Optimization pipeline was modified by introducing early LoopFullUnrollPass which matches ISPC unrolled loops with manually unrolled loops in many cases. ISPC now uses LLVM's new pass manager.added two new device names: mtl-m and mtl-p. added two new ISPC targets: xelpg-x16 and xelpg-x8.The default behavior (before version 1.21.0) can be preserved by using -wrap-signed-int, which maintains defined wraparound behavior for signed integers, though it may limit some compiler optimizations.Īdded support of Intel Meteor Lake Xe-LPG graphics: You can manage this behavior using the -wrap-signed-int compiler switch. This change may cause compatibility issues. Now, in case of signed integer overflow, ispc will assume undefined behavior similar to C and C++.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |