search for: isl_id

...you would probably expect is that the union of the two sets [p] -> {[i] = p} and [p] -> {[i] = p} is a single set [p] -> {[i] = p} as the two parameters have the very same name. However, this is not always true. Even though parameters share the same name, they may in fact be different isl_id objects. isl_id_alloc() takes a parameter name and a pointer and only if both of them are identical, the very same isl_id object is returned. Sven: In terms of making the behaviour of isl easier to understand, it may make sense to fail/assert in case operands have parameters that are named ident...

Hi, thanks to Tobias for doing most of the work to get the vector code generation working with ISL's code generation. Attached are two patches to port the vector code generation part of the testsuite from Cloog/CodeGen to Isl/CodeGen. Tobi, do you want to commit these two patches separately, or you want me to combine them, as the second patch is needed to make the testsuite pass? Also, let

Hi Sebastian, Recently, I found the "Polly - Calculate dependences" pass would lead to significant compile-time overhead when compiling some loop-intensive source code. Tobias told me you found similar problem as follows: http://llvm.org/bugs/show_bug.cgi?id=14240 My evaluation shows that "Polly - Calculate dependences" pass consumes 96.4% of total compile-time overhead

Dear community, the next step of the "Improvement of vectorization process in Polly" project is to implement the packing transformation described in http://www.cs.utexas.edu/users/flame/pubs/TOMS-BLIS-Analytical.pdf. I had a discussion with Tobias and we decided that a packing transformation is in many ways a data-layout transformation that will require to introduce a new array, copy