IP Library Granted Patent US 12,111,711
Granted Patent B2
US 12,111,711 · App. 17/402,927 · Granted Oct 8, 2024

Method, apparatus, and system for energy efficiency and energy conservation including power and performance balancing between multiple processing elements and/or a communication bus

Inventors: Travis T. Schluessler (Berthoud, CO); Russell J. Fenger (Beaverton, OR)
Assignee: Daedalus Prime LLC
G06F1/3206G06F1/206G06F1/3203G06F1/3253G06F1/3287G06F1/329G06F9/5094G06F9/50Y02D10/00
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 12,111,711
App. No.
17/402,927
Granted
Oct 8, 2024
Kind
B2
Abstract

An apparatus, method and system is described herein for efficiently balancing performance and power between processing elements based on measured workloads. If a workload of a processing element indicates that it is a bottleneck, then its performance may be increased. However, if a platform or integrated circuit including the processing element is already operating at a power or thermal limit, the increase in performance is counterbalanced by a reduction or cap in another processing elements performance to maintain compliance with the power or thermal limit. As a result, bottlenecks are identified and alleviated by balancing power allocation, even when multiple processing elements are operating at a power or thermal limit.

Claims (21)

1. A system on chip (SoC) comprising:

an integrated circuit package comprising:

a core unit having a first core to support out-of-order execution of instructions, including a first cache memory, a second core to support in-order execution of instructions including a second cache memory, and a shared cache memory to be shared by at least the first core and the second core;

a graphics processing unit (GPU) to execute a graphics workload;

a memory controller;

a communication bus coupled to the core unit, the communication bus to couple the core unit and the GPU, the communication bus comprising a cache coherent interconnect;

a static random access memory;

an interface to interface the SoC with another device via a Peripheral Component Interconnect Express (PCIE) protocol;

a first workload monitor to determine a core workload of the core unit;

a second workload monitor to determine the graphics workload of the GPU;

a third workload monitor to determine a bus workload for the communication bus; and

a power controller to reduce a power consumption of at least the core unit if a thermal value of the SoC exceeds a thermal design power (TDP) limit for the SoC, wherein in a first scenario the power controller is to increase a frequency for the GPU when the graphics workload is greater than a graphics threshold and reduce the frequency of the core unit, and in a second scenario to increase a frequency for the core unit and the communication bus and reduce the frequency of the GPU,

wherein the power controller is to receive the bus workload and to dynamically balance power between the core unit and the communication bus based on the TDP limit and a comparison between the bus workload and a bus threshold, and

wherein the power controller, in response to operation of the SoC at the TDP limit, is to increase frequency for the communication bus and cap the frequency for the core unit if the bus workload is greater than the bus threshold, and decrease the frequency for the communication bus and increase the frequency for the core unit if the bus workload is less than the bus threshold.

2. The SoC of claim 1 , wherein the power controller is to reduce a power consumption of at least one of the core unit or the communication bus if the thermal value of the SoC exceeds the TDP limit.

3. The SoC of claim 1 , wherein the shared cache memory comprises a level two cache memory.

4. The SoC of claim 1 , wherein the power controller is to reduce the frequency for the core unit and to increase the frequency for the GPU when the SoC is to execute a game application.

5. The SoC of claim 1 , wherein the power controller is to receive a hint regarding a future workload and to dynamically balance the power based on the hint.

6. The SoC of claim 1 , wherein the power controller is to increase the frequency for the GPU and reduce the frequency for the core unit when the GPU is to execute a producer thread and the core unit is to execute a consumer thread to consume information produced by the producer thread.

7. The SoC of claim 1 , wherein the core unit further comprises a third core, wherein the third core is asymmetric to at least the first core.

8. The SoC of claim 7 , wherein at least the first core comprises an out-of-order processor core.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2022
From: INTEL CORPORATION
To: DAEDALUS PRIME LLC
Reel/Frame 060392/0594 →
Continuity (6)
Continuation 16421647 · May 24, 2019
Continuation 15611876 · Jun 2, 2017
Continuation 14526040 · Oct 28, 2014
Continuation 13398641 · Feb 16, 2012
Continuation In Part 13327670 · Dec 15, 2011
Related Publication 20210373638A1 · Dec 2, 2021