Arm DynamIQ: Intelligent Solutions Using Cluster Based Multiprocessing
•Als PPTX, PDF herunterladen•
2 gefällt mir•1,208 views
Peter Greenhalgh, VP and GM of Central Technology, Arm.
Empfohlen
Empfohlen
Weitere ähnliche Inhalte
Was ist angesagt?
Was ist angesagt? (20)
Ähnlich wie Arm DynamIQ: Intelligent Solutions Using Cluster Based Multiprocessing
Ähnlich wie Arm DynamIQ: Intelligent Solutions Using Cluster Based Multiprocessing (20)
Mehr von Arm
Mehr von Arm (11)
Kürzlich hochgeladen
Kürzlich hochgeladen (20)
Arm DynamIQ: Intelligent Solutions Using Cluster Based Multiprocessing
- 1. © 2017 Arm Limited Peter Greenhalgh VP and GM of Central Technology Arm DynamIQ: Intelligent Solutions Using Cluster Based Multiprocessing
- 2. © 2017 Arm Limited2 Drones Wearable technology Smartwatch 3D printing Voice recognition Social media Technology innovations of 2013
- 3. © 2017 Arm Limited3 Looking ahead from edge to cloud The future requires a new approach to CPU design Safe and autonomous Hyper-efficient Secure private compute Cortex beyond mobile Mixed reality
- 4. Confidential © Arm 20174 Arm DynamIQ Rearchitecting the compute experience Multi-core redefined for broad market Massive system performance uplift More intelligent systems
- 5. © 2017 Arm Limited5 Innovating for the scalable future Up to 8 CPUs ‘Octacore’ smartphones Dual cluster Heterogeneous processing Nearly “Unlimited” design spectrum Covers all existing use cases DynamIQ cluster Dynamic flexibility 2013 2017 Expanding Arm technology processor architecture for broad market Arm AMBA Arm big.LITTLE Arm CoreLink Arm TrustZone Arm NEON Key Arm technologies
- 6. © 2017 Arm Limited DSU – Broadening the reach of technology
- 7. © 2017 Arm Limited7 DynamIQ: New cluster design for new cores DynamIQ big.LITTLE systems: • Greater product differentiation and scalability • Improved energy efficiency and performance • SW compatibility with Energy Aware Scheduling (EAS) Private L2 and shared L3 caches • Local cache close to processors • L3 cache shared between all cores DynamIQ Shared Unit (DSU) • Contains L3, Snoop Control Unit (SCU) and all cluster interfaces 1b+4L1b+3L1b+2L 1b+7L Example DynamIQ big.LITTLE configurations .. AMBA4 ACE SCU Shared L3 cacheACP Cortex-A55 32b/64b Core Private L2 cache Async BridgesPeripheral Port Cortex-A75 32b/64b Core Private L2 cache DynamIQ Shared Unit (DSU) 2b+6L 4b+4L
- 8. © 2017 Arm Limited8 DynamIQ cluster 0 - 7 CoresCore 0 Snoop filter Power Management L3 Cache Bus I/F ACP and peripheral port I/F Core 7 Asynchronous bridges DynamIQ Shared Unit (DSU) DynamIQ Shared Unit (DSU) Streamlines traffic across bridges Advanced power management features Latency and bandwidth optimizations Support for multiple performance domains Scalable interfaces for edge to cloud applications Supports large amounts of local memory Low latency interfaces for closely coupled accelerators
- 9. © 2017 Arm Limited9 Level 3 cache memory system New memory system for Cortex-A clusters Integrated snoop filter to improve efficiency Enabling lower cache latencies DynamIQ cluster 0–7 Cores Core0 Snoop filter Power Mngmt L3 Cache Bus I/F ACP and peripheral port I/F Core7 Asynchronous bridges DynamIQ Shared Unit (DSU) L1 cache L2 cache Load to Use Cycles* Cortex-A53 Cortex-A55 Cortex-A73 Cortex-A75 L1 hit 3 2 3 3 L2 hit 13 6 19 8 L3 hit - 21 - 25 Interconnect boundary 20 21 26 25 L1 cache L2 cache
- 10. © 2017 Arm Limited10 Level 3 cache partition Infrastructure • Process 1 = data plane • Process 2 = control plane • Packet processing data sent through low latency ACP interface Sensors or I/O agents ACP Process 2 Core group 2 Example configuration with two Core groups in a DynamIQ cluster Group 1 Group 2 Core group 1 Process 1 L3 cache Core0 Core1 Core2 Core3 Core4 Core5 Core6 Core7 Reserved for external accelerators via ACP
