IP Library › Granted Patent US 12,153,952
Granted Patent B1
US 12,153,952 · App. 18/641,999 · Granted Nov 26, 2024

Method for processing multiple transactions converted from single transaction in processor, and processor for performing same

Inventors: Kwang Sun Lee (Yongin-si, KR); Do Hun Kim (Yongin-si, KR); Kee Bum Shin (Yongin-si, KR)
Assignee: MetisX CO., Ltd.
G06F9/467G06F9/3016G06F12/0875G06F2212/452
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,153,952
App. No.
18/641,999
Granted
Nov 26, 2024
Kind
B1
Abstract

A method for processing multiple transactions converted from a single transaction is provided, which is performed by a processor including at least one core and includes converting a first transaction conforming to an instruction according to an instruction set architecture (ISA) into a plurality of second transactions conforming to the register size of the core, and transferring, by the load-store unit (LSU) of the core, the plurality of second transactions to the cache, in which the LSU may be configured to further transfer, to the cache, conversion information indicating whether the plurality of second transactions are converted from the first transaction.

Claims (26)

1. A method for processing multiple transactions converted from a single transaction, the method being performed by a processor including at least one core and comprising:

determining, by a decoding circuit of the core, whether a size of a first transaction conforming to an instruction according to an instruction set architecture (ISA) is the same as a register size of the core;

in response to determining that the size of the first transaction is larger than the register size of the core, converting, by the decoding circuit or a load-store unit (LSU) of the core, the first transaction into a plurality of second transactions conforming to the register size of the core; and

transferring, by the LSU, the plurality of second transactions to a cache of the core,

wherein the LSU is configured to further transfer, to the cache, conversion information indicating whether the plurality of second transactions are converted from the first transaction.

2. The method according to claim 1 , wherein the conversion information is transferred using a user signal or a sideband signal of AXI protocol.

3. The method according to claim 1 , wherein the LSU is configured to continuously transfer the plurality of second transactions to the cache.

4. The method according to claim 1 , further comprising, when the conversion information indicates that the plurality of second transactions is converted from the first transaction, combining, by the cache receiving the conversion information, the plurality of second transactions into a third transaction.

5. The method according to claim 4 , wherein the cache is an internal cache used only by one core, and

wherein the combining is performed by a cache controller of the cache.

6. The method according to claim 5 , wherein a data width of a bus used by the cache is larger than the register size of the core.

7. The method according to claim 6 , wherein the third transaction is configured to conform to the data width of the bus used by the cache.

8. A processor that performs a method for processing multiple transactions converted from a single transaction,

wherein the processor includes at least one core,

wherein the method includes:

determining, by a decoding circuit of the core, whether a size of a first transaction conforming to an instruction according to an instruction set architecture (ISA) is the same as a register size of the core;

in response to determining that the size of the first transaction is larger than the register size of the core, converting, by the decoding circuit or a load-store unit (LSU) of the core, the first transaction into a plurality of second transactions conforming to the register size of the core; and

transferring, by the LSU, the plurality of second transactions to the cache of the core, and

wherein the LSU is configured to further transfer, to the cache, conversion information indicating whether the plurality of second transactions is converted from the first transaction.

9. The processor according to claim 8 , wherein the conversion information is transferred using a user signal or a sideband signal of AXI protocol.

10. The processor according to claim 8 , wherein the LSU is configured to continuously transfer the plurality of second transactions to the cache.

11. The processor according to claim 8 , wherein the method further includes, when the conversion information indicates that the plurality of second transactions is converted from the first transaction, combining, by the cache receiving the conversion information, the plurality of second transactions into a third transaction.

12. The processor according to claim 11 , wherein the cache is an internal cache used only by one core, and

wherein the combining is performed by a cache controller of the cache.

13. The processor according to claim 12 , wherein a data width of a bus used by the cache is larger than the register size of the core.

14. The processor according to claim 13 , wherein the third transaction is configured to conform to the data width of the bus used by the cache.

Assignments (2)
CHANGE OF NAME Recorded Jan 13, 2025
From: METISX CO., LTD.
To: XCENA INC.
Reel/Frame 069877/0477 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 22, 2024
From: LEE, KWANG SUN; KIM, DO HUN; SHIN, KEE BUM
To: METISX CO., LTD.
Reel/Frame 067181/0661 →
Priority Claims (1)
KR 10-2023-0093168 · Jul 18, 2023 · national