Abstract: Described herein is a graphics processing unit (GPU) configured to receive an instruction having multiple operands, where the instruction is a single instruction multiple data (SIMD) instruction configured to use a bfloat16 (BF16) number format and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent. The GPU can process the instruction using the multiple operands, where to process the instruction includes to perform a multiply operation, perform an addition to a result of the multiply operation, and apply a rectified linear unit function to a result of the addition.

Abstract: Low-latency synchronization utilizing local team barriers for thread team processing is described. An example of an apparatus includes one or more processors including a graphics processor, the graphics processor including a plurality of processing resources; and memory for storage of data including data for graphics processing, wherein the graphics processor is to receive a request for establishment of a local team barrier for a thread team, the thread team being allocated to a first processing resource, the thread team including multiple threads; determine requirements and designated threads for the local team barrier; and establish the local team barrier in a local register of the first processing resource based at least in part on the requirements and designated threads for the local barrier.

Abstract: Shared local registers for thread team processing is described. An example of an apparatus includes one or more processors including a graphic processor having multiple processing resources; and memory for storage of data, the graphics processor to allocate a first thread team to a first processing resource, the first thread team including hardware threads to be executed solely by the first processing resource; allocate a shared local register (SLR) space that may be directly reference in the ISA instructions to the first processing resource, the SLR space being accessible to the threads of the thread team and being inaccessible to threads outside of the thread team; and allocate individual register spaces to the thread team, each of the individual register spaces being accessible to a respective thread of the thread team.

Abstract: Embodiments described herein provide a technique enable a broadcast load from an L1 cache or shared local memory to register files associated with hardware threads of a graphics core. One embodiment provides a graphics processor comprising a cache memory and a graphics core coupled with the cache memory. The graphics core includes a plurality of hardware threads and memory access circuitry to facilitate access to memory by the plurality of hardware threads. The graphics core is configurable to process a plurality of load request from the plurality of hardware threads, detect duplicate load requests within the plurality of load requests, perform a single read from the cache memory in response to the duplicate load requests, and transmit data associated with the duplicate load requests to requesting hardware threads.

Abstract: An apparatus to facilitate supporting vector multiply add with double accumulator access in a graphics environment is disclosed. The apparatus includes a processor comprising processing resources, the processing resources comprising multiplier circuitry to: receive operands for a matrix multiplication operation, wherein the operands comprising two source matrices to be multiplied as part of the matrix multiplication operation; and issue a multiply and add vector (MADV) instruction for the multiplication operation utilizing a double accumulator access output, wherein the MADV instruction to multiply two vectors of the two source matrices in a single floating point (FP) pipeline of the processor.

Abstract: Examples described herein relate to a software and hardware optimization that manages scenarios where a write operation to a register is less than an entirety of the register. A compiler detects instructions that make partial writes to the same register, groups such instructions, and provides hints to hardware of the partial write. The execution unit combines the output data for grouped instructions and updates the destination register as single write instead of multiple separate partial writes.

Abstract: An apparatus to facilitate computing efficient cross channel operations in parallel computing machines using systolic arrays is disclosed. The apparatus includes a plurality of registers and one or more processing elements communicably coupled to the plurality of registers. The one or more processing elements include a systolic array circuit to perform cross-channel operations on source data received from a single source register of the plurality of registers, wherein the systolic array circuit is modified to: receive inputs from the single source register at different stages of the systolic array circuit; perform cross-channel operations at channels of the systolic array circuit; bypass disabled channels of the systolic array circuit, the disabled channels not used to compute the cross-channel operations; and broadcast a final result of a final stage of the systolic array circuit to all channels of a destination register.

Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch a single instruction for execution, a decode unit to decode the single instruction into a decoded instruction, wherein the decoded instruction is to cause the graphics processing unit to perform a set of parallel dot product operations on elements of input matrices, and a systolic dot product unit to execute the decoded instruction across one or more parallel processor lanes using multiple systolic layers associated with multiple pipeline stages. The multiple pipeline stages include one or more sets of interconnected multipliers and adders to compute multiple concurrent dot products.

Abstract: Described herein is a graphics processor including a plurality of processing clusters coupled with a host interface, each processing cluster comprising a plurality of multiprocessors, the plurality of multiprocessors interconnected via a data interconnect, and each multiprocessor comprising sparse matrix multiply acceleration hardware including a systolic processing array with feedback inputs.

Abstract: Described herein is a graphics processing unit (GPU) comprising a first processing cluster to perform parallel processing operations, the parallel processing operations including a ray tracing operation and a matrix multiply operation; and a second processing cluster coupled to the first processing cluster, wherein the first processing cluster includes a floating-point unit to perform floating point operations, the floating-point unit is configured to process an instruction using a bfloat16 (BF16) format with a multiplier to multiply second and third source operands while an accumulator adds a first source operand with output from the multiplier.

Abstract: Described herein is a graphics processing unit (GPU) configured to receive an instruction having multiple operands, where the instruction is a single instruction multiple data (SIMD) instruction configured to use a bfloat16 (BF16) number format and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent. The GPU can process the instruction using the multiple operands, where to process the instruction includes to perform a multiply operation, perform an addition to a result of the multiply operation, and apply a rectified linear unit function to a result of the addition.

