| /llvm-project-15.0.7/llvm/include/llvm/Support/ |
| H A D | Compiler.h | 130 #define LLVM_PREFETCH(addr, rw, locality) __builtin_prefetch(addr, rw, locality) argument 132 #define LLVM_PREFETCH(addr, rw, locality) argument
|
| /llvm-project-15.0.7/mlir/test/Dialect/Affine/ |
| H A D | load-store.mlir | 190 affine.prefetch %0[%i0 + 3, %i1 + 11], write, locality<0>, data : memref<100x100xf32> 191 …// CHECK: affine.prefetch %{{.*}}[%{{.*}} + 3, %{{.*}} + 11], write, locality<0>, data : memref<10… 192 affine.prefetch %0[%i0, %i1 + 1], read, locality<3>, instr : memref<100x100xf32> 193 …// CHECK: affine.prefetch %{{.*}}[%{{.*}}, %{{.*}} + 1], read, locality<3>, instr : memref<100x100…
|
| H A D | load-store-invalid.mlir | 93 affine.prefetch %0[%i], rw, locality<0>, data : memref<10xf32> 102 affine.prefetch %0[%i], read, locality<0>, false : memref<10xf32>
|
| /llvm-project-15.0.7/polly/ |
| H A D | README | 11 cache locality, optimize arrays, apply advanced automatic parallelization, drive
|
| /llvm-project-15.0.7/mlir/test/IR/ |
| H A D | core-ops.mlir | 186 // CHECK: memref.prefetch %arg0[%arg1, %arg1], write, locality<1>, data : memref<4x4xi32> 187 memref.prefetch %0[%1, %1], write, locality<1>, data : memref<4x4xi32> 189 // CHECK: memref.prefetch %arg0[%arg1, %arg1], read, locality<3>, instr : memref<4x4xi32> 190 memref.prefetch %0[%1, %1], read, locality<3>, instr : memref<4x4xi32>
|
| /llvm-project-15.0.7/mlir/include/mlir/Dialect/Affine/IR/ |
| H A D | AffineOps.td | 766 a read/write specifier, a locality hint, and a cache type specifier as shown 770 affine.prefetch %0[%i, %j + 5], read, locality<3>, data : memref<400x400xi32> 773 The read/write specifier is either 'read' or 'write', the locality hint 774 specifier ranges from locality<0> (no locality) to locality<3> (extremely
|
| /llvm-project-15.0.7/llvm/test/CodeGen/X86/ |
| H A D | code_placement_ext_tsp.ll | 153 ; A larger test where it is beneficial for locality to break the loop
|
| /llvm-project-15.0.7/flang/docs/ |
| H A D | f2018-grammar.md | 481 [,] CONCURRENT concurrent-header concurrent-locality 489 R1129 concurrent-locality -> [locality-spec]... 490 R1130 locality-spec ->
|
| /llvm-project-15.0.7/mlir/include/mlir/Dialect/MemRef/IR/ |
| H A D | MemRefOps.td | 952 read/write specifier, a locality hint, and a cache type specifier as shown 956 memref.prefetch %0[%i, %j], read, locality<3>, data : memref<400x400xi32> 959 The read/write specifier is either 'read' or 'write', the locality hint 960 ranges from locality<0> (no locality) to locality<3> (extremely local keep
|
| /llvm-project-15.0.7/mlir/test/Dialect/MemRef/ |
| H A D | invalid.mlir | 778 memref.prefetch %0[%i], rw, locality<0>, data : memref<10xf32> 787 memref.prefetch %0[%i], read, locality<0>, false : memref<10xf32> 796 memref.prefetch %0[%i], read, locality<5>, data : memref<10xf32>
|
| /llvm-project-15.0.7/mlir/test/Conversion/MemRefToLLVM/ |
| H A D | convert-dynamic-memref-ops.mlir | 216 memref.prefetch %A[%i, %j], write, locality<3>, data : memref<?x?xf32> 221 memref.prefetch %A[%i, %j], read, locality<0>, data : memref<?x?xf32> 226 memref.prefetch %A[%i, %j], read, locality<2>, instr : memref<?x?xf32>
|
| /llvm-project-15.0.7/clang/docs/ |
| H A D | SafeStack.rst | 37 stack increases the locality of frequently accessed values on the stack, such
|
| H A D | ShadowCallStack.rst | 32 To optimize for memory consumption and cache locality, the shadow call
|
| H A D | LanguageExtensions.rst | 2796 void __builtin_prefetch(const void *addr, int rw=0, int locality=3) 2806 The ``__builtin_prefetch(addr, rw, locality)`` builtin is expected to be used to 2810 for *write*. In case of *read write* access, ``1`` is to be used. ``locality``
|
| /llvm-project-15.0.7/polly/docs/ |
| H A D | UsingPollyWithClang.rst | 186 for data-locality and parallelism using the Pluto algorithm.
|
| /llvm-project-15.0.7/mlir/include/mlir/Dialect/Affine/ |
| H A D | Passes.td | 57 transformation leads to enhanced locality and lower memory footprint through
|
| /llvm-project-15.0.7/mlir/test/Conversion/AffineToStandard/ |
| H A D | lower-affine.mlir | 603 affine.prefetch %0[%i0 + symbol(%arg0) + 7], read, locality<3>, data : memref<10xf32> 608 // CHECK-NEXT: memref.prefetch %[[v0:.*]][%[[b]]], read, locality<3>, data : memref<10xf32>
|
| /llvm-project-15.0.7/llvm/docs/ |
| H A D | GarbageCollection.rst | 112 locality and performance benefits of using aggressive garbage collection 759 highly efficient "bump pointer" allocation and can improve locality of
|
| H A D | NewPassManager.rst | 140 This is better for cache locality around LLVM data structures. This similarly
|
| H A D | CodingStandards.rst | 1069 locality. 1536 indentation of their body, and they reduce locality of reference: if you see a
|
| H A D | LangRef.rst | 1695 placed into special subsection of the text section to improving locality. 13093 declare void @llvm.prefetch(ptr <address>, i32 <rw>, i32 <locality>, i32 <cache type>) 13108 ``locality`` is a temporal locality specifier ranging from (0) - no 13109 locality, to (3) - extremely local keep in cache. The ``cache type`` 13111 instruction (0) cache. The ``rw``, ``locality`` and ``cache type``
|
| H A D | ProgrammersManual.rst | 1977 contiguous in memory (good for cache locality), has few allocations, is easy to
|
| /llvm-project-15.0.7/mlir/test/Transforms/ |
| H A D | loop-fusion.mlir | 830 // loop nest, which improves locality and enables subsequence passes to
|
| /llvm-project-15.0.7/lldb/docs/use/ |
| H A D | python-reference.rst | 227 used to optimize function placement within a binary for execution locality.
|