- 11. © 2017 Arm Limited11 Level 3 cache partition Automotive • Each process could represent an independent ADAS algorithm • Sensors linked through low latency ACP interface Sensors or I/O agents ACP Process 4 Core group 4 Example configuration with four Core groups in a DynamIQ cluster Group 1,2 Group 4 Core group 1 Process 1 L3 cache Core0 Core1 Core6 Core7 Core group 2 Process 2 Core2 Core3 Core group 3 Process 3 Core4 Core5 Group 3 Reserved for external accelerators via ACP
- 12. © 2017 Arm Limited12 Increasing performance through cache stashing Enables reads/writes into the shared L3 cache or per-core L2 cache Allows closely coupled accelerators and I/O agents to gain access to core memory AMBA 5 CHI and Accelerator Coherency Port (ACP) can be used for cache stashing More throughput with Peripheral Port (PP) for acceleration, network, storage use-cases Accelerator or I/O CoreLink CMN-600 DMC-620 DMC-620 Agile System Cache DDR4 DDR4 L3 Cache L2 Cache CPU L2 Cache CPU L2 Cache CPU L2 Cache Cortex-A Agile System Cache L3 Cache L2 Cache CPU L2 Cache CPU L2 Cache CPU L2 Cache Cortex-A Stash critical data to any cache level DynamIQ cluster 0–7 Cores Core0 Snoop filter Power Mngmt L3 Cache Bus I/F ACP and peripheral port I/F Core7 Asynchronous bridges DynamIQ Shared Unit (DSU) L1 cache L2 cache L1 cache L2 cache
- 13. © 2017 Arm Limited13 Increasing performance through tight integration Offload acceleration Example application: Offload crypto acceleration I/O processing Example application: Packet processing in network systems DynamIQ cluster Accelerator (4) Writes result into Core memory (1) Configure registers for task (2) Fetches data from Core memory (3) Carries out acceleration ACP PP DynamIQ cluster I/O agent (4) Reads result from Core memory or sends data for onward processing (3) Processing completed (1) Writes data into Core memory (2) Carries out computation ACP PP
- 14. © 2017 Arm Limited14 Automotive and industrial safety and reliability ADAS and IVI compute performance • DynamIQ provides performance required for autonomous cars • Faster responsiveness DynamIQ: Functional Safety • Following ASIL D systematic flow • Provides higher safety integrity Industry’s broadest functional safety capable CPU portfolio Autonomous system Sense Perceive Decide Actuate Cortex-M Cortex-R Safety IslandApplication cores L3 Cache L2 Cache CPU L2 Cache CPU L2 Cache CPU L2 Cache Cortex-A Sensors SoC Lock-step core
- 15. © 2017 Arm Limited Cortex-A75 – Increasing Performance Cortex-A55 – Improving Efficiency
- 16. © 2017 Arm Limited16 New levels of performance for smart solutions Cortex-A75 Cortex-A55 All comparisons at ISO process and frequency Baseline to Cortex-A73 Baseline to Cortex-A53 1.21x 1.42x 1.97x 1.14x 1.22x SPECINT2006 SPECFP2006 LMBench memcpy Octane 2.0 Geekbench v4 1.22x 1.33x 1.16x 1.48x 1.34x SPECINT2006 SPECFP2006 LMBench memcpy Octane 2.0 Geekbench v4 All comparisons at ISO process and frequency
- 17. © 2017 Arm Limited17 Architecture and Pipelines Common features • Armv8.2-A Architecture • DynamIQ big.LITTLE Cortex-A75 – performance focussed • Out-of-Order, 11-13 stage integer pipeline Cortex-A55 – efficiency focussed • In-order, 8 stage integer pipeline ALU/INT (MAC) NEON/FP F0 Decode NEON/FP F1 Instruction Fetch Writeback Issue ALU/INT (DIV) Branch AGU Load AGU Store Cortex-A55 Int I0 (MUL) Decode Instruction Fetch Writeback Int I1 (DIV) AGU LD/ST AGU LD/ST Branch B Cortex-A75 Instruction Queue Writeback Rename Dispatch IsQ (12) IsQ (12) IsQ (8) IsQ (8) IsQ (20) Decode Rename IsQ (8) IsQ (8) IsQ (8) NEION/FP F1 NE/FP Store NEON/FP F0 Writeback
- 18. © 2017 Arm Limited18 Instruction Extraction & Parsing Instruction Queue FillBuffer Conditional PredictorL1 Instruction Cache AGU Indirect Predictor Branch Predictor Instruction fetch Common features • 4-way set associative • Virtually indexed, physically tagged (VIPT) • Decoupled from Cores thru instruction queue Cortex-A75 • 64KB • 4-wide instruction fetch Cortex-A55 • 16KB / 32KB / 64KB • 2-wide instruction fetch
