- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 581 for ireduce (0.1 sec)
-
tensorflow/compiler/mlir/lite/stablehlo/transforms/legalize_hlo_conversions/reduce.h
LogicalResult MatchReduceToArgMinMaxType2(mhlo::ReduceOp reduce_op, bool is_argmax); // Base class for converting mhlo::ReduceOp to TF/TFL ArgMax/ArgMin ops. template <typename Reduce, typename ArgReduce, typename BooleanReduce, bool is_argmax> class ConvertReduceOpToArgMinMax : public OpConversionPattern<mhlo::ReduceOp> { public: using OpConversionPattern::OpConversionPattern;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/BUILD
"tf-reduce-identity.mlir": ["no_windows"], }, test_file_exts = ["mlir"], ) # Bundle together all of the test utilities that are used by tests. filegroup( name = "test_utilities", testonly = True, data = [ ":reducer_tester", "//tensorflow/compiler/mlir:tf-opt", "//tensorflow/compiler/mlir:tf-reduce", "@llvm-project//llvm:FileCheck",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Mar 27 18:00:18 UTC 2024 - 1.6K bytes - Viewed (0) -
doc/next/6-stdlib/2-unique.md
`Make[T]` function, which produces a reference to a canonical copy of the value in the form of a `Handle[T]`. Two `Handle[T]` are equal if and only if the values used to produce the handles are equal, allowing programs to deduplicate values and reduce their memory footprint. Comparing two `Handle[T]` values is efficient, reducing down to a simple
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon May 20 18:34:13 UTC 2024 - 566 bytes - Viewed (0) -
src/runtime/mgcwork.go
// workbufAlloc is the number of bytes to allocate at a time // for new workbufs. This must be a multiple of pageSize and // should be a multiple of _WorkbufSize. // // Larger values reduce workbuf allocation overhead. Smaller // values reduce heap fragmentation. workbufAlloc = 32 << 10 ) func init() { if workbufAlloc%pageSize != 0 || workbufAlloc%_WorkbufSize != 0 { throw("bad workbufAlloc") } }
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon Mar 25 19:53:03 UTC 2024 - 12.9K bytes - Viewed (0) -
gradle.properties
# Reduce Xmx after https://github.com/gradle/gradle-private/issues/4168 is resolved org.gradle.jvmargs=-Xmx2700m -XX:MaxMetaspaceSize=768m -XX:+HeapDumpOnOutOfMemoryError -Dfile.encoding=UTF-8 org.gradle.parallel=true org.gradle.caching=true org.gradle.configuration-cache=true systemProp.gradle.publish.skip.namespace.check=true # Kotlin DSL settings org.gradle.kotlin.dsl.allWarningsAsErrors=true # Kotlin settings kotlin.incremental.useClasspathSnapshot=true
Registered: Wed Jun 12 18:38:38 UTC 2024 - Last Modified: Tue Jun 11 16:35:19 UTC 2024 - 1.4K bytes - Viewed (0) -
src/crypto/internal/bigmod/nat.go
n := uint(len(rr.limbs)) mLen := uint(m.BitLen()) logR := _W * n // We start by computing R = 2^(_W * n) mod m. We can get pretty close, to // 2^⌊log₂m⌋, by setting the highest bit we can without having to reduce. rr.limbs[n-1] = 1 << ((mLen - 1) % _W) // Then we double until we reach 2^(_W * n). for i := mLen - 1; i < logR; i++ { rr.Add(rr, m) }
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon May 13 18:57:38 UTC 2024 - 24K bytes - Viewed (0) -
platforms/documentation/docs/src/docs/userguide/core-plugins/build_init_plugin.adoc
==== Compile-time dependencies Maven automatically exposes dependencies using its implicit `compile` scope to the consumers of that project. This behavior is undesirable, and Gradle takes steps to help library authors reduce their API footprint using the `api` and `implementation` configurations of the `java-library` plugin.
Registered: Wed Jun 12 18:38:38 UTC 2024 - Last Modified: Wed May 08 20:10:43 UTC 2024 - 19.4K bytes - Viewed (0) -
doc/next/5-toolchain.md
## Compiler {#compiler} The build time overhead to building with [Profile Guided Optimization](/doc/pgo) has been reduced significantly. Previously, large builds could see 100%+ build time increase from enabling PGO. In Go 1.23, overhead should be in the single digit percentages. <!-- https://go.dev/issue/62737 , https://golang.org/cl/576681, https://golang.org/cl/577615 --> The compiler in Go 1.23 can now overlap the stack frame slots of local variables
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Tue Jun 11 17:18:10 UTC 2024 - 1.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/replace_cast_hacks_with_tf_xla_ops.cc
out_dims); } Value reduced = builder.create<TF::EinsumOp>( loc, RankedTensorType::get(output_shape, builder.getIntegerType(32)), input_arguments, builder.getStringAttr(einsum_equation)); reduced.getDefiningOp()->setAttr( kTfQuantCreatedEinsum, BoolAttr::get(reduced.getDefiningOp()->getContext(), true));
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 47.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/optimize_op_order.cc
namespace mlir { namespace TFL { namespace { #define GEN_PASS_DEF_OPTIMIZEOPORDERPASS #include "tensorflow/compiler/mlir/lite/transforms/passes.h.inc" // Dequantize ops will produce 3x larger tensors, so we want to move it after // some passthrough ops to reduce the memory consumption. struct PushDownDequantize : public OpRewritePattern<DequantizeOp> { explicit PushDownDequantize(MLIRContext* context)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.1K bytes - Viewed (0)