Search Options

Results per page
Sort
Preferred Languages
Advance

Results 61 - 70 of 206 for computations (0.17 sec)

  1. tensorflow/compiler/jit/xla_launch_util.h

    // For case 3, we need to create a PjRtBuffer from the raw device mem pointer,
    // and we need to ensure the PjRtBuffer persists till XLA computation is
    // complete. Therefore we put the newly created PjRtBuffer into `owned_args`.
    // Caller is responsible to ensure `owned_args` lives till the end of XLA
    // computation.
    Status PreparePjRtExecutableArguments(
        int num_missing_prefix_ctx_inputs, const std::vector<int>& input_mapping,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Feb 21 09:53:30 UTC 2024
    - 11.8K bytes
    - Viewed (0)
  2. tensorflow/compiler/jit/extract_outside_compilation_pass_test.cc

      }
    
     private:
      std::unique_ptr<DeviceMgr> device_mgr_;
      std::unique_ptr<ProcessFunctionLibraryRuntime> pflr_;
    };
    
    TEST_F(ExtractOutsideCompilationForFunctionTest, Basic) {
      // Build the XLA computation func.
      // "const0"
      // "identity0" = "const0" (outside compilation cluster "0")
      // "identity1" = "identity0" (outside compilation cluster "1")
      // "identity2" = "identity1"
      FunctionDefLibrary fdl;
      {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Sep 06 19:12:29 UTC 2023
    - 41K bytes
    - Viewed (0)
  3. tensorflow/compiler/jit/xla_compile_on_demand_op.cc

    XlaCompiler::CompileOptions GetCompileOptions(bool for_pjrt = false) {
      XlaCompiler::CompileOptions compile_options;
      compile_options.is_entry_computation = true;
      // Optimization: where possible, have the computation return a naked array
      // rather than a one-element tuple.
      compile_options.always_return_tuple = false;
      if (for_pjrt) {
        compile_options.use_tuple_arg = false;
        compile_options.always_return_tuple = true;
      }
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Feb 29 08:39:39 UTC 2024
    - 13.4K bytes
    - Viewed (0)
  4. tensorflow/compiler/mlir/lite/quantization/ir/QuantOps.td

    //
    // Like qcasts, a dcast is allowed to have both its operand and result
    // as non quantized types. This facilitates transformations and marks edges
    // where the computation must be carried out in the expressed type.
    //
    // Especially early in transformation, it is common to have dcasts on
    // all operands to ops that must operate with the expressed type (typically
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Oct 13 12:46:08 UTC 2022
    - 10.2K bytes
    - Viewed (0)
  5. src/strconv/ftoaryu.go

    	// Now compute mant*(2^e2)*(10^q).
    	// Is it an exact computation?
    	// Only small positive powers of 10 are exact (5^28 has 66 bits).
    	exact := q <= 27 && q >= 0
    
    	di, dexp2, d0 := mult64bitPow10(mant, e2, q)
    	if dexp2 >= 0 {
    		panic("not enough significant bits after mult64bitPow10")
    	}
    	// As a special case, computation might still be exact, if exponent
    Registered: Wed Jun 12 16:32:35 UTC 2024
    - Last Modified: Fri Sep 09 00:28:56 UTC 2022
    - 15.7K bytes
    - Viewed (0)
  6. src/cmd/internal/obj/riscv/cpu.go

    //
    // If you modify this table, you MUST run 'go generate' to regenerate anames.go!
    const (
    	// Unprivileged ISA (Document Version 20190608-Base-Ratified)
    
    	// 2.4: Integer Computational Instructions
    	AADDI = obj.ABaseRISCV + obj.A_ARCHSPECIFIC + iota
    	ASLTI
    	ASLTIU
    	AANDI
    	AORI
    	AXORI
    	ASLLI
    	ASRLI
    	ASRAI
    	ALUI
    	AAUIPC
    	AADD
    	ASLT
    	ASLTU
    	AAND
    Registered: Wed Jun 12 16:32:35 UTC 2024
    - Last Modified: Wed Mar 20 14:19:33 UTC 2024
    - 13.1K bytes
    - Viewed (0)
  7. tensorflow/compiler/mlir/quantization/common/ir/QuantOps.td

    //
    // Like qcasts, a dcast is allowed to have both its operand and result
    // as non quantized types. This facilitates transformations and marks edges
    // where the computation must be carried out in the expressed type.
    //
    // Especially early in transformation, it is common to have dcasts on
    // all operands to ops that must operate with the expressed type (typically
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Jan 09 03:10:59 UTC 2024
    - 10.2K bytes
    - Viewed (0)
  8. tensorflow/compiler/jit/encapsulate_util.cc

          }
        } else if (src_outside_compilation && !dst_outside_compilation) {
          // Case 1b: outside compilation to its XLA computation control edge.
          ReplaceAttr(e->src(), kXlaConnectedToXlaComputationAttrName, true);
        } else if (!src_outside_compilation && dst_outside_compilation) {
          // Case 1b: XLA computation to outside compilation in it control edge.
          ReplaceAttr(e->dst(), kXlaConnectedFromXlaComputationAttrName, true);
        }
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Mar 12 06:33:33 UTC 2024
    - 15.5K bytes
    - Viewed (0)
  9. tensorflow/c/eager/parallel_device/parallel_device_lib.h

      // A non-blocking version of `Execute`. After each call, `Join` must be called
      // before `StartExecute` is called again. Using `StartExecute` with `Join`
      // allows the caller to schedule computation on multiple ParallelDevices
      // without sequencing those operations (first call `StartExecute` on each
      // parallel device, then call `Join` on each; even if some of the `Join`s
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Apr 25 15:21:13 UTC 2023
    - 12.9K bytes
    - Viewed (0)
  10. guava/src/com/google/common/math/Quantiles.java

    public final class Quantiles {
    
      /** Specifies the computation of a median (i.e. the 1st 2-quantile). */
      public static ScaleAndIndex median() {
        return scale(2).index(1);
      }
    
      /** Specifies the computation of quartiles (i.e. 4-quantiles). */
      public static Scale quartiles() {
        return scale(4);
      }
    
      /** Specifies the computation of percentiles (i.e. 100-quantiles). */
    Registered: Wed Jun 12 16:38:11 UTC 2024
    - Last Modified: Fri May 12 17:02:53 UTC 2023
    - 29.9K bytes
    - Viewed (0)
Back to top