Multicore Software Technology Roadmap

Size: px
Start display at page:

Download "Multicore Software Technology Roadmap"

Transcription

1 November, 2010 Multicore Software Technology Roadmap Jacques Landry and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

2 Session Introduction This presentation will review the multicore software strategy for the Freescale Networking and Multimedia processor roadmap This will give you an overview of the key enablement plans for high-end and low-end processor families The multicore software strategy in this presentation focuses on the software components that will be used by application software to drive application-level performance and capability and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 2

3 Session Objective After completing this session you will be able to: Describe how the Freescale multicore software architecture enables application developers to achieve performance on Freescale multicore devices Name the components that make up the Freescale multicore software architecture Understand the roadmap for the major multicore software architecture components and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 3

4 Agenda Overview of the application space for networking Multicore software programming models High-performance multicore software architecture Low-end multicore software architecture Full system instrumentation for multicore Multicore software roadmap and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 4

5 Home Business Mobile Networking Segments User, Access, Core User Access Core Storage D Video Printers D Equipment (Medical, Industrial) Routers / Switches D SMB Gateway Security Appliances BTS Node B enb BTS 2G GSM/CDMA 3G UTRAN BSC RNC RNC D 3G LTE / Evolved WiMAX e Metro/WDM (SONET/SDH) IP/PBX D D D D PSTN GSN AGW ACR MGW D PSTN IP Core Network IMS/SIP Network Storage Media Hub Residential Gateway D D Femto BTS Modem Set Top Box DSLAM/MSAN PON OLT Cable CMTS BRAS Note: Simplified diagram, not all connections/applications shown D Applications with DSP and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 5

6 Power Key Technology Trends in Networking Segments Flattening of the network Consolidation of services into fewer devices, increased sustained bandwidth and processing rates, secure and trusted processing requirements Moore s law challenged Higher performance with power constraint. Advent of multicore and application-specific acceleration. Required software support. 1xCPU Frequency scaling of CPU cores no longer valid due to power constraints 30W Ceiling NxCPU Multicore processors viewed as the most viable approach to achieve required performance gains within power budgets 16W 8W 4W 2W Performance Requirement and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 6

7 Hardware Multicore Implementations Single Core with Hardware Accelerators CPU Homogeneous Multi/Many Core With or without accelerators Shared or distributed memory Heterogeneous Multi/Many Core Shared Bus CPU CPU CPU CPU DRAM CPU GPU DSP CPU DRAM DRAM Bridge Shared Bus Accel I/O I/O Accel I/O I/O Accel DRAM Accel I/O I/O FPU DRAM Sequential operations that cannot be multi-threaded Hardware acceleration provides more power/performance efficiency than software Easier programming environment Easier migration of legacy code Lack of specialized hardware for differing tasks Specialized hardware for different tasks Most power/performance efficient Software complexity and portability Increasing Software Complexity and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 7

8 Varied Multicore Programming Models Required Shared Cache APP APP Multicore System Hardware I/O Interrupt Controller Linux CPU CPU CPU CPU Memory I/O I/O I/O I/O Symmetric Multiprocessing Single on all cores Applications can run on any core - Common implementation in desktops Shared Cache Multicore System Hardware I/O Interrupt Controller Partition Partition Partition Partition Linux APP APP CPU I/O Linux APP APP Linux APP APP CPU I/O Linux APP APP Linux APP APP CPU I/O Linux APP APP Linux APP APP CPU Memory Memory Memory Memory I/O Linux APP APP Asymmetric Multiprocessing Many instances of the same on cores - Common implementation in servers Goal: consolidate servers, increase utilization Multicore System Hardware Shared Cache I/O Interrupt Controller Partition Partition Partition APP APP Linux APP APP RT APP APP Legacy CPU CPU CPU CPU Memory Memory Memory I/O Accel I/O I/O Memory Asymmetric Multiprocessing Many different s on dedicated cores - Common implementation in embedded markets and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 8

9 Power Closing the Gap with Multicore Solutions 1xCPU Freescale closes The Gap with Balanced Architecture 30W Ceiling NxCPU Smart multicore devices NxCPU + Acceleration Targeted application acceleration 6W 8W 4W 2W Performance Requirement Aggressive process technology Extensive multicore optimized software and ecosystem support and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 9

10 Security Accelerators Datapath Acceleration Multicore DSP / Processor Architectures 128KB Backside L2 Cache Power Architecture E500-mc Core 32KB D-Cache 32KB I-Cache SC3850 DSP Core 32KB L1 I-Cache 32KB L1 D-Cache 512KB L2 Cache M2 Memory MAPLE-B Dual RISC Processors Turbo/ Viterbi DFT/ IDFT FFT/ IFFT CRC DMA 4 TDMs QUICC Engine Subsystem High-Speed Serial Interface Management Interfaces JTAG High-Speed Interconnect Debug DDR2/DDR3 SDRAM Controller DDR2/DDR3 SDRAM Controller M3 Memory 1056 Kbyte Standard I/O DDR Interface 64/32-bit 800 MHz Multiple SC3850 DSP cores Multi accelerator platform engine for baseband (MAPLE-B) High-speed, high-bandwidth CLASS / Tri-level cache hierarchy CoreNet on-chip fabric Dual RISC core QUICC Engine subsystem Multiple e500 superscalar processor cores Hardware virtualization support On-demand application acceleration Industry-leading performance and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 10

11 Invest Development Tools Partner Invest in Optimizing Freescale Platforms Networking Software Strategy Own / control silicon-optimized software IP across all of our hardware devices and platforms Multi-core, PPC, DSP, accelerator Standalone base tools and run-time technologies Built around standard platforms Stacks VortiQa Applications Available throughout the ecosystem APIs/Libraries Partner for Vertical Solutions Complete solutions in select application spaces VortiQa networking apps s Schedulers Drivers/BSPs/HAL Silicon Leverage partners (ENEA, Mentor Graphics, Greenhills, QNX and others) elsewhere and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 11

12 Multicore Software Solution Model MC Applications: VortiQa security applications SMP And AMP models Component model for scalability Com Stacks/APIs: Silicon-optimized Open and scalable Linux: Control plane processing SMP support Light Weight Executive (LWE): Data path acceleration library Run to completion BSP: Silicon-optimized Full featured Open source HyperVisor: Security and separation Messaging among cores System-level event handling Debug support Multicore Applications Comm Stacks And Apis Linux (RT, 3p) Light Weight Exec (Data Path Acceleration) Optimized Board Support Package Virtualization/Hypervisor Cores Accelerators Peripherals and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 12

13 DSP Software Solution Model DSP Application Frameworks Reusable system frameworks Robust media delivery platform Well-defined APIs Components: Optimized for high channel densities WiMax, LTE L1 Support of numerous multimedia codecs Video - H264, SVC Voice - G.729AB, G.726, G.723.1, ilbc DSP RT: Lightweight and optimized Multicore enabled/support Real-time support DSP Application Framework DSP Components DSP RT (SD) DSP Drivers (Chip Support Library) Cores Accelerators Peripherals Drivers: Silicon-optimized Well-defined APIs and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 13

