Searched defs:threads_per_block (Results 1 – 11 of 11) sorted by relevance
| /external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| D | launch_dimensions.cc | 38 int64 threads_per_block = gpu_device_info.threads_per_block_limit; in ThreadsPerBlockLimit() local
79 int64 threads_per_block = ThreadsPerBlockLimit(gpu_device_info); in CalculateLaunchDimensions() local
|
| D | elemental_ir_emitter.cc | 313 llvm::Value* threads_per_block = IntCast( in EmitThreadId() local
|
| D | ir_emitter_unnested.cc | 4321 int threads_per_block) { in EmitFullWarpShuffleDownLoopForAllReduces()
4332 llvm::Value* partial_result_address, int threads_per_block) { in EmitFullWarpShuffleDownLoopForReduce()
4669 llvm::Value* IrEmitterUnnested::EmitThreadId(int64 threads_per_block, in EmitThreadId()
4681 int64 threads_per_block, llvm::Type* index_ty, int64 num_threads_x) { in EmitThreadIdInfo()
|
| /external/tensorflow/tensorflow/core/kernels/image/ |
| D | adjust_hue_op_gpu.cu.cc | 35 const int threads_per_block = config.thread_per_block; in operator ()() local
|
| D | adjust_saturation_op_gpu.cu.cc | 36 const int threads_per_block = config.thread_per_block; in operator ()() local
|
| /external/tensorflow/tensorflow/stream_executor/ |
| D | device_description.cc | 155 int64 element_count, int64 *threads_per_block, in CalculateDimensionality()
|
| /external/tensorflow/tensorflow/stream_executor/gpu/ |
| D | redzone_allocator.cc | 223 int64 threads_per_block = std::min( in RunRedzoneChecker() local
|
| /external/mesa3d/src/gallium/drivers/radeonsi/ |
| D | si_get.c | 731 unsigned threads_per_block = get_max_threads_per_block(sscreen, ir_type); in si_get_compute_param() local
|
| /external/mesa3d/src/gallium/drivers/r600/ |
| D | r600_pipe_common.c | 958 unsigned threads_per_block = get_max_threads_per_block(rscreen, ir_type); in r600_get_compute_param() local
|
| /external/tensorflow/tensorflow/stream_executor/rocm/ |
| D | rocm_driver.cc | 1308 GpuContext* context, hipFunction_t kernel, int threads_per_block, in GetMaxOccupiedBlocksPerCore()
|
| /external/tensorflow/tensorflow/stream_executor/cuda/ |
| D | cuda_driver.cc | 1624 GpuContext* context, CUfunction kernel, int threads_per_block, in GetMaxOccupiedBlocksPerCore()
|