Abstract: A graphics processing unit (GPU) includes a table located in a memory of the GPU and a cache hierarchy. The table contains an address of inactive data in a cache hierarchy of the GPU in which the inactive data is associated with an intermediate render target. The cache hierarchy is responsive to an eviction event by discarding the inactive data from the cache hierarchy without performing a writeback to a system memory associated with the GPU based on the address of the inactive data being contained in the table. The cache hierarchy may obtain the address of the inactive data from the table, and the inactive data may be located in a last-level cache of the cache hierarchy. In one embodiment, the address of inactive data in a cache hierarchy of the GPU includes a range of addresses for the inactive data.

Abstract: A graphics processing unit (GPU) includes a table located in a memory of the GPU and a cache hierarchy. The table contains an address of inactive data in a cache hierarchy of the GPU in which the inactive data is associated with an intermediate render target. The cache hierarchy is responsive to an eviction event by discarding the inactive data from the cache hierarchy without performing a writeback to a system memory associated with the GPU based on the address of the inactive data being contained in the table. The cache hierarchy may obtain the address of the inactive data from the table, and the inactive data may be located in a last-level cache of the cache hierarchy. In one embodiment, the address of inactive data in a cache hierarchy of the GPU includes a range of addresses for the inactive data.

Abstract: Techniques for executing a load instruction in a processor are described. In one example, load instructions which are detected to have an offset (or displacement) of zero are sent directly to a data cache, bypassing the address generation stage thereby reducing pipeline length. Load instructions having a nonzero offset can be executed in an address generation stage as is conventional. To avoid conflicts between a current load instruction with zero offset and a previous load instruction with nonzero offset, the current instruction can be rescheduled or sent through a separate dedicated load pipe. An alternative technique permits a load instruction with zero offset to be issued one cycle earlier than it would need to be if it had a nonzero offset, thus reducing load latency.

Abstract: Techniques for executing a load instruction in a processor are described. In one example, load instructions which are detected to have an offset (or displacement) of zero are sent directly to a data cache, bypassing the address generation stage thereby reducing pipeline length. Load instructions having a nonzero offset can be executed in an address generation stage as is conventional. To avoid conflicts between a current load instruction with zero offset and a previous load instruction with nonzero offset, the current instruction can be rescheduled or sent through a separate dedicated load pipe. An alternative technique permits a load instruction with zero offset to be issued one cycle earlier than it would need to be if it had a nonzero offset, thus reducing load latency.

Abstract: Embodiments of the present technology are directed toward techniques for balancing memory accesses to different memory types.

Abstract: Embodiments of the present technology are directed toward techniques for balancing memory accesses to different memory types.

Abstract: A microprocessor includes multiple register files. In a single thread mode, the microprocessor allows a single thread to have access to multiple ones of the register files. In a multi-thread mode, each thread has access to respective ones of the register files. In the multi-thread mode, multiple threads are simultaneously executing. Circuitry and hardware are provided to facilitate the respective modes and to facilitate transitions between the modes.

Abstract: A microprocessor includes multiple register files. In a single thread mode, the microprocessor allows a single thread to have access to multiple ones of the register files. In a multi-thread mode, each thread has access to respective ones of the register files. In the multi-thread mode, multiple threads are simultaneously executing. Circuitry and hardware are provided to facilitate the respective modes and to facilitate transitions between the modes.

Abstract: An efficient method for implementing string operations used to process blocks of data within a memory. The registers used to track the memory addresses are updated and committed before the outcome of a read or write address operation is known. In the event an exception occurs, exception handling hardware and microcode is used to restore the state of the registers to the condition they were in prior to the iteration which produced the exception. This reduces the number of microcode instructions required to implement the string operation, producing a faster cycling of the code through multiple iterations. The result is a more optimal code for string operations and a decrease in the time required to carry out the string instruction.