Abstract: An apparatus to facilitate computing efficient cross channel operations in parallel computing machines using systolic arrays is disclosed. The apparatus includes a plurality of registers and one or more processing elements communicably coupled to the plurality of registers. The one or more processing elements include a systolic array circuit to perform cross-channel operations on source data received from a single source register of the plurality of registers, wherein the systolic array circuit is modified to: receive inputs from the single source register at different stages of the systolic array circuit; perform cross-channel operations at channels of the systolic array circuit; bypass disabled channels of the systolic array circuit, the disabled channels not used to compute the cross-channel operations; and broadcast a final result of a final stage of the systolic array circuit to all channels of a destination register.

Abstract: Embodiments described herein provide for an instruction and associated logic to enable a vector multiply add instructions with automatic zero skipping for sparse input. One embodiment provides for a general-purpose graphics processor comprising logic to perform operations comprising fetching a hardware macro instruction having a predicate mask, a repeat count, and a set of initial operands, where the initial operands include a destination operand and multiple source operands. The hardware macro instruction is configured to perform one or more multiply/add operations on input data associated with a set of matrices.

Abstract: An apparatus to facilitate facilitating forward progress guarantee using single-level synchronization at individual thread granularity is disclosed. The apparatus includes a processor comprising a barrier synchronization hardware circuitry to assign a set of global named barrier identifiers (IDs) to individual execution threads of a plurality of execution threads and synchronize execution of the individual execution threads on a single level via the set of global named barrier IDs; and a plurality of processing resources to execute the plurality of execution threads and comprising divergent barrier scheduling hardware circuitry to facilitate execution flow switching from a first divergent branch executed by a first thread to a second divergent branch executed by a second thread, the execution flow switching performed responsive to the first thread stalling to wait on a named barrier of the set of global named barrier IDs.

Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch an instruction for execution and a decode unit to decode the instruction into a decoded instruction. The decoded instruction is a matrix instruction to cause the graphics processing unit to perform a parallel dot product operation. The GPGPU also includes systolic dot product circuitry to execute the decoded instruction across one or more SIMD lanes using multiple systolic layers, wherein to execute the decoded instruction, a dot product computed at a first systolic layer is to be output to a second systolic layer, wherein each systolic layer includes one or more sets of interconnected multipliers and adders, each set of multipliers and adders to generate a dot product.

Abstract: Described herein is an accelerator device including a host interface, a fabric interconnect coupled with the host interface, and one or more hardware tiles coupled with the fabric interconnect, the one or more hardware tiles including sparse matrix multiply acceleration hardware including a systolic array with feedback inputs.

Abstract: An apparatus to facilitate gathering payload from arbitrary registers for send messages in a graphics environment is disclosed. The apparatus includes processing resources comprising execution circuitry to receive a send gather message instruction identifying a number of registers to access for a send message and identifying IDs of a plurality of individual registers corresponding to the number of registers; decode a first phase of the send gather message instruction; based on decoding the first phase, cause a second phase of the send gather message instruction to bypass an instruction decode stage; and dispatch the first phase subsequently followed by dispatch of the second phase to a send pipeline. The apparatus can also perform an immediate move of the IDs of the plurality of individual registers to an architectural register of the execution circuitry and include a pointer to the architectural register in the send gather message instruction.

Abstract: Embodiments described herein are generally directed to an improved vector normalization instruction. An embodiment of a method includes responsive to receipt by a GPU of a single instruction specifying a vector normalization operation to be performed on V vectors: (i) generating V squared length values, N at a time, by a first processing unit, by, for each N sets of inputs, each representing multiple component vectors for N of the vectors, performing N parallel dot product operations on the N sets of inputs. Generating V sets of outputs representing multiple normalized component vectors of the V vectors, N at a time, by a second processing unit, by, for each N squared length values of the V squared length values, performing N parallel operations on the N squared length values, wherein each of the N parallel operations implement a combination of a reciprocal square root function and a vector scaling function.

Abstract: An apparatus is disclosed. The apparatus includes one or more processors comprising register sharing circuitry to receive meta-information indicating a number of threads that are to be disabled and provide an indication that an associated thread is disabled, a plurality of General Purpose Register Files (GRFs), wherein one or more of the plurality of GRFs is associated with one of the plurality of threads and a plurality of multiplexers coupled to the one or more GRFs to receive the indication from the register sharing circuitry and disable thread access to an associated GRF based on an indication that a thread is to be disabled.

Abstract: An apparatus to facilitate 64-bit two-dimensional (2D) block load with transpose is disclosed. The apparatus includes a processor comprising processing resources; and load store pipeline hardware circuitry coupled to the processing resources, the load store pipeline hardware circuitry to receive a 64-bit two-dimensional (2D) block load message with transpose from the processing resources. The load store pipeline hardware circuitry comprising a load store pipeline sequencer to map rows of a block of memory corresponding to the 64-bit 2D block load message with transpose to 64-bit standard load messages; and load store pipeline return circuitry to: sequentially number general register files (GRFs) used for returning elements of the block of memory accessed by the 64-bit standard load messages to the processing resources; and return, to the processing resources, the sequentially numbered GRFs in response to the 64-bit 2D block load message with transpose.