Systems and methods for rapid processing and storage of data
Systems and methods of building massively parallel computing systems using low power computing complexes in accordance with embodiments of the invention are disclosed. A massively parallel computing system in accordance with one embodiment of the invention includes at least one Solid State Blade configured to communicate via a high performance network fabric. In addition, each Solid State Blade includes a processor configured to communicate with a plurality of low power computing complexes interconnected by a router, and each low power computing complex includes at least one general processing core, an accelerator, an I/O interface, and cache memory and is configured to communicate with non-volatile solid state memory.
1. A computing system, comprising:
a plurality of solid state blades interconnect via a high performance network switch fabric, wherein each solid state blade comprises:
a processor;
an array of System on Chip (SOC) computing complexes and associated non-volatile solid state memory components located on the solid state blade;
wherein the processor is configured to communicate with the array of SOC computing complexes interconnected by an on-blade router;
wherein each SOC computing complex is directly connected to and communicating with at least one associated and dedicated non-volatile solid state memory component from a plurality of non-volatile solid state memory components located on the solid state blade;
wherein each SOC computing complex in the array of SOC computing complexes integrates a plurality of functions onto a single chip, the plurality of functions including general processing, accelerated processing, storage control, and communications links, wherein a SOC computing complex integrates on a single chip at least one general processing core, an I/O interface, a cache memory, a memory controller, and a Package on Package DRAM memory;
wherein the general processing core in a given SOC computing complex is configured to use the memory controller to coordinate reading and writing data to the at least one associated non-volatile solid state memory component within the given SOC computing complex; and
wherein the general processing cores in the plurality of SOC computing complexes are configured to directly read from and write data to the non-volatile solid state memory component to which they are connected in parallel.
2. The computing system of claim 1 , wherein the non-volatile solid state memory component is NAND Flash memory.
3. The computing system of claim 1 , wherein the SOC computing complex is configured to communicate with the at least one associated and dedicated non-volatile solid state memory component at a rate of at least 200 MB/s.
4. The computing system of claim 1 , wherein at least one non-volatile solid state memory component is configured in a RAID configuration.
5. The computing system of claim 1 , wherein the array of SOC computing complexes are directly connected.
6. The computing system of claim 1 , wherein the non-volatile solid state memory component is configured as a RAID array.
7. The computing system of claim 1 , wherein each of the at least one non-volatile solid state memory components dedicated to a SOC computing complex is packaged by Package on Package to the computing complex.
8. The computing system of claim 1 , wherein a first SOC computing complex is configured to access data within a non-volatile solid state memory component that is dedicated to a second SOC computing complex by requesting the data from the second SOC computing complex via an on-blade router.
9. The computing system of claim 1 , where a software RAID configuration is implemented across all of the non-volatile solid state memory components of each of the array of SOC computing complexes.
10. The computing system of claim 1 , wherein each interconnect is configured to provide data rates of at least 500 MB/s.
11. The computing system of claim 1 , wherein an interconnect between the on-blade router and the processor is configured to provide data rates of at least 25 GB/s.
12. The computing system of claim 1 , wherein at least one solid state blade comprises at least 32 SOC computing complexes.
13. The computing system of claim 1 , wherein the I/O interface is configured to communicate at a rate of at least 500 MB/s.
14. The computing system of claim 1 , wherein each SOC computing complex directly reads and writes data to at least one associated and dedicated non-volatile solid state memory component configured as a RAID array.
15. The computing system of claim 14 , wherein the RAID array is implemented using a memory controller incorporated in each SOC computing complex, and wherein the memory controller is a RAID controller.
16. The computing system of claim 1 , wherein the I/O between the SOC computing complex and other devices is managed by the I/O interface.
17. The computing system of claim 1 , wherein the on-blade router is a programmable router.
18. The computing system of claim 1 , wherein at least one solid state blade is programmable using an Open Computing Language (Open CL) and triplestores.