3.2 has been officially released.
In preparing for the imminent release of LLVM 3.2, another worthwhile feature to go over is the NVPTX back-end that's been merged for this forthcoming open-source compiler infrastructure release. The NVPTX LLVM back-end is what's used by NVIDIA's closed-source driver for its CUDA and OpenCL compiler.
The soon-to-be-released LLVM 3.2 compiler infrastructure will expand upon its coverage of processor support and CPU capabilities.
Premiering with LLVM 3.2, which will debut later this month, is an automatic loop vectorizer. I've already delivered benchmarks of LLVM's new automatic loop vectorizer, but here's more details on this new LLVM compiler feature.
The videos from last month's LLVM Developers' Meeting in San Jose, California have now been uploaded to the Internet.
625 Compiler news articles published on Phoronix.