14 High End Multicore Software Architecture and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 14

15 QorIQ P4 Multicore Hardware Architecture and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 15

16 Multicore Software Architecture Models and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 16

17 Unsupervised AMP Multicore Approaches Support for allowing heterogeneous operating environments to execute concurrently on different cores in an SoC Cooperative approaches to sharing the resources of the device Supervised AMP Software hypervisor to provide a virtualized environment in which guests can run Spatial and (optional) temporal partitioning Hypervisor manages global resources (e.g. interrupt controller) and provides services Lightweight Executive API Provide model for programming (run-to-completion) simple AMP applications for the data path Virtualized guest of the hypervisor Migration to an encapsulated environment in user space of a host (Linux) and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 17

18 Unsupervised AMP and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 18

19 Unsupervised AMP General Approach Manage the partitioning of the system so that multiple es can boot safely Partition the peripherals so that they are segregated into different resource pools (each managed by a different ) Provide interpartition communication for applications and operating environments Paravirtualize I/O requests so that they can be delegated to the operating environment that owns the device Create standards for interoperability for heterogeneous es (boot, IPC) Freescale solution Linux AMP environment that supports multicore booting of the Linux and allows a guest to be booted on secondary cores Ecosystem support Wide support within the ecosystem for enablement of AMP solutions Adoption of standards is growing (e.g. epapr) Typically support vendor RT and Linux and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 19

20 Lightweight Executive and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 20

21 QorIQ P4080/4040 Multicore Programming Paradigm Support a variety of customer use cases Multiple operating systems utilized across cores on a single device Proprietary, third-party and open source multicore operating systems Symmetric Multi-Processing (SMP) and Asymmetric Multi-Processing (AMP), often running concurrently Often bare-metal, or engineered light-, used on forwarding/data plane cores Freescale has developed a reference development platform Freescale embedded reference Hypervisor Freescale boot standards, including u-boot Leverage open boot protocol and API standards (e.g. Power.org ) Freescale Light Weight Executive (LWE) for run-to-completion data plane processing Demonstrate performance and provide reference example for customers Services Linux Linux AMP Forwarding/ Data Plane Light Weight Executive AMP (Light RT) Control Plane 3 rd Party SMP L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache Power Architecture Core Power Architecture Core Power Architecture Core Power Architecture Core Power Architecture Core Power Architecture Core Power Architecture Core Power Architecture Core D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache D-Cache I-Cache and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 21

22 Light Weight Executive Concept Set of C-libraries needed to support data plane applications (C++ planned) Run-to-completion software model Processes do not pre-empt each other. The process must run to completion before other processes get a chance to run, as scheduled by the QMan (= implicit work scheduler) IRQs are supported, software responsibility to postpone actual processing using SWI or implement proper protection/sharing mechanism Device trees for LWE configuration Runs in supervisor state Dependency on Hypervisor Hypercalls used to access Hypervisor functionality Ingress Channel Egress Channel FQ FQ FQ FQ priority FQ Function FQ FQ FQ FQ priority and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 22

23 Lightweight Executive Lightweight Executive (LWE) Support Run-to-completion software model in Linux user space LWE (data plane) tasks run as user space applications No dependencies outside of Linux kernel (i.e. Hypervisor optional) Flexible association between software portals and LWE tasks Core/thread affine for maximum performance or floating for scalability Leverage Linux facilities and standard capabilities whenever possible Runtime support Isolation of cores running realtime tasks Linux Manage realtime constraints Standardize on distribution mechanism Freescale delivers optimized BSPs; partners deliver value-added distributions Single commercial/non-commercial distribution of Linux for Freescale Freescale focus on driving Linux features that enhance system performance, enforce partitioning and satisfy realtime constraints Realtime scheduling and synchronization Optimization of Linux networking stack and drivers for DPAA Improved latency and non-blocking operation: tickless, TLB miss reduction, etc. Enforce partitioning between LWE encapsulation environments (virtualization) and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 23

24 Supervised AMP (Hypervisor) and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 24

25 Freescale s Embedded Hypervisor A small hypervisor for embedded systems based on Power Architecture technology (architecture version 2.06) Initial version focuses on static partitioning CPUs, memory and I/O devices can be divided into logical partitions Partitions are isolated from one another Configuration is fixed until a reconfigure and system reboot Not addressing problem of multiple operating systems on 1 CPU Uses the Embedded Hypervisor feature in the QorIQ/e500mc which makes virtualization efficient Uses a combination of full-virtualization and para-virtualization which provides good performance and minimal changes to guest operating systems and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

26 Hypervisor Contrasts Freescale Hypervisor Implementation Traditional Hypervisor Implementation Guest Guest Guest Guest CPU CPU CPU Requirement: supervised AMP -- isolation, performance Implications: No more than one per core, has direct control of high-speed peripherals Requirement: high level of virtualization-- solves problem of under-utilized CPUs, plus isolation Implications: more than one per core, complexity, performance implications QorIQ P4080 hypervisor hardware assists in meeting both requirement sets and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

27 Hypervisor Architecture Overview Hypervisor partitions system spatially into separate domains Guests run in separate partitions Separation of domains enforced by virtualization capabilities of e500-mc core and P4080 SoC partition App App partition App App partition App App Linux RT LWE Hypervisor Multicore System Hardware CPU CPU CPU CPU Memory Memory Memory Shared Cache Interrupt Controller I/O I/O I/O I/O I/O IOMMU Memory and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 27

28 Operating System sees a virtual core plus Hypervisor services Hypervisor Features Virtual CPU (like e500mc minus hypervisor features) Services via hypercall Interrupt controller IOMMU Inter-partition doorbells Partition mangement Byte-channels Power management Error management HA failover Emulation (privileged instructions) Virtual CPU (e500vcpu) Hypervisor Services PIC Partition Mgmt Debug console Guest operating system Hypercalls Doorbells IOMMU Error Mgmt Debug stub Device tree Boot services (epapr) Byte Channels Mux Direct I/O Debug stub interface for debugging guest operating systems Device tree UART System hardware UART and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 28

29 Capabilities Copy data to/from another partition s memory (e.g. loading images) Starting, rebooting other partitions Notifications watchdog expiration, guest requests reboot, state change Linux partman command implements basic partition management features App App Partition Management partition partition partition Linux App App RT App App Legacy Hypervisor Multicore System Hardware CPU CPU CPU CPU Memory Memory Memory Shared Cache Interrupt Controller I/O I/O I/O I/O I/O Memory and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 29

30 Error Management Each partition has a guest event queue for partitionspecific errors Guest event queue Partition Partition Error mgr partition Global event queue A global error queue is owned by a partition designated to be an error manager Hypervisor The guests implement policies specific to their needs System Hardware MPIC CPU CPU CPU CPU Memory Memory Memory Memory and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 30

31 Debug of guest operating systems is supported using hypervisor-resident debug agents Transport over multiplexed serial interface Code Warrior and GDB supported Plug-in architecture for creating stubs Host Hypervisor System Hardware MUX Partition Partition stub stub stub CPU CPU CPU Memory Memory Debugging GDB GDB UART Memory MUX server GDB remote serial protocol and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 31

32 Byte-channel a hypercall-based character I/O channel Flexible endpoint configuration A physical UART on the QorIQ P4080 Another byte-channel endpoint A byte-channel to UART multiplexer A hypervisor debug stub The hypervisor console Partition Debug console UART Host Partition byte-channel Hypervisor Debug stub Byte-channel mux server Partition Byte-Channels Partition Bytechannel mux UART RS232 telnet telnet gdb (host) and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 32

