| /netbsd-src/external/apache2/llvm/dist/llvm/lib/Target/X86/ |
| H A D | README-FPStack.txt | 12 This should use fiadd on chips where it is profitable:
16 complexity. We need a way to specify the later is more profitable.
|
| H A D | README.txt | 247 estimate to determine whether the match is profitable.
|
| /netbsd-src/external/apache2/llvm/dist/llvm/docs/Frontend/ |
| H A D | PerformanceTips.rst | 85 be profitable to use a zext rather than a sext.
156 condition is not taken.) It can be profitable, in some cases, to emit such
166 improvement. Note that this is not always profitable and does involve a
180 profitable for code generation purposes, the optimizer will likely form the
182 profitable to emit these directly in the language frontend. This item
240 intrinsics where possible. Common profitable uses are for stack like data
|
| /netbsd-src/external/apache2/llvm/dist/llvm/docs/ |
| H A D | FaultMaps.rst | 14 is profitable to make the non-failing case cheaper even if it makes
117 be profitable to convert it to an implicit null check:
|
| H A D | Vectorizers.rst | 283 vectorization is profitable.
370 The Loop Vectorizer uses a cost model to decide when it is profitable to unroll loops.
|
| H A D | TransformMetadata.rst | 21 optimizer not applying transformations that would be highly profitable.
|
| H A D | CompileCudaWithLLVM.rst | 115 * ``fast``: fuse multiplies and adds wherever profitable, even across
|
| H A D | Passes.rst | 582 where it is profitable, the loop could be transformed to count down to zero
|
| H A D | SpeculativeLoadHardening.md | 831 is unlikely to be profitable in practice. The latency hit of the hardening
|
| /netbsd-src/external/gpl3/gcc/dist/gcc/config/h8300/ |
| H A D | testcompare.md | 166 ;; The only generally useful/profitable case is when we want to test the
171 ;; profitable.
|
| /netbsd-src/external/apache2/llvm/dist/llvm/lib/Target/ARM/ |
| H A D | ARM.td | 208 // Whether it is profitable to unpredicate certain instructions during if-conversion
211 "Is profitable to unpredicate">;
265 // Whether or not it is profitable to expand VFP/NEON MLA/MLS instructions.
|
| H A D | README.txt | 560 It might be profitable to cse MOVi16 if there are lots of 32-bit immediates
|
| /netbsd-src/external/gpl3/gcc/dist/gcc/ |
| H A D | tree-vect-slp.cc | 5480 bool profitable = true; in vect_bb_vectorization_profitable_p() local
5546 profitable = false; in vect_bb_vectorization_profitable_p()
5550 if (profitable && vi < li_vector_costs.length ()) in vect_bb_vectorization_profitable_p()
5556 profitable = false; in vect_bb_vectorization_profitable_p()
5561 if (!orig_loop || !profitable) in vect_bb_vectorization_profitable_p()
5568 return profitable; in vect_bb_vectorization_profitable_p()
|
| H A D | params.opt | 222 …lied to inline-insns-single and auto limits when heuristics hints that inlining is very profitable.
418 The minimum stride ratio for loop interchange to be profitable.
1149 Minimum percentage of memrefs that must go away for unroll-and-jam to be considered profitable.
|
| /netbsd-src/external/gpl3/gcc.old/dist/gcc/ |
| H A D | params.opt | 179 …lied to inline-insns-single and auto limits when heuristics hints that inlining is very profitable.
331 The minimum stride ratio for loop interchange to be profitable.
941 Minimum percentage of memrefs that must go away for unroll-and-jam to be considered profitable.
|
| /netbsd-src/external/gpl3/gcc.old/dist/gcc/config/pa/ |
| H A D | predicates.md | 171 profitable to do so when the frame pointer is being eliminated. */
|
| /netbsd-src/external/gpl3/gcc/dist/gcc/config/pa/ |
| H A D | predicates.md | 171 profitable to do so when the frame pointer is being eliminated. */
|
| /netbsd-src/external/gpl3/gcc.old/dist/gcc/fortran/ |
| H A D | lang.opt | 598 Try to interchange loops if profitable.
|
| H A D | invoke.texi | 1812 limit (see @option{-fblas-matmul-limit}). This may be profitable if an
1966 profitable. Enabled by default by any @option{-O} option.
|
| /netbsd-src/external/apache2/llvm/dist/clang/docs/analyzer/developer-docs/ |
| H A D | IPA.rst | 206 We do not inline functions which were not profitable to inline in a different
|
| /netbsd-src/external/gpl3/gcc/dist/gcc/fortran/ |
| H A D | lang.opt | 615 Try to interchange loops if profitable.
|
| H A D | invoke.texi | 1878 limit (see @option{-fblas-matmul-limit}). This may be profitable if an
2032 profitable. Enabled by default by any @option{-O} option.
|
| /netbsd-src/external/apache2/llvm/dist/llvm/lib/Target/ |
| H A D | README.txt | 466 profitable. For example, we compile this C++ example:
1156 It is very profitable for this benchmark to turn the conditional stores to mc[k]
|
| /netbsd-src/external/gpl3/gcc/dist/gcc/config/arm/ |
| H A D | thumb1.md | 1986 ;; unlikely to be profitable.
|
| /netbsd-src/external/gpl3/gcc.old/dist/gcc/config/arm/ |
| H A D | thumb1.md | 2022 ;; unlikely to be profitable.
|