Advanced Micro Devices Corporation

Lsi Logic Corporation

Samsung Electronics Co., Ltd.

Fataneh Ghodrat

Skyler Jonathon Saleh

David A Thomas

Jeffrey Christopher Allan

Tien E Wei

Christopher Jude Brennan

Judy M Gehman

Sagar Shankar Bhandare

Zhenhong Liu

Paul Raymond Vella

Daniel Schneider

Michael R Stein

Stephen W Somogyi

Leslie Abraham

Michael Lee Grossfeld

Kevin Warren Furrow

A technique for performing ray tracing operations is provided. The technique includes traversing through a bounding volume hierarchy to an instance node; performing an instance node transform using common circuitry; traversing to a leaf node of the bounding volume hierarchy; and performing an intersection test for the leaf node using the common circuitry.

Common circuitry for triangle intersection and instance transformation for ray tracing

Techniques for performing multi-sample anti-aliasing operations are provided. The techniques include detecting an instruction for a multi-sample anti-aliasing load operation; determining a sampling rate of source data for the load operation, data storage format of the source data, and loading mode indicating whether the load operation requests same or different color components, or depth data; and based on the determined sampling rate, data storage format, and loading mode, load data from a multi-sample source into a register.

Load instruction for multi sample anti-aliasing

A system includes a memory implementing one or more virtual queues and a processor coupled to the memory. In response to issuing one or more requests for data, a processor maps one or more of the requests for data to a return queue structure. The processor then allocates one or more virtual queues to the return queue structure based on the mapped requests. In response to allocating the virtual queues to the return queue, the processor writes the data indicated in the mapped requests to the allotted virtual queues and enables the return queue for arbitration. When the return queue is enabled for arbitration, the processor reads out the data written to the allocated virtual queues, processes the read out data, and provides the processed data to a processing pipeline.

Adaptive out of order arbitration for numerous virtual queues

Devices, systems, and methods for sampling partially resident texture data. An instruction which includes a residency map descriptor is received. The instruction is executed to retrieve partially resident texture data from a mipmap stored in a memory based on the residency map descriptor. The residency map descriptor includes a residency map.

Sampling for partially resident textures

A technique for processing computer instructions is provided. The technique includes obtaining information for an instruction state memory entry for an instruction; identifying, for the instruction state memory entry, a slot in an instruction state memory having selectably powered rows and blocks, based on clustering criteria; and placing the instruction state memory entry into the identified slot.

Adaptable allocation of SRAM based on power

A technique for performing ray tracing operations is provided. The technique includes processing small bounding box nodes in a box intersection test circuit to generate intersection test results for the small bounding box nodes; and processing large bounding box nodes in the box intersection test circuit to generate intersection test results for the large bounding box nodes.

Variable width bounding volume hierarchy nodes

A graphics pipeline includes a texture cache having cache lines that are partitioned into a plurality of subsets. The graphics pipeline also includes one or more compute units that selectively generates a miss request for a first subset of the plurality of subsets of a cache line in the texture cache in response to a cache miss for a memory access request to an address associated with the first subset of the cache line. In some embodiments, the cache lines are partitioned into a first sector and a second sector. The compute units generate miss requests for the first sector, and bypass generating miss requests for the second sector, in response to cache misses for memory access requests received during a request cycle being in the first sector.

Selective generation of miss requests for cache lines

Techniques for performing ray tracing for a ray are provided. The techniques include, based on first traversal of a bounding volume hierarchy, identifying a first memory page that is classified as resident, obtaining a first portion of the bounding volume hierarchy associated with the first memory page, traversing the first portion of the bounding volume hierarchy according to a ray intersection test, based on second traversal of the bounding volume hierarchy, identifying a second memory page that is classified as valid and non-resident, and in response to the second memory page being classified as valid and non-resident, determining that a miss occurs for each node of the bounding volume hierarchy within the second memory page.

Partially resident bounding volume hierarchy

A technique for performing ray tracing operations is provided. The technique includes reading descendant-shared type metadata for a non-leaf node of a bounding volume hierarchy; identifying one or more culling types for a ray-intersection test for a ray; and determining whether to treat the non-leaf node as not intersected based on whether the one or more culling types includes at least one type specified by the descendant-shared type metadata.

Early culling for ray tracing

Techniques for allowing cache access returns out of order are disclosed. A return ordering queue exists for each of several cache access types and stores outstanding cache accesses in the order in which those accesses were made. When a cache access request for a particular type is at the head of the return ordering queue for that type and the cache access is available for return to the wavefront that made that access, the cache system returns the cache access to the wavefront. Thus, cache accesses can be returned out of order with respect to cache accesses of different types. Allowing out-of-order returns can help to improve latency, for example in the situation where a relatively low-latency access type (e.g., a read) is issued after a relatively high-latency access type (e.g., a texture sampler operation).

Out-of-order cache returns

Isochronous data transfers guarantee data packets are received at a particular frequency and within a prespecified jitter-tolerance. Asynchronous data transfers guarantee data integrity by allowing missed or errant packets to be resent as many times as needed until an error-free packet may be reconstructed at the receiver. Isochronous transfers address real-time needs but do not address the data integrity issue. Asynchronous transfers address the data integrity issue but cannot guarantee error-free data packets will be available so as to meet a real-time constraint. The present invention provides method and apparatus enable isochronous data transfers with improved data integrity. Various link layer and transaction layer mechanisms are taught. An embodiment involving the IEEE 1394 bus specification is addressed in detail.

Method and apparatus for isochronous data transfer with retry capability

A method and apparatus for processing data packets through direct memory access (DMA) in transferring data packets between a bus and an apparatus containing DMA engines. The DMA engines process different contexts, also referred to as distinct logical data streams. The phase of a bus along with the status of DMA transactions are monitored. The phase and the status are used to dynamically allocate priorities to the DMA engines to maximize the efficiency in processing data.

Method for allocating priorities to plurality of DMA engines for processing data packets based on bus phase and transactions status

An integrated circuit that includes an improved architecture that reduces the interface between different blocks by minimizing the wire connections between the two blocks. Specifically, the two blocks are structured to transfer data between the two blocks using only the data bus and a common clock, thus eliminating the need for an address bus. Each block contains data registers used for storing data. The data registers in one block correspond to the registers in the second block, with each block being aware of the memory structure of the other block. When one block needs data from the data registers of the other block, it requests the data and the sending block places the contents of its data registers on the bus sequentially. The requesting block reads the data from the data bus at the appropriate time by counting the number of clock cycles from the time that the data was requested.

Method and apparatus for data sharing between two different blocks in an integrated circuit

System for transferring data packets of different context utilizing single interface and concurrently processing data packets of different contexts

A method and apparatus for receiving packets from a bus. A packet is received at an interface to the bus. The packet is parsed, and a determination is made whether to retain the packet from the parsing of the packet. The packet is placed in a buffer with a header. The packet is moved from the buffer to another bus using information located within the header, wherein repeated parsing of the packet to move the packet to another bus is unnecessary.

Growing community of inventors

Boxborough, MA, United States of America

Fataneh Ghodrat