33 Hypervisor Contrasts Freescale Hypervisor Implementation Traditional Hypervisor Implementation Guest Guest Guest Guest CPU CPU CPU Requirement: supervised AMP -- isolation, performance Implications: No more than one per core, has direct control of high-speed peripherals Requirement: high level of virtualization-- solves problem of under-utilized CPUs, plus isolation Implications: more than one per core, complexity, performance implications QorIQ P4080 hypervisor hardware assists in meeting both requirement sets and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

34 Virtualization Overview A push towards consolidation has led the need to run multiple operating systems on a single processor Guest Guest hardware Guest Unsupervised AMP A hypervisor: Establishes a virtual machine environment in which es run Enforces security Provides services Guest Guest hypervisor Guest Varying level of modifications may be needed hardware Supervised AMP and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

35 Freescale Virtualization Strategy Standards KVM Topaz 3 rd Party ISVs and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

36 power.org epapr (embedded Power Architecture Platform Requirements) 1.0 complete in 8/2008 Resource discovery (device tree) Multi-CPU boot Updated version, including virtualization extensions targeted for Q power.org Embedded Virtualization Committee Virtual CPU standard the behavior of instructions and registers in a virtual machine Paravirtualization & standard hcalls Guest standard interfaces Guest hypervisor hardware Standards Guest and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

37 Partitioning and Virtualization Partitioning Virtualization Topaz KVM Hardware consolidation Partitioned/dedicated resources, minimal sharing. Dedicated CPUs, I/O devices N virtual machines Shared resources Virtual I/O Highly virtualized environment and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

38 KVM (kernel virtual machine) Linux kernel is the hypervisor: KVM kernel module + Qemu Qemu provides virtual I/O services Allows fully virtualized platforms can run many more virtual machines than physical resources available Extensive virtual I/O support Established open source community Targets: e500v2, e500mc GNU Public License Guest Guest Linux / KVM / Qemu hardware Logical view Guest and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

39 Freescale Embedded Hypervisor (Topaz) An embedded hypervisor designed for Power architecture from the ground up Requires CPU with Power ISA 2.06 virtualization extensions Partitioning focus-- secure partitioning of the hardware resources of an SOC and board No scheduler Guest Guest Topaz Guest Hypervisor is minimally intrusive A moderate set of services interrupt controller, inter-partition interrupts, byte-channels, power management, active/standby/failover, error management hardware Targets: e500mc BSD License and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

40 Virtual Machines Under KVM and Topaz Architectural goal is to provide compatible virtual machines environments under both KVM and Topaz No guest modifications required Compliant with base epapr (device trees) ISA virtual CPU epapr para-virtualization extensions and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

41 Virtualization Roadmap Q KVM (e500v2): performance evaluation KVM (e500mc): initial port Q KVM (e500v2/e500mc): release with basic feature set, minimal direct assignment of memory/devices Topaz: SDK 2.3 Q KVM: direct device assignment, hugetlbfs, performance, extended vcpu features, MMU performance improvements e500mc/p4080 KVM: virtual network I/O via P4080 datapath, Topaz: performance, 64-bit, targeted feature development 2H 2011 (and beyond) KVM: SMP, error management, failover, power management, P4080 portal context switching e500mc KVM: 64-bit support Topaz: Processor roadmap support, targeted feature development and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc.

42 Multicore Software Development Kit (SDK) and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 42

43 P4080 SDK Architecture Today PME Compiler Linux User Space Partition Manager LWE Applications IPFwd IPSec Crypto FM Config Script LWE/Apps Image Pktwire Bridging FM Tester Other Linux Apps LWE CP Apps PME QM tester Linux Kernel Space LWE PME Driver QM Driver BM Driver FM Config Driver Legacy Drivers SEC Driver Mem Mgt BM Driver SEC Driver PME Driver Initialization Statistics Ethernet Driver QM Driver Byte Channel Atomic Calls Timer Inter Process Communication Hypervisor Virtual CPU Interrupt controller Error Mgmt Boot services IPI IOMMU Byte-channels Guest debugging Power Mgmt Partition Mgmt U-Boot Secure Boot Integration / Packaging GNU Tools and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 43

44 Linux User Space QorIQ DPAA Architecture Example Other Other Processes Processes USDPAA Application Can Use 1 to 8 Cores Each thread has a dedicated portal and is affined to a core, 1 thread per core USDPAA Application in User Space Process thread thread thread thread thread thread thread thread isolated cores C0 C1 C2 C3 C4 C5 C6 C7 QPortal QPortal QPortal QPortal QPortal QPortal QPortal QPortal BPortal BPortal BPortal BPortal BPortal BPortal BPortal BPortal Net Stack Kernel BMan / QMan Eth Driver Other Driver BQMan Drivers QPortal FMan Ethernet Ports 7 cores are isolated but 1 can run an USDPAA thread as well as other processes. BPortal Core 0 has portal for kernel use and standard Linux networking and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 44

45 Future High-end Multicore Software Architecture Linux User Space PME Tools pthreads DPAA Tools stats/state access Std commands/libs perfmon control debug support LWE Applications IPFwd/IPSEC Focused Performance Examples PME Crypto LWE Mem Mgt SEC Driver Initialization BM Driver PME Driver Statistics FM Enhanced CfgDriver System Configuration and Control QM Driver Atomic Calls Timer Linux Kernel scheduler control hugetlbfs UIO Drivers for LWE FM Basic Cfg Driver DPAA Ethernet Driver perfmon QM Driver BM Driver SEC Driver PME Driver Legacy Drivers Hypervisor Virtual CPU Interrupt controller Error Mgmt Boot services IPI IOMMU Byte-channels Guest debugging Power Mgmt Partition Mgmt U-Boot Secure Boot MG System Builder GNU Tools and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 45

46 Low End Multicore Software Architecture and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 46

47 Faster Packet Processing All flows are created equal But some flows can be put on a fast-track. Store flows requiring simple, deterministic processing in a cache. Recognize cached flows and process such packets in a separate highly optimized context Fast-Path. and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 47

48 Application Specific Fast-Path Advantage: 2x to 5x advantage over standard Linux 2-core scaling of > 1.8x Leverages hardware acceleration features effectively Compatible with hardware fastpath IP (QE) VortiQa Stack Soft Fast-Path Linux Drivers Control Plane Linux Net- Work Stack DPA Control Fast-Path API Customer Stack QE/FE Drivers Current scope (under definition): Feature: IPv4, NAPT, firewall, IPSec Platforms: P1020, P1021, P2020, P1022, P1010 Single fast-path for both Linux BSP and VortiQa VeTSEC DPAA CAAM QE/FE Roll-out strategy Q3-10: Demo release Q4-10: Reference solution Q1-Q4-11: IPv6, QoS, GTP and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 48

49 Full System Instrumentation and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 49

50 NSD Software and Enablement Technologies Advanced software development tools Full application visibility/control CodeWarrior Silicon-optimized software components Scalable robust software architectures Applications Comm Stacks and APIs App Profile Comm Events Run Time, Schedulers, Virtualization Run Time Events Compiler friendly cores Advanced debug IP Optimized Software Drivers/BSPs/HAL Cores Accelerators Peripherals Instrumentation IP Events, Trace and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 50

