- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 137 for Koop (0.14 sec)
-
tensorflow/compiler/mlir/tensorflow/tests/convert_control_to_data_outputs.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 22 18:35:00 UTC 2024 - 68.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/g3doc/_includes/tf_passes.md
operations in the while loop body are dependent on which inputs, it captures inter iteration parallelism in while loop. Control dependencies on the other hand create a barrier at the end of while loop body thus blocking any parallelism across iterations. For example, the following while loop body has a `%barrier` at the end. Although there is no data/control dependency between `tf.AssignVariableOp`
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Aug 02 02:26:39 UTC 2023 - 96.4K bytes - Viewed (0) -
tensorflow/compiler/jit/mark_for_compilation_pass.cc
// ApplyWeightUpdates_1 -> Computation_B // ApplyWeightUpdates_2 -> Computation_C // Computation_A -> NoOp // Computation_B -> NoOp // Computation_C -> NoOp // "iteration++" -> NoOp // } // // In the graph above we can't cluster iteration++ with any of the
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 12:19:41 UTC 2024 - 85.3K bytes - Viewed (0) -
src/cmd/compile/internal/ppc64/ssa.go
// generates STXV instructions on // power9. The Short variation is used // if no loop is generated. // sizes >= 64 generate a loop as follows: // Set up loop counter in CTR, used by BC // XXLXOR clears VS32 // XXLXOR VS32,VS32,VS32 // MOVD len/64,REG_TMP // MOVD REG_TMP,CTR // loop: // STXV VS32,0(R20) // STXV VS32,16(R20)
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Wed May 22 19:59:38 UTC 2024 - 55.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/sparsecore/embedding_pipelining.cc
// Fourth, add all the inputs to sc_forward(). These all come from the // while loop operands or the non_tpu() call that's in the loop body. The // loop operands need to be pulled from the "i" (or "2") version of the // inputs. The inputs coming from non_tpu() are from the same loop iteration // (non_tpu_res_i). std::vector<Value> f_operands;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 92.9K bytes - Viewed (0) -
src/index/suffixarray/sais2.go
bucketMax_8_64(text, freq, bucket) numLMS := 0 lastB := int64(-1) bucket = bucket[:256] // eliminate bounds check for bucket[c1] below // The next stanza of code (until the blank line) loop backward // over text, stopping to execute a code body at each position i // such that text[i] is an L-character and text[i+1] is an S-character. // That is, i+1 is the position of the start of an LMS-substring.
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon Mar 18 23:57:18 UTC 2024 - 52.3K bytes - Viewed (0) -
tensorflow/compiler/jit/deadness_analysis_test.cc
"{#true,&,*iv0/cond:0}<loop>"); EXPECT_EQ(predicate_map[ControlOutputFor(dependent_iv0)], "{#true,&,(iv0/iv:0 & *iv0/cond:0)}<loop>"); EXPECT_EQ(predicate_map[ControlOutputFor(dependent_iv1)], "{#true,&,(iv0/iv:0 & *iv0/cond:0)}<loop>"); EXPECT_EQ(predicate_map[ControlOutputFor(add0)], "{#true,&,(iv0/iv:0 & *iv0/cond:0)}<loop>"); } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 22 06:59:07 UTC 2024 - 51.6K bytes - Viewed (0) -
tensorflow/c/c_api.h
TF_Output cond_output; // The loop body graph. The inputs are the current values of the loop // variables. The outputs are the updated values of the loop variables. TF_Graph* const body_graph; const TF_Output* const body_inputs; TF_Output* const body_outputs; // Unique null-terminated name for this while loop. This is used as a prefix // for created operations. const char* name; } TF_WhileParams;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Oct 26 21:08:15 UTC 2023 - 82.3K bytes - Viewed (0) -
src/cmd/compile/internal/ssa/prove.go
// nxt = inc + ind // goto loop // // exit_loop: // // is rewritten to: // // loop: // ind = (Phi end nxt) // if (Const [x]) < ind // then goto enter_loop // else goto exit_loop // // enter_loop: // do something without using ind nor nxt // nxt = ind - inc // goto loop // // exit_loop: //
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon Mar 04 17:30:21 UTC 2024 - 48.9K bytes - Viewed (0) -
tensorflow/compiler/jit/deadness_analysis.cc
// // `X` may contain symbolic predicates and the operations corresponding to these // symbolic predicates are either in frame `loop` or outside it. The symbols // that are inside frame `loop` are loop variant (i.e. can have different // liveness in each loop iteration) and the symbols that are outside frame // `loop` are loop invariant (i.e. have the same liveness across all // iterations). class AndRecurrencePredicate : public Predicate { public:
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 12 06:33:33 UTC 2024 - 60.4K bytes - Viewed (0)