- 19. © 2017 Arm Limited19 Instruction Extraction & Parsing Instruction Queue FillBuffer Conditional PredictorL1 Instruction Cache AGU Indirect Predictor Branch Predictor Branch prediction Cortex-A75 • Fine-tuned 0-cycle prediction • State of the art, mobile focussed, table based conditional prediction Cortex-A55 • Brand new 0-cycle predictors • New main conditional predictor - Neural network based • New loop predictors
- 20. © 2017 Arm Limited20 Cortex-A75: Datapaths 3-way superscalar high-performance pipeline • Single-cycle decode with instruction fusing and micro-ops 7 independent high-performance issue queues • 2x Load/Store, 2x NEON/FPU, 1x Branch and 2x Integer core Increased capacity to sustain operation under L1 miss / L2 hit • 12 entries for integer core to maximise on in- flight instructions and out-of-order capabilities • 8 entries for Load/Store and NEON/FPU Cortex-A75 Private L2 Cache Instruction Fetch Main TLB Arm Register File D.E. Register File Dispatch Issue 64k D-Cache STB 64k I-Cache Branch Prediction Decode Rename Load/Store Advanced NEON Floating Point ALUs iDIV MAC AGUs Writeback
- 21. © 2017 Arm Limited21 Cortex-A55: Datapaths Dual issue of loads and stores Improved latency for forwarding ALU results to the AGU • Reduced by one cycle for many common ALU operations Reduced L1 cache load-to-use latency for pointer chasing to two cycles Integer Register File NEON-FP Regfile NEON Pipe Decode Store Pipe x2 Cortex-A55 ALU Pipe ALU Pipe Integer Pipe Divide Pipe Mult Acc Shift ALU Shift ALU Load PipeAGU Data Cache Output Data Cache Address
- 22. © 2017 Arm Limited22 L1 memory system Common features • 4-way set associative • VIPT with PIPT programmer’s view • Improved prefetchers Cortex-A75 • 64KB • Wider load-store than Cortex-A73 • Support Read-after-Write OoO with filtering Cortex-A55 • 16KB / 32KB / 64KB • Improved store buffer bandwidth to L1 • Larger 16-entry L1-TLB Store Buffer L1 Data Cache Prefetcher L1 TLB L2 TLB L2 Cache
- 23. © 2017 Arm Limited23 Store Buffer L1 Data Cache Prefetcher L1 TLB L2 TLB L2 Cache L2 memory system Common features • Private L2 cache in each Core • Running at Core speed • Exclusive data cache • Cache stashing into the L2 • Non-blocking 1024-entry TLB for hit-under-miss Cortex-A75 • 256KB / 512 KB Cortex-A55 • 0KB / 64KB / 128KB / 256KB
- 24. © 2017 Arm Limited24 Next-generation features Dot product and half-precision float for AI/ML processing Virtualized Host Extensions (VHE) offering Type-2 hypervisor (KVM) performance improvements Cache stashing and atomic operations improves multicore networking performance and improves latency Cache clean to persistence to support storage class memory Infrastructure class RAS enhancement including data poisoning and improved error management
- 25. © 2017 Arm Limited25 Innovating for the scalable future 2013-2017: The nature of compute is changing the landscape Expanding Arm technologies for broad market applicability New cluster design with new DynamIQ cores: • Cortex-A75: Breakthrough performance • Cortex-A55: Efficiency redefined Functional safety for industrial and automotive applications New features expanding microarchitecture capabilities: • DynamIQ Shared Unit , new cache features, new branch prediction
- 26. 2626 Thank You! Danke! Merci! 谢谢! ありがとう! Gracias! Kiitos! © 2017 Arm Limited
- 27. 2727 © 2017 Arm Limited The Arm trademarks featured in this presentation are registered trademarks or trademarks of Arm Limited (or its subsidiaries) in the US and/or elsewhere. All rights reserved. All other marks featured may be trademarks of their respective owners. www.arm.com/company/policies/trademarks