51 Profiling, Debug, and Instrumentation Libraries Instant access to debug hardware resources (no exposure to the specifics of hardware debug complex) Re-use your debug and profile solutions (seamless porting on QorIQ processors) Access hardware debug resources from target Applications running on target may configure and control hardware debug resources using API At least two scenarios may be implemented User applications may be instrumented to directly call API to get access to hardware resources Operating system may implement its debug services (e.g. profile, events, trace) by calling API Access hardware debug resources from host Traditional debug and profile tools running on host may use the library to Apply configurations on target Control the selected resources Retrieve profile/trace data from target The classic Debug Agent required by the host tools only needs to call API to get access to the required debug services User API driver User Application debug services Libraries Operating System Host Machine Configuration Parameters Profile/Trace Data P4080 User Application Debug Agent Libraries Operating System driver Cores Accelerators Peripherals Cores Accelerators Peripherals and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 51

52 Multicore Software Roadmap and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 52

53 Multicore Software Roadmap Jan Feb Mar Apr May Jun Jul Aug Sept Oct Nov Dec SDK Beta 2.0 P4080 silicon support DS Expedition board Linux + LWE guests 2010 Beta SDK Full testing on initial Rev 2 silicon samples Linux Ethernet jumbo frame support Critical bug fixes Hypervisor Error management services High availability/fault tolerant HV infrastructure notifications and shared device management 64-bit support SDK 2.2 : 36 bit addressing 10 GB XAUI dual mode support Offline port support enabled in FMD Congestion group demo 32 bit support for P bit support for P3041 Distributions: P4080DS SDK 2.2 (Open Source) Distribution Tools System Builder Linux DPAA to user space 64-bit kernel (P5020) Rapid IO driver HugeTLBfs Multicore Fast Path Driver optimization SDK QorIQ OpenEmbedded support UserSpace DPAA (Alpha) Huge TLB fs support Initial 64 bit kernel for P5020 RAID for P5020 SATA for P5020/3041 and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 53

54 Session Summary Freescale is focused on developing high-performance, full enablement multicore software components Freescale s multicore software strategy supports various customer application programming models Freescale s multicore software strategy supports both high performance and low cost multicore devices and VortiQa are trademarks of Freescale Semiconductor, Inc. All other product or service names are the property of their respective owners Freescale Semiconductor, Inc. 54

55

QorIQ P4080 Software Development Kit

QorIQ P4080 Software Development Kit July 2009 QorIQ P4080 Software Development Kit Kelly Johnson Applications Engineering service names are the property of their respective owners. Freescale Semiconductor, Inc. 2009. QorIQ P4080 Software

More information

KVM on Embedded Power Architecture Platforms

KVM on Embedded Power Architecture Platforms KVM on Embedded Power Architecture Platforms Stuart Yoder Software Architect, Freescale Semiconductor Agenda Background Freescale / Networking Embedded Systems Use Cases KVM on Embedded Power New requirements

More information

Enabling the Migration to an All-IP Network

Enabling the Migration to an All-IP Network July, 2009 Enabling the Migration to an All-IP Network Colin Cureton Product Marketer Enable next generation broadband networking systems to deliver a seamless user experience via processors offering:

More information

Freescale QorIQ Program Overview

Freescale QorIQ Program Overview August, 2009 Freescale QorIQ Program Overview Multicore processing view Jeffrey Ho Technical Marketing service names are the property of their respective owners. Freescale Semiconductor, Inc. 2009. We

More information

On-Chip Debugging of Multicore Systems

On-Chip Debugging of Multicore Systems Nov 1, 2008 On-Chip Debugging of Multicore Systems PN115 Jeffrey Ho AP Technical Marketing, Networking Systems Division of Freescale Semiconductor, Inc. All other product or service names are the property

More information

Challenges for Next Generation Networking AMP Series

Challenges for Next Generation Networking AMP Series 21 June 2011 Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, QorIQ, StarCore and Symphony are trademarks

More information

FTF-ENT-F0585. August 2011

FTF-ENT-F0585. August 2011 FTF-ENT-F0585 August 2011 Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, QorIQ, StarCore and Symphony

More information

RAD55xx Platform SoC. Dean Saridakis, Richard Berger, Joseph Marshall *** *** *** *** *** *** *** photo courtesy of NASA

RAD55xx Platform SoC. Dean Saridakis, Richard Berger, Joseph Marshall *** *** *** *** *** *** *** photo courtesy of NASA 1 RAD55xx Platform SoC Dean Saridakis, Richard Berger, Joseph Marshall *** *** *** *** *** *** *** photo courtesy of NASA 2 Agenda RAD55xx Platform SoC Introduction Processor Core / RAD750 Processor Heritage

More information

Next Generation Enterprise Solutions from ARM

Next Generation Enterprise Solutions from ARM Next Generation Enterprise Solutions from ARM Ian Forsyth Director Product Marketing Enterprise and Infrastructure Applications Processor Product Line Ian.forsyth@arm.com 1 Enterprise Trends IT is the

More information

Software Datapath Acceleration for Stateless Packet Processing

Software Datapath Acceleration for Stateless Packet Processing June 22, 2010 Software Datapath Acceleration for Stateless Packet Processing FTF-NET-F0817 Ravi Malhotra Software Architect Reg. U.S. Pat. & Tm. Off. BeeKit, BeeStack, CoreNet, the Energy Efficient Solutions

More information

EMC2. Prototyping and Benchmarking of PikeOS-based and XTRATUM-based systems on LEON4x4

EMC2. Prototyping and Benchmarking of PikeOS-based and XTRATUM-based systems on LEON4x4 EMC2 Prototyping and Benchmarking of PikeOS-based and XTRATUM-based systems on LEON4x4 Introduction Multi-core architectures will be adopted in the next generations of avionics and aerospace systems. Integrated

More information

PC Touchpad Appliance

PC Touchpad Appliance October 2013 Networks strained by use of smarter, bandwidth-hungry devices need: Multicore platforms performing more intelligently and securely Low-power, low-cost, easy-to-use equipment Scalable platform

More information

High-Performance, Highly Secure Networking for Industrial and IoT Applications

High-Performance, Highly Secure Networking for Industrial and IoT Applications High-Performance, Highly Secure Networking for Industrial and IoT Applications Table of Contents 2 Introduction 2 Communication Accelerators 3 Enterprise Network Lineage Features 5 Example applications

More information

An Introduction to the QorIQ Data Path Acceleration Architecture (DPAA) AN129

An Introduction to the QorIQ Data Path Acceleration Architecture (DPAA) AN129 July 14, 2009 An Introduction to the QorIQ Data Path Acceleration Architecture (DPAA) AN129 David Lapp Senior System Architect What is the Datapath Acceleration Architecture (DPAA)? The QorIQ DPAA is a

More information

VortiQa Software with Unified Threat Management for Service Provider Equipment

VortiQa Software with Unified Threat Management for Service Provider Equipment July 2009 VortiQa Software with Unified Threat Management for Service Provider Equipment Performance Optimization on QorIQ P4080 Multicore Processor Bharat Mota Director of Engineering, Software Products

