18490588. On-demand Memory Allocation simplified abstract (Apple Inc.)
Contents
On-demand Memory Allocation
Organization Name
Inventor(s)
Justin A. Hensley of Mountain View CA (US)
Karl D. Mann of Geneva FL (US)
Yoong Chert Foo of London (GB)
Terence M. Potter of Austin TX (US)
Frank W. Liljeros of Sanford FL (US)
Ralph C. Taylor of Deland FL (US)
On-demand Memory Allocation - A simplified explanation of the abstract
This abstract first appeared for US patent application 18490588 titled 'On-demand Memory Allocation
Simplified Explanation
The abstract of this patent application describes techniques for dynamically allocating and mapping private memory for requesting circuitry. The disclosed circuitry can receive a private address and translate it to a virtual address, which can then be translated by an MMU (Memory Management Unit) to a physical address to access a storage element. The private memory allocation circuitry can generate page table information and map private memory pages for requests if the page table information is not already set up. This allows for dynamic private memory allocation, which can efficiently allocate memory for graphics shaders with different types of workloads. Caching techniques for page table information are also disclosed, which can improve performance compared to traditional techniques. Additionally, the disclosed embodiments can facilitate memory consolidation across a device, such as a graphics processor.
- Techniques for dynamically allocating and mapping private memory for requesting circuitry are disclosed.
- Private memory allocation circuitry can generate page table information and map private memory pages for requests.
- Private addresses are translated to virtual addresses, which are then translated to physical addresses by an MMU.
- Dynamic private memory allocation allows for efficient allocation of memory for graphics shaders with different workloads.
- Caching techniques for page table information improve performance compared to traditional techniques.
- Memory consolidation across a device, such as a graphics processor, is facilitated.
Potential Applications
- Graphics processing
- Virtual reality systems
- High-performance computing
- Gaming consoles
Problems Solved
- Efficient allocation of memory for graphics shaders with different workloads
- Improved performance in memory management
- Facilitating memory consolidation across a device
Benefits
- Dynamic private memory allocation allows for efficient use of resources
- Caching techniques improve performance in memory management
- Memory consolidation simplifies memory management and improves efficiency
Original Abstract Submitted
Techniques are disclosed relating to dynamically allocating and mapping private memory for requesting circuitry. Disclosed circuitry may receive a private address and translate the private address to a virtual address (which an MMU may then translate to physical address to actually access a storage element). In some embodiments, private memory allocation circuitry is configured to generate page table information and map private memory pages for requests if the page table information is not already setup. In various embodiments, this may advantageously allow dynamic private memory allocation, e.g., to efficiently allocate memory for graphics shaders with different types of workloads. Disclosed caching techniques for page table information may improve performance relative to traditional techniques. Further, disclosed embodiments may facilitate memory consolidation across a device such as a graphics processor.
