a2940d63b4a3ed43b3a079b669fab3bd466f9dad
build to handle recent change to API. If building with LLVM tot, a
version starting with or after this change must be used:
commit 276365dd4bc0c2160f91fd8062ae1fc90c86c324
Author: Evan Cheng <evan.cheng@apple.com>
Date: Thu Jun 30 01:53:36 2011 +0000
Fix the ridiculous SubtargetFeatures API where it implicitly expects CPU name to
be the first encoded as the first feature. It then uses the CPU name to look up
features / scheduling itineray even though clients know full well the CPU name
being used to query these properties.
The fix is to just have the clients explictly pass the CPU name!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134127 91177308-0d34-0410-b5e6-96231b3b80d8
Improve implementation of __masked_store_blend_64() for AVX target by doing two 8-wide 32-bit blends rather than serializing. Fixes issue #29
Pipe through source file locations of structure element declarations; these are now supplied to the llvm::DIBuilder::createMemberType() method rather than giving it the position of the overall struct declaration for each one. Fixes issue #31
Pipe through source file locations of structure element declarations; these are now supplied to the llvm::DIBuilder::createMemberType() method rather than giving it the position of the overall struct declaration for each one. Fixes issue #31
Implement our own routine to turn C99-style hexadecimal float constants in strong form into floating-point values. With this, we can correctly handle hex float constants on Windows, where the builtin atof() routine just returns zero for them. Fixes issue #16.
Pipe through source file locations of structure element declarations; these are now supplied to the llvm::DIBuilder::createMemberType() method rather than giving it the position of the overall struct declaration for each one. Fixes issue #31
Improve implementation of __masked_store_blend_64() for AVX target by doing two 8-wide 32-bit blends rather than serializing. Fixes issue #29
============================== Intel(r) SPMD Program Compiler ============================== Welcome to the Intel(r) SPMD Program Compiler (ispc)! ispc is a new compiler for "single program, multiple data" (SPMD) programs. Under the SPMD model, the programmer writes a program that mostly appears to be a regular serial program, though the execution model is actually that a number of program instances execute in parallel on the hardware. ispc compiles a C-based SPMD programming language to run on the SIMD units of CPUs; it frequently provides a a 3x or more speedup on CPUs with 4-wide SSE units, without any of the difficulty of writing intrinsics code. ispc is an open source compiler under the BSD license; see the file LICENSE.txt. ispc supports Windows, Mac, and Linux, with both x86 and x86-64 targets. It currently supports the SSE2 and SSE4 instruction sets, though support for AVX should be available soon. For more information and examples, as well as a wiki and the bug database, see the ispc distribution site, http://ispc.github.com.
Description
Languages
C++
63.5%
LLVM
19.1%
M4
11.6%
Python
4.5%
Makefile
0.5%
Other
0.6%