More information

Migrating Unicore Network Packet Processing Applications to Multicore

Migrating Unicore Network Packet Processing Applications to Multicore August, 2009 Migrating Unicore Network Packet Processing Applications to Multicore Challenges and Techniques (1.0) Wilson Lo Architect, Network Software Division, NMG service names are the property of

More information

EUF-NET-T0862. QorIQ P Software Architecture for the P4080 Development System. Peter Van Ackeren Sr. Software FAE Freescale Semiconductor EMEA

EUF-NET-T0862. QorIQ P Software Architecture for the P4080 Development System. Peter Van Ackeren Sr. Software FAE Freescale Semiconductor EMEA May 11, 2010 QorIQ P4080 - Software Architecture for the P4080 Development System EUF-NET-T0862 Peter Van Ackeren Sr. Software FAE Freescale Semiconductor EMEA SDK Release 2.1 Beta for the P4080DS Development

More information

QorIQ Intelligent Network Interface Card (inic) Solution SDK v1.0 Update

QorIQ Intelligent Network Interface Card (inic) Solution SDK v1.0 Update QorIQ Intelligent Network Interface Card (inic) Solution SDK v1.0 Update APF-NET-T0658 Gary Chu A U G. 2 0 1 4 TM External Use The New Virtualized Network Cloud Cloud gaining momentum as the service platform

More information

An Intelligent NIC Design Xin Song

An Intelligent NIC Design Xin Song 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016) An Intelligent NIC Design Xin Song School of Electronic and Information Engineering Tianjin Vocational

More information

EDGE COMPUTING & IOT MAKING IT SECURE AND MANAGEABLE FRANCK ROUX MARKETING MANAGER, NXP JUNE PUBLIC

EDGE COMPUTING & IOT MAKING IT SECURE AND MANAGEABLE FRANCK ROUX MARKETING MANAGER, NXP JUNE PUBLIC EDGE COMPUTING & IOT MAKING IT SECURE AND MANAGEABLE FRANCK ROUX MARKETING MANAGER, NXP JUNE 6 2018 PUBLIC PUBLIC 2 Key concerns with IoT.. PUBLIC 3 Why Edge Computing? CLOUD Too far away Expensive connectivity

More information

QorIQ T4 Family of Processors. Our highest performance processor family. freescale.com

QorIQ T4 Family of Processors. Our highest performance processor family. freescale.com of Processors Our highest performance processor family freescale.com Application Brochure QorIQ Communications Platform: Scalable Processing Performance Overview The QorIQ communications processors portfolio

More information

30-Mar What's New in SDK V Highlights

30-Mar What's New in SDK V Highlights 30-Mar-2017 NXP Digital Networking is pleased to announce the release of QorIQ Linux SDK v2.0-1703 supporting our QorIQ family of processors. This release is one of a series of releases based on SDK v2.0

More information

Effectively describe, at a high level, NetComm Software for DPAA-based devices

Effectively describe, at a high level, NetComm Software for DPAA-based devices Aug. 31 st 2011 Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, QorIQ, StarCore and Symphony are trademarks

More information

Deflating the hype: Embedded Virtualization in 3 steps

Deflating the hype: Embedded Virtualization in 3 steps Deflating the hype: Embedded Virtualization in 3 steps Klaas van Gend MontaVista Software LLC For Embedded Linux Conference Europe 2010, Cambridge Agenda Why multicore made the topic more relevant Partitioning

More information

Leveraging Data Plane Acceleration Techniques on the QorIQ P4080 Processor

Leveraging Data Plane Acceleration Techniques on the QorIQ P4080 Processor June 2010 Leveraging Data Plane Acceleration Techniques on the QorIQ P4080 Processor For High-Performance Network Security Applications (v1.0) John Rekesh Software Architect, Software Products Division

More information

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC,

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, QorIQ, StarCore and Symphony are trademarks of Freescale

More information

Using a Hypervisor to Manage Multi-OS Systems Cory Bialowas, Product Manager

Using a Hypervisor to Manage Multi-OS Systems Cory Bialowas, Product Manager Using a Hypervisor to Manage Multi-OS Systems Cory Bialowas, Product Manager cory.bialowas@windriver.com Trends, Disruptions and Opportunity Wasn t life simple? Single-OS: SMP OS OS CPU Single Core Virtualization

More information

Simplifying the Development and Debug of 8572-Based SMP Embedded Systems. Wind River Workbench Development Tools

Simplifying the Development and Debug of 8572-Based SMP Embedded Systems. Wind River Workbench Development Tools Simplifying the Development and Debug of 8572-Based SMP Embedded Systems Wind River Workbench Development Tools Agenda Introducing multicore systems Debugging challenges of multicore systems Development

More information

Performance Analysis with Hybrid Simulation

Performance Analysis with Hybrid Simulation 6 th November, 2008 Performance Analysis with Hybrid Simulation PN111 Matthew Liong System and Application Engineer, NMG owners. Freescale Semiconductor, Inc. 2008. r2 Overview Hybrid Modeling Overview

More information

HKG : OpenAMP Introduction. Wendy Liang

HKG : OpenAMP Introduction. Wendy Liang HKG2018-411: OpenAMP Introduction Wendy Liang Agenda OpenAMP Projects Overview OpenAMP Libraries Changes in Progress Future Improvements OpenAMP Projects Overview Introduction With today s sophisticated

More information

Android OS and Power Architecture

Android OS and Power Architecture June 24, 2010 OS and Power Architecture FTF-NET-F0677 Phil Brownfield Software Product Manager, NMG Reg. U.S. Pat. & Tm. Off. BeeKit, BeeStack, CoreNet, the Energy Efficient Solutions logo, Flexis, MXC,

More information

$1 1. Cloud Wireless Enterprise. Smart Energy. Transportation. 50B Connected Nodes by 2020* $ Past Today Future

$1 1. Cloud Wireless Enterprise. Smart Energy. Transportation. 50B Connected Nodes by 2020* $ Past Today Future August 2013 1T 100B 50B Connected Nodes by 2020* Computers People Everything $100 1 2 3 1.0 2.0 3.0 10B Cloud Wireless Enterprise 1B 10M $1 1 Past Today Future 1990 2000 2010 2020 1 2 3 *Source Ericsson

More information

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC,

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, C-Ware, t he Energy Efficient Solutions logo, mobilegt, PowerQUICC, QorIQ, StarCore and Symphony are trademarks of Freescale

More information

A unified multicore programming model

A unified multicore programming model A unified multicore programming model Simplifying multicore migration By Sven Brehmer Abstract There are a number of different multicore architectures and programming models available, making it challenging

More information

Software Development Using Full System Simulation with Freescale QorIQ Communications Processors

Software Development Using Full System Simulation with Freescale QorIQ Communications Processors Patrick Keliher, Simics Field Application Engineer Software Development Using Full System Simulation with Freescale QorIQ Communications Processors 1 2013 Wind River. All Rights Reserved. Agenda Introduction

More information

KeyStone C665x Multicore SoC

KeyStone C665x Multicore SoC KeyStone Multicore SoC Architecture KeyStone C6655/57: Device Features C66x C6655: One C66x DSP Core at 1.0 or 1.25 GHz C6657: Two C66x DSP Cores at 0.85, 1.0, or 1.25 GHz Fixed and Floating Point Operations

