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.

A method includes receiving, by a level two (L2) controller, a first request for a cache line in a shared cache coherence state; mapping, by the L2 controller, the first request to a second request for a cache line in an exclusive cache coherence state; and responding, by the L2 controller, to the second request.

A method includes receiving, by a level two (L2) controller, a write request for an address that is not allocated as a cache line in a L2 cache. The write request specifies write data. The method also includes generating, by the L2 controller, a read request for the address; reserving, by the L2 controller, an entry in a register file for read data returned in response to the read request; updating, by the L2 controller, a data field of the entry with the write data; updating, by the L2 controller, an enable field of the entry associated with the write data; and receiving, by the L2 controller, the read data and merging the read data into the data field of the entry.

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.

A universal floating-point Instruction Set Architecture (ISA) compute engine implemented entirely in hardware. The ISA compute engine computes directly with human-readable decimal character sequence floating-point representation operands without first having to explicitly perform a conversion-to-binary-format process in software. A fully pipelined convertToBinaryFromDecimalCharacter hardware operator logic circuit converts one or more human-readable decimal character sequence floating-point representations to IEEE 754-2008 binary floating-point representations every clock cycle. Following computations by at least one hardware floating-point operator, a convertToDecimalCharacterFromBinary hardware conversion circuit converts the result back to a human-readable decimal character sequence floating-point representation.

Embodiments are generally directed to a multi-tile architecture for graphics operations. An embodiment of an apparatus includes a multi-tile architecture for graphics operations including a multi-tile graphics processor, the multi-tile processor includes one or more dies; multiple processor tiles installed on the one or more dies; and a structure to interconnect the processor tiles on the one or more dies, wherein the structure to enable communications between processor tiles the processor tiles.