| Thread Tools | Search this thread |
|---|
srimks
| November 29, 2008 9:38 AM PST Vectorization Limitations - The step towards SIMD Programming | ||||
Hi All. Since vectorization in one way to achieve parallelization of code within a section of code through Compiler's directives within SMP system. It seems auto-vectorization is not infallible as in many cases the compiler can't prove independence of statements, so code stays scalar, or even if the compiler appears to have vectorised the code - it might still under-exploit some hardware features and hence generate less efficient code than the programmer would have written using vector intrinsics. Could anyone explain what are key Compilers limitations for executing efficient vectorization code which makes a sinerio for SIMD programming to take it's importance? Any papers or publications which discusses above thoughts? ~BR | |||||
|
|||||||||||||
|
|||||||||||||
|
|||||||||||||
| 6668 users have contributed to 28284 threads and 87462 posts to date. |
|---|
| In the past 24 hours, we have 5 new thread(s) 32 new posts(s), and 37 new user(s). In the past 3 days, the most popular thread for everyone has been Fortran and Matlab The most posts were made to Larger Test Data The post with the most views is Quoting - nabeels Hello e Please welcome our newest member karolbe |