More information

Performance Analysis on SMP and Non-SMP for Multicore Technology

Performance Analysis on SMP and Non-SMP for Multicore Technology June, 2010 Performance Analysis on SMP and Non-SMP for Multicore Technology FTF-ENT-F0697 TieFei Zang Principle Software Engineer Introduction Multicore in communication processor technology Dual cores

More information

Security and Performance Benefits of Virtualization

Security and Performance Benefits of Virtualization Security and Performance Benefits of Virtualization Felix Baum mentor.com/embedded Android is a trademark of Google Inc. Use of this trademark is subject to Google Permissions. Linux is the registered

More information

Differences Between P4080 Rev. 2 and P4080 Rev. 3

Differences Between P4080 Rev. 2 and P4080 Rev. 3 Freescale Semiconductor Application Note Document Number: AN4584 Rev. 1, 08/2014 Differences Between P4080 Rev. 2 and P4080 Rev. 3 About this document This document describes the differences between P4080

More information

Building blocks for 64-bit Systems Development of System IP in ARM

Building blocks for 64-bit Systems Development of System IP in ARM Building blocks for 64-bit Systems Development of System IP in ARM Research seminar @ University of York January 2015 Stuart Kenny stuart.kenny@arm.com 1 2 64-bit Mobile Devices The Mobile Consumer Expects

More information

RapidIO.org Update. Mar RapidIO.org 1

RapidIO.org Update. Mar RapidIO.org 1 RapidIO.org Update rickoco@rapidio.org Mar 2015 2015 RapidIO.org 1 Outline RapidIO Overview & Markets Data Center & HPC Communications Infrastructure Industrial Automation Military & Aerospace RapidIO.org

More information

Netronome NFP: Theory of Operation

Netronome NFP: Theory of Operation WHITE PAPER Netronome NFP: Theory of Operation TO ACHIEVE PERFORMANCE GOALS, A MULTI-CORE PROCESSOR NEEDS AN EFFICIENT DATA MOVEMENT ARCHITECTURE. CONTENTS 1. INTRODUCTION...1 2. ARCHITECTURE OVERVIEW...2

More information

Freescale Roadmap for Communications Processors Built on Power Architecture Technology

Freescale Roadmap for Communications Processors Built on Power Architecture Technology August, 2010 Freescale Roadmap for Communications Processors Built on Power Architecture Technology NET-F0425 Jeffrey Ho Technical Marketing Reg. U.S. Pat. & Tm. Off. BeeKit, BeeStack, CoreNet, the Energy

More information

Implementing debug. and trace access. through functional I/O. Alvin Yang Staff FAE. Arm Tech Symposia Arm Limited

Implementing debug. and trace access. through functional I/O. Alvin Yang Staff FAE. Arm Tech Symposia Arm Limited Implementing debug and trace access through functional I/O Alvin Yang Staff FAE Arm Tech Symposia 2017 Agenda Debug and trace access limitations A new approach Protocol based Bare metal vs mission mode

More information

Designing, developing, debugging ARM Cortex-A and Cortex-M heterogeneous multi-processor systems

Designing, developing, debugging ARM Cortex-A and Cortex-M heterogeneous multi-processor systems Designing, developing, debugging ARM and heterogeneous multi-processor systems Kinjal Dave Senior Product Manager, ARM ARM Tech Symposia India December 7 th 2016 Topics Introduction System design Software

More information

Multicore platform towards automotive safety challenges

Multicore platform towards automotive safety challenges Multicore platform towards automotive safety challenges Romuald NOZAHIC European Application Engineer mentor.com/automotive Android is a trademark of Google Inc. Use of this trademark is subject to Google

More information

Making Full use of Emerging ARM-based Heterogeneous Multicore SoCs

Making Full use of Emerging ARM-based Heterogeneous Multicore SoCs Making Full use of Emerging ARM-based Heterogeneous Multicore SoCs Felix Baum, Arvind Raghuraman To cite this version: Felix Baum, Arvind Raghuraman. Making Full use of Emerging ARM-based Heterogeneous

More information

PCD Graphs & PCD Processing Elements. Advanced Data Flows & DPAA Domains

PCD Graphs & PCD Processing Elements. Advanced Data Flows & DPAA Domains November 2013 As developers of Networking solutions over Multiple-core devices, having a suitable software base is crucial to your success and competiveness. Attending this session, will help you gain

More information

Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models. Jason Andrews

Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models. Jason Andrews Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models Jason Andrews Agenda System Performance Analysis IP Configuration System Creation Methodology: Create,

More information

Software Driven Verification at SoC Level. Perspec System Verifier Overview

Software Driven Verification at SoC Level. Perspec System Verifier Overview Software Driven Verification at SoC Level Perspec System Verifier Overview June 2015 IP to SoC hardware/software integration and verification flows Cadence methodology and focus Applications (Basic to

More information

Building High Performance, Power Efficient Cortex and Mali systems with ARM CoreLink. Robert Kaye

Building High Performance, Power Efficient Cortex and Mali systems with ARM CoreLink. Robert Kaye Building High Performance, Power Efficient Cortex and Mali systems with ARM CoreLink Robert Kaye 1 Agenda Once upon a time ARM designed systems Compute trends Bringing it all together with CoreLink 400

More information

Early Software Development Through Emulation for a Complex SoC

Early Software Development Through Emulation for a Complex SoC Early Software Development Through Emulation for a Complex SoC FTF-NET-F0204 Raghav U. Nayak Senior Validation Engineer A P R. 2 0 1 4 TM External Use Session Objectives After completing this session you

More information

Chapter 5. Introduction ARM Cortex series

Chapter 5. Introduction ARM Cortex series Chapter 5 Introduction ARM Cortex series 5.1 ARM Cortex series variants 5.2 ARM Cortex A series 5.3 ARM Cortex R series 5.4 ARM Cortex M series 5.5 Comparison of Cortex M series with 8/16 bit MCUs 51 5.1

More information

KeyStone C66x Multicore SoC Overview. Dec, 2011

KeyStone C66x Multicore SoC Overview. Dec, 2011 KeyStone C66x Multicore SoC Overview Dec, 011 Outline Multicore Challenge KeyStone Architecture Reminder About KeyStone Solution Challenge Before KeyStone Multicore performance degradation Lack of efficient

More information

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, ColdFire+, C- Ware, the Energy Efficient Solutions logo, Kinetis,

Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, ColdFire+, C- Ware, the Energy Efficient Solutions logo, Kinetis, May 2013 Freescale, the Freescale logo, AltiVec, C-5, CodeTEST, CodeWarrior, ColdFire, ColdFire+, C- Ware, the Energy Efficient Solutions logo, Kinetis, mobilegt, PEG, PowerQUICC, Processor Expert, QorIQ,

More information

The Next Steps in the Evolution of Embedded Processors

The Next Steps in the Evolution of Embedded Processors The Next Steps in the Evolution of Embedded Processors Terry Kim Staff FAE, ARM Korea ARM Tech Forum Singapore July 12 th 2017 Cortex-M Processors Serving Connected Applications Energy grid Automotive

More information

FCQ2 - P2020 QorIQ implementation

FCQ2 - P2020 QorIQ implementation Formation P2020 QorIQ implementation: This course covers NXP QorIQ P2010 and P2020 - Processeurs PowerPC: NXP Power CPUs FCQ2 - P2020 QorIQ implementation This course covers NXP QorIQ P2010 and P2020 Objectives

