The version year information contained in the prebuilt driver vtsspp for VTune™ Amplifier XE 2015 Update 1 is incorrect. You may notice this when using a tool such as readelf to view the binary elf headers, or when browsing the sepdk source files.
Product affected: Intel® System Studio 2015
Component affected: Intel® C++ Compiler 15.0 for Android* target
OS affected: Windows OS, Linux OS
NDK affected: should affect all supported NDK versions (verified with NDK r9d to reproduce).
Internal defect tracking ID (CQ): DPD200362855
英特尔致力于帮助开发人员提供能够在英特尔架构上正常运行（甚至出色运行）的 Android 应用。 虽然英特尔主要致力于社区层面：优化 Dalvik Java、V8 引擎和 Bionic C；丰富代码库；为 IA 提供采用 32 位和 64 位内核的版本，他们同样提供了多种类型的新工具为 Android 开发人员提供帮助。 这些工具主要用于提高性能，使其超过面向 x86 的默认 ARM 转换层：libhoudini 所提供的性能。
但是首先需要选择合适的工具。 创建 Android 应用有 3 种常见的方法。
Product Version: Intel® Fortran Compiler 15.0 and a later version
The vectorization report generated using Intel® Fortran Compiler's optimization and vectorization report options includes non-vectorized loop instance:
Windows* OS: /O2 /Qopt-report:2 /Qopt-report-phase:vec
There is a known compatibility problem between Hydra and versions 7.2 and 7.3 of the GNU* Debugger (gdb*). When running Hydra under one of these versions, Hydra will hang.
Please use a different version of gdb in order to run Hydra under gdb.
This has only been seen in Linux* at this time.
There is currently a known issue in the Intel® MPI Library for Linux*, affecting Version 5.0 and Version 5.0 Update 1. The compiler wrapper scripts will always return 0, even if the compile or link failed. This can lead to errors in makefiles or any job checking the return code. The error is corrected and a fix is available in Version 5.0 Update 2.
There are currently three workarounds for this issue:
This is a list of what are hopefully helpful hints for troubleshooting problems with OFED* and InfiniBand* when used with the Intel® Xeon Phi™ coprocessor.
1) Finding Documentation
The primary sources for information on OFED for the Intel Xeon Phi coprocessor are:
Intel has a vested interest in helping developers provide Android applications that run well (or even best) on Intel architecture. While Intel is working at the community level - optimizing Dalvik Java, V8 engine, and Bionic C; contributing to the code base; and providing releases with both 32 bit and 64-bit Kernels for IA; they are also creating new tools to help Android developers. Many of these focus on improving performance beyond that available with the default ARM translation layer for x86: libhoudini