A method for optimizing a deep learning operator, includes: calling a method of reading an image object to read target data from an L1 cache of an image processor to the processor in response to detecting the target data in the L1 cache, performing a secondary quantization operation on the target data in the processor to obtain an operation result and writing the operation result into a main memory of the image processor. The target data is fixed-point data obtained after performing a quantization operation on data to be quantized in advance and the data to be quantized is one of the following: float-point data of an initial network layer of the neural network model and fixed-point data outputted from a network layer previous to the current network layer.

Embodiments are generally directed to cache structure and utilization. An embodiment of an apparatus includes one or more processors including a graphics processor; a memory for storage of data for processing by the one or more processors; and a cache to cache data from the memory; wherein the apparatus is to provide for dynamic overfetching of cache lines for the cache, including receiving a read request and accessing the cache for the requested data, and upon a miss in the cache, overfetching data from memory or a higher level cache in addition to fetching the requested data, wherein the overfetching of data is based at least in part on a current overfetch boundary, and provides for data is to be prefetched extending to the current overfetch boundary.

Graphics processors of the present design provide hierarchical open sectors and variable cache sizes for cache operations. In one embodiment, a graphics processor comprises a cache memory having a hierarchical open sector design including a first hierarchy of upper and lower regions with each region including a second hierarchy of sectors. A cache controller is configured to initially open a first sector of the lower region, to receive a memory request that does not match an address in the first sector, and to open a second sector of the lower region.

Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache coupled to the processing resources. The cache controller is configured to control cache priority by determining whether default settings or an instruction will control cache operations for the cache.

Embodiments are generally directed to graphics processor data access and sharing. An embodiment of an apparatus includes a circuit element to produce a result in processing of an application; a load-store unit to receive the result and generate pre-fetch information for a cache utilizing the result; and a prefetch generator to produce prefetch addresses based at least in part on the pre-fetch information; wherein the load-store unit is to receive software assistance for prefetching, and wherein generation of the pre-fetch information is based at least in part on the software assistance.

Methods and apparatus relating to memory controller techniques. In an example, an apparatus comprises a cache memory, a high-bandwidth memory, and a processor communicatively coupled to the cache memory and the high-bandwidth memory, the processor to manage data transfer between the cache memory and the high-bandwidth memory for memory access operations directed to the high-bandwidth memory. Other embodiments are also disclosed and claimed.

Embodiments are generally directed to cache structure and utilization. An embodiment of an apparatus includes one or more processors including a graphics processor; a memory for storage of data for processing by the one or more processors; and a cache to cache data from the memory; wherein the apparatus is to provide for dynamic overfetching of cache lines for the cache, including receiving a read request and accessing the cache for the requested data, and upon a miss in the cache, overfetching data from memory or a higher level cache in addition to fetching the requested data, wherein the overfetching of data is based at least in part on a current overfetch boundary, and provides for data is to be prefetched extending to the current overfetch boundary.

Embodiments are generally directed to compute optimization in graphics processing. An embodiment of an apparatus includes one or more processors including a multi-tile graphics processing unit (GPU) to process data, the multi-tile GPU including multiple processor tiles; and a memory for storage of data for processing, wherein the apparatus is to receive compute work for processing by the GPU, partition the compute work into multiple work units, assign each of multiple work units to one of the processor tiles, and process the compute work using the processor tiles assigned to the work units.

Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received. In one embodiment, the cache memory configured to be partitioned into multiple cache regions, wherein the multiple cache regions include a first cache region having a cache eviction policy with a configurable level of data persistence.

Described herein is a graphics processing unit (GPU) comprising a single instruction, multiple thread (SIMT) multiprocessor comprising an instruction cache, a shared memory coupled with the instruction cache, and circuitry coupled with the shared memory and the instruction cache, the circuitry including multiple texture units, a first core including hardware to accelerate matrix operations, and a second core configured to receive an instruction having multiple operands in a bfloat16 (BF16) number format, wherein the multiple operands include a first source operand, a second source operand, and a third source operand, and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent and process the instruction, wherein to process the instruction includes to multiply the second source operand by the third source operand and add a first source operand to a result of the multiply.