More information

Profiling and Debugging OpenCL Applications with ARM Development Tools. October 2014

Profiling and Debugging OpenCL Applications with ARM Development Tools. October 2014 Profiling and Debugging OpenCL Applications with ARM Development Tools October 2014 1 Agenda 1. Introduction to GPU Compute 2. ARM Development Solutions 3. Mali GPU Architecture 4. Using ARM DS-5 Streamline

More information

FTF-IND-F Multi-core processing for Safe and Secure Industrial applications Solutions from Freescale

FTF-IND-F Multi-core processing for Safe and Secure Industrial applications Solutions from Freescale FTF-IND-F0414 - Multi-core processing for Safe and Secure Industrial applications Solutions from Freescale Agenda Trends Power Architecture Multi-Core technology Software Components Case Studies and Summary

More information

Xen Project Status Ian Pratt 12/3/07 1

Xen Project Status Ian Pratt 12/3/07 1 Xen Project Status Ian Pratt 12/3/07 1 Project Status xen.org and the Xen Advisory Board Xen project mission Ubiquitous virtualization Realizing Xen s architectural advantages From servers to clients Interoperability

More information

NI Linux Real-Time. Fanie Coetzer. Field Sales Engineer SA North. ni.com

NI Linux Real-Time. Fanie Coetzer. Field Sales Engineer SA North. ni.com 1 NI Linux Real-Time Fanie Coetzer Field Sales Engineer SA North Agenda 1. Hardware Overview 2. Introduction to NI Linux Real-Time OS Background & Core Technology Filesystem Connectivity and Security 3.

More information

OCP Engineering Workshop - Telco

OCP Engineering Workshop - Telco OCP Engineering Workshop - Telco Low Latency Mobile Edge Computing Trevor Hiatt Product Management, IDT IDT Company Overview Founded 1980 Workforce Approximately 1,800 employees Headquarters San Jose,

More information

Application Brief. QorIQ P2040/P2041, P3 and P5 Series. High-performance multicore processors. freescale.com/qoriq

Application Brief. QorIQ P2040/P2041, P3 and P5 Series. High-performance multicore processors. freescale.com/qoriq QorIQ P2040/P2041, P3 and P5 Series High-performance multicore processors Title here Secondary Title here QorIQ Communications Platform: Scalable Processing Performance Ideal for networking infrastructure,

More information

SmartNICs: Giving Rise To Smarter Offload at The Edge and In The Data Center

SmartNICs: Giving Rise To Smarter Offload at The Edge and In The Data Center SmartNICs: Giving Rise To Smarter Offload at The Edge and In The Data Center Jeff Defilippi Senior Product Manager Arm #Arm Tech Symposia The Cloud to Edge Infrastructure Foundation for a World of 1T Intelligent

More information

QorIQ and QorIQ Qonverge Multicore SoCs and PowerQUICC Processors

QorIQ and QorIQ Qonverge Multicore SoCs and PowerQUICC Processors QorIQ and QorIQ Qonverge Multicore SoCs and QUICC Processors Selector Guide Designed for Performance. Built to Connect. freescale.com/qoriq Selector Guide Processor Selector Guide QorIQ Number Speed (MHz)

More information

Live Demo: A New Hardware- Based Approach to Secure the Internet of Things

Live Demo: A New Hardware- Based Approach to Secure the Internet of Things SESSION ID: CCS-W04 Live Demo: A New Hardware- Based Approach to Secure the Internet of Things Cesare Garlati Chief Security Strategist prpl Foundation @CesareGarlati Securing the Internet of (broken)

More information

Tile Processor (TILEPro64)

Tile Processor (TILEPro64) Tile Processor Case Study of Contemporary Multicore Fall 2010 Agarwal 6.173 1 Tile Processor (TILEPro64) Performance # of cores On-chip cache (MB) Cache coherency Operations (16/32-bit BOPS) On chip bandwidth

More information

Virtualization, Xen and Denali

Virtualization, Xen and Denali Virtualization, Xen and Denali Susmit Shannigrahi November 9, 2011 Susmit Shannigrahi () Virtualization, Xen and Denali November 9, 2011 1 / 70 Introduction Virtualization is the technology to allow two

More information

SIERRAWARE SIERRATEE FOR MIPS OMNISHIELD

SIERRAWARE SIERRATEE FOR MIPS OMNISHIELD SIERRAWARE SIERRATEE FOR MIPS OMNISHIELD Introduction SierraTEE for MIPS OmniShield is a Global Platform compliant Trusted Execution Environment (TEE) designed for devices based on Imagination Technologies'

More information

Zatara Series ARM ASSP High-Performance 32-bit Solution for Secure Transactions

Zatara Series ARM ASSP High-Performance 32-bit Solution for Secure Transactions 1 ARM-BASED ASSP FOR SECURE TRANSACTIONS ZATARA SERIES 32-BIT ARM ASSP PB022106-1008 ZATARA SERIES ADVANTAGE SINGLE-CHIP SOLUTION BEST FEATURE SET IN POS PCIPED PRE-CERTIFIED EMV L1 CERTIFIED TOTAL SOLUTION

More information

Intelop. *As new IP blocks become available, please contact the factory for the latest updated info.

Intelop. *As new IP blocks become available, please contact the factory for the latest updated info. A FPGA based development platform as part of an EDK is available to target intelop provided IPs or other standard IPs. The platform with Virtex-4 FX12 Evaluation Kit provides a complete hardware environment

More information

Multicore Challenges and Choices: Deciding Which Solution Is Right for You

Multicore Challenges and Choices: Deciding Which Solution Is Right for You Multicore Challenges and Choices: Deciding Which Solution Is Right for You Tomas Evensen Chief Technology Officer, Wind River Table of Contents Executive Summary... 1 Business and Technology Trends...

More information

HSA foundation! Advanced Topics on Heterogeneous System Architectures. Politecnico di Milano! Seminar Room A. Alario! 23 November, 2015!

HSA foundation! Advanced Topics on Heterogeneous System Architectures. Politecnico di Milano! Seminar Room A. Alario! 23 November, 2015! Advanced Topics on Heterogeneous System Architectures HSA foundation! Politecnico di Milano! Seminar Room A. Alario! 23 November, 2015! Antonio R. Miele! Marco D. Santambrogio! Politecnico di Milano! 2

More information

Projects on the Intel Single-chip Cloud Computer (SCC)

Projects on the Intel Single-chip Cloud Computer (SCC) Projects on the Intel Single-chip Cloud Computer (SCC) Jan-Arne Sobania Dr. Peter Tröger Prof. Dr. Andreas Polze Operating Systems and Middleware Group Hasso Plattner Institute for Software Systems Engineering

More information

Re-architecting Virtualization in Heterogeneous Multicore Systems

Re-architecting Virtualization in Heterogeneous Multicore Systems Re-architecting Virtualization in Heterogeneous Multicore Systems Himanshu Raj, Sanjay Kumar, Vishakha Gupta, Gregory Diamos, Nawaf Alamoosa, Ada Gavrilovska, Karsten Schwan, Sudhakar Yalamanchili College

More information

An Ultra High Performance Scalable DSP Family for Multimedia. Hot Chips 17 August 2005 Stanford, CA Erik Machnicki

An Ultra High Performance Scalable DSP Family for Multimedia. Hot Chips 17 August 2005 Stanford, CA Erik Machnicki An Ultra High Performance Scalable DSP Family for Multimedia Hot Chips 17 August 2005 Stanford, CA Erik Machnicki Media Processing Challenges Increasing performance requirements Need for flexibility &

More information

Real-Time Systems and Intel take industrial embedded systems to the next level

Real-Time Systems and Intel take industrial embedded systems to the next level Solution brief Industrial IoT (IIoT) Embedded Software and Systems Real-Time Systems and Intel take industrial embedded systems to the next level Innovative hypervisor and partitioning software increases

More information

HSA Foundation! Advanced Topics on Heterogeneous System Architectures. Politecnico di Milano! Seminar Room (Bld 20)! 15 December, 2017!

