公开(公告)号：US20190012156A1

公开(公告)日：2019-01-10

申请号：US15644150

申请日：2017-07-07

Applicant: Intel Corporation

Inventor： Daniel P. Daly ,  Thomas E. Willis ,  Pat Wang ,  Vishal Anand ,  Hung Nguyen ,  Varsha Apte

IPC: G06F9/45

Abstract: Technologies for network application programming include a computing device that analyzes a network application source program. The source program includes a declarative description of a network application in a domain-specific language, such as P4. The computing device translates the declarative description of the network application into a register-transfer level (RTL) description, and then compiles the RTL description into a bitstream definition that is targeted to an FPGA. For example, the computing device may generate a parse graph based on the network application source program, and then generate an RTL TCAM-SRAM structure for each node of the parse graph. The computing device may optimize the RTL description, for example by simplifying RTL structures or removing unused logic. The computing device may program an FPGA with the bitstream definition. Other embodiments are described and claimed.

公开(公告)号：US10268464B2

公开(公告)日：2019-04-23

申请号：US15644150

申请日：2017-07-07

Applicant: Intel Corporation

Inventor： Daniel P. Daly ,  Thomas E. Willis ,  Pat Wang ,  Vishal Anand ,  Hung Nguyen ,  Varsha Apte

IPC: G06F8/41 ,  G06F8/51 ,  G11C15/04 ,  G11C11/412

Abstract: Technologies for network application programming include a computing device that analyzes a network application source program. The source program includes a declarative description of a network application in a domain-specific language, such as P4. The computing device translates the declarative description of the network application into a register-transfer level (RTL) description, and then compiles the RTL description into a bitstream definition that is targeted to an FPGA. For example, the computing device may generate a parse graph based on the network application source program, and then generate an RTL TCAM-SRAM structure for each node of the parse graph. The computing device may optimize the RTL description, for example by simplifying RTL structures or removing unused logic. The computing device may program an FPGA with the bitstream definition. Other embodiments are described and claimed.

公开(公告)号：US11687264B2

公开(公告)日：2023-06-27

申请号：US15721053

申请日：2017-09-29

Applicant: Intel Corporation

Inventor： Chih-Jen Chang ,  Brad Burres ,  Jose Niell ,  Dan Biederman ,  Robert Cone ,  Pat Wang ,  Kenneth Keels ,  Patrick Fleming

IPC: H04L67/63 ,  G06F3/06 ,  G06F16/174 ,  G06F21/57 ,  G06F21/73 ,  G06F8/65 ,  H04L41/0816 ,  H04L41/0853 ,  H04L41/12 ,  H04L67/10 ,  G06F11/30 ,  G06F9/50 ,  H01R13/453 ,  G06F9/48 ,  G06F9/455 ,  H05K7/14 ,  H04L61/5007 ,  H04L67/75 ,  H03M7/30 ,  H03M7/40 ,  H04L43/08 ,  H04L47/20 ,  H04L47/2441 ,  G06F11/07 ,  G06F11/34 ,  G06F7/06 ,  G06T9/00 ,  H03M7/42 ,  H04L12/28 ,  H04L12/46 ,  G06F13/16 ,  G06F21/62 ,  G06F21/76 ,  H03K19/173 ,  H04L9/08 ,  H04L41/044 ,  H04L49/104 ,  H04L43/04 ,  H04L43/06 ,  H04L43/0894 ,  G06F9/38 ,  G06F12/02 ,  G06F12/06 ,  G06T1/20 ,  G06T1/60 ,  G06F9/54 ,  H04L67/1014 ,  G06F8/656 ,  G06F8/658 ,  G06F8/654 ,  G06F9/4401 ,  H01R13/631 ,  H04L47/78 ,  G06F16/28 ,  H04Q11/00 ,  G06F11/14 ,  H04L41/046 ,  H04L41/0896 ,  H04L41/142 ,  H04L9/40 ,  G06F15/80

CPC classification number: G06F3/0641 ,  G06F3/0604 ,  G06F3/065 ,  G06F3/067 ,  G06F3/0608 ,  G06F3/0611 ,  G06F3/0613 ,  G06F3/0617 ,  G06F3/0647 ,  G06F3/0653 ,  G06F7/06 ,  G06F8/65 ,  G06F8/654 ,  G06F8/656 ,  G06F8/658 ,  G06F9/3851 ,  G06F9/3891 ,  G06F9/4401 ,  G06F9/45533 ,  G06F9/4843 ,  G06F9/4881 ,  G06F9/5005 ,  G06F9/505 ,  G06F9/5038 ,  G06F9/5044 ,  G06F9/5083 ,  G06F9/544 ,  G06F11/0709 ,  G06F11/079 ,  G06F11/0751 ,  G06F11/3006 ,  G06F11/3034 ,  G06F11/3055 ,  G06F11/3079 ,  G06F11/3409 ,  G06F12/0284 ,  G06F12/0692 ,  G06F13/1652 ,  G06F16/1744 ,  G06F21/57 ,  G06F21/6218 ,  G06F21/73 ,  G06F21/76 ,  G06T1/20 ,  G06T1/60 ,  G06T9/005 ,  H01R13/453 ,  H01R13/4536 ,  H01R13/4538 ,  H01R13/631 ,  H03K19/1731 ,  H03M7/3084 ,  H03M7/40 ,  H03M7/42 ,  H03M7/60 ,  H03M7/6011 ,  H03M7/6017 ,  H03M7/6029 ,  H04L9/0822 ,  H04L12/2881 ,  H04L12/4633 ,  H04L41/044 ,  H04L41/0816 ,  H04L41/0853 ,  H04L41/12 ,  H04L43/04 ,  H04L43/06 ,  H04L43/08 ,  H04L43/0894 ,  H04L47/20 ,  H04L47/2441 ,  H04L49/104 ,  H04L61/5007 ,  H04L67/10 ,  H04L67/1014 ,  H04L67/63 ,  H04L67/75 ,  H05K7/1452 ,  H05K7/1487 ,  H05K7/1491 ,  G06F11/1453 ,  G06F12/023 ,  G06F15/80 ,  G06F16/285 ,  G06F2212/401 ,  G06F2212/402 ,  G06F2221/2107 ,  H04L41/046 ,  H04L41/0896 ,  H04L41/142 ,  H04L47/78 ,  H04L63/1425 ,  H04Q11/0005 ,  H05K7/1447 ,  H05K7/1492

Abstract: Technologies for an accelerator interface over Ethernet are disclosed. In the illustrative embodiment, a network interface controller of a compute device may receive a data packet. If the network interface controller determines that the data packet should be pre-processed (e.g., decrypted) with a remote accelerator device, the network interface controller may encapsulate the data packet in an encapsulating network packet and send the encapsulating network packet to a remote accelerator device on a remote compute device. The remote accelerator device may pre-process the data packet (e.g., decrypt the data packet) and send it back to the network interface controller. The network interface controller may then send the pre-processed packet to a processor of the compute device.