The Linaro Toolchain Working Group is pleased to announce the release of both Linaro GCC 4.6 and Linaro GCC 4.5.
Linaro GCC 4.6 is the fourth release in the 4.6 series. Based off the latest GCC 4.6.0+svn174261, it adds new optimisations and vectoriser improvements.
Interesting changes include: * Updates to 4.6.0+r174261 * Blocks can now vectorise into ORN and BIC instructions * Support for half word to double word multiply and accumulate operations * Better support for other widening multiply operations * Further performance improvements in NEON strided loads and stores * Performance improvements targeted at EEMBC CoreMark
Fixes: * PR target/48454: Set the lengths correctly for the case with Quad vectors.
Known issues: * Building Python 2.7 with -mfpu=neon exposes a bug in vmov.i64 in binutils 2.20.51. Please use 2.21 or later.
The strided load/store improvements allow the vectoriser to efficiently access values that occur at every n'th address, such as all of the red values in a RGB image or all of the left channel samples in a interleaved audio array. For example, a plain C function that converts between RGB and CYMK now runs 7.3 x faster on an A9.
Linaro GCC 4.5 2011.06 is the eleventh release in the 4.5 series. Based off the latest GCC 4.5.3+svn174250, it is a maintenance focused release.
Interesting changes in 4.5 include: * Updates to 4.5.3+r174250
Fixes: * LP: #744754: ICE in reload_cse_simplify_operands, at postreload.c:402 with neon optimized code * LP: #748138: ICE in redirect_jump, at jump.c:1443
The source tarball is available from: https://launchpad.net/gcc-linaro/+milestone/4.6-2011.06-0 https://launchpad.net/gcc-linaro/+milestone/4.5-2011.06-0
Downloads are available from the Linaro GCC page on Launchpad: https://launchpad.net/gcc-linaro
Interested in commercial support? inquire at email@example.com