HSA Foundation! Advanced Topics on Heterogeneous System Architectures. Politecnico di Milano! Seminar Room (Bld 20)! 15 December, 2017! Advanced Topics on Heterogeneous System Architectures HSA Foundation! Politecnico di Milano! Seminar Room (Bld 20)! 15 December, 2017! Antonio R. Miele! Marco D. Santambrogio! Politecnico di Milano! 2

More information

Part 1: Introduction to device drivers Part 2: Overview of research on device driver reliability Part 3: Device drivers research at ERTOS

Part 1: Introduction to device drivers Part 2: Overview of research on device driver reliability Part 3: Device drivers research at ERTOS Some statistics 70% of OS code is in device s 3,448,000 out of 4,997,000 loc in Linux 2.6.27 A typical Linux laptop runs ~240,000 lines of kernel code, including ~72,000 loc in 36 different device s s

More information

vnetwork Future Direction Howie Xu, VMware R&D November 4, 2008

vnetwork Future Direction Howie Xu, VMware R&D November 4, 2008 vnetwork Future Direction Howie Xu, VMware R&D November 4, 2008 Virtual Datacenter OS from VMware Infrastructure vservices and Cloud vservices Existing New - roadmap Virtual Datacenter OS from VMware Agenda

More information

System Impact of Distributed Multicore Systems December 5th 2012

System Impact of Distributed Multicore Systems December 5th 2012 System Impact of Distributed Multicore Systems December 5th 2012 Software Systems Division & Data Systems Division Final Presentation Days Mathieu Patte (Astrium Satellites) Alfons Crespo (UPV) Outline

More information

Outline Background Jaluna-1 Presentation Jaluna-2 Presentation Overview Use Cases Architecture Features Copyright Jaluna SA. All rights reserved

Outline Background Jaluna-1 Presentation Jaluna-2 Presentation Overview Use Cases Architecture Features Copyright Jaluna SA. All rights reserved C5 Micro-Kernel: Real-Time Services for Embedded and Linux Systems Copyright 2003- Jaluna SA. All rights reserved. JL/TR-03-31.0.1 1 Outline Background Jaluna-1 Presentation Jaluna-2 Presentation Overview

More information

Designing Security & Trust into Connected Devices

Designing Security & Trust into Connected Devices Designing Security & Trust into Connected Devices Eric Wang Sr. Technical Marketing Manager Tech Symposia China 2015 November 2015 Agenda Introduction Security Foundations on ARM Cortex -M Security Foundations

More information

Multiprocessor Scheduling. Multiprocessor Scheduling

Multiprocessor Scheduling. Multiprocessor Scheduling Multiprocessor Scheduling Will consider only shared memory multiprocessor or multi-core CPU Salient features: One or more caches: cache affinity is important Semaphores/locks typically implemented as spin-locks:

More information

FPQ9 - MPC8360E implementation

FPQ9 - MPC8360E implementation Training MPC8360E implementation: This course covers PowerQUICC II Pro MPC8360E - PowerPC processors: NXP Power CPUs FPQ9 - MPC8360E implementation This course covers PowerQUICC II Pro MPC8360E Objectives

More information

CCIX: a new coherent multichip interconnect for accelerated use cases

CCIX: a new coherent multichip interconnect for accelerated use cases : a new coherent multichip interconnect for accelerated use cases Akira Shimizu Senior Manager, Operator relations Arm 2017 Arm Limited Arm 2017 Interconnects for different scale SoC interconnect. Connectivity

More information

RAMP-White / FAST-MP

RAMP-White / FAST-MP RAMP-White / FAST-MP Hari Angepat and Derek Chiou Electrical and Computer Engineering University of Texas at Austin Supported in part by DOE, NSF, SRC,Bluespec, Intel, Xilinx, IBM, and Freescale RAMP-White

More information

A Closer Look at the Epiphany IV 28nm 64 core Coprocessor. Andreas Olofsson PEGPUM 2013

A Closer Look at the Epiphany IV 28nm 64 core Coprocessor. Andreas Olofsson PEGPUM 2013 A Closer Look at the Epiphany IV 28nm 64 core Coprocessor Andreas Olofsson PEGPUM 2013 1 Adapteva Achieves 3 World Firsts 1. First processor company to reach 50 GFLOPS/W 3. First semiconductor company

More information

Virtual Leverage: Server Consolidation in Open Source Environments. Margaret Lewis Commercial Software Strategist AMD

Virtual Leverage: Server Consolidation in Open Source Environments. Margaret Lewis Commercial Software Strategist AMD Virtual Leverage: Server Consolidation in Open Source Environments Margaret Lewis Commercial Software Strategist AMD What Is Virtualization? Abstraction of Hardware Components Virtual Memory Virtual Volume

More information

RISC-V based core as a soft processor in FPGAs Chowdhary Musunuri Sr. Director, Solutions & Applications Microsemi

RISC-V based core as a soft processor in FPGAs Chowdhary Musunuri Sr. Director, Solutions & Applications Microsemi Power Matters. TM RISC-V based core as a soft processor in FPGAs Chowdhary Musunuri Sr. Director, Solutions & Applications Microsemi chowdhary.musunuri@microsemi.com RIC217 1 Agenda A brief introduction

More information

Real Safe Times in the Jailhouse Hypervisor Unrestricted Siemens AG All rights reserved

Real Safe Times in the Jailhouse Hypervisor Unrestricted Siemens AG All rights reserved Siemens Corporate Technology Real Safe Times in the Jailhouse Hypervisor Real Safe Times in the Jailhouse Hypervisor Agenda Jailhouse introduction Safe isolation Architecture support Jailhouse application

More information

FTF-CON-F0403. An Introduction to Heterogeneous Multiprocessing (ARM Cortex -A + Cortex- M) on Next-Generation i.mx Applications Processors

FTF-CON-F0403. An Introduction to Heterogeneous Multiprocessing (ARM Cortex -A + Cortex- M) on Next-Generation i.mx Applications Processors An Introduction to Heterogeneous Multiprocessing (ARM Cortex -A + Cortex- M) on Next-Generation i.mx Applications Processors FTF-CON-F0403 Glen Wienecke i.mx Systems Architect A P R. 2 0 1 4 TM External

More information

Messaging Overview. Introduction. Gen-Z Messaging

Messaging Overview. Introduction. Gen-Z Messaging Page 1 of 6 Messaging Overview Introduction Gen-Z is a new data access technology that not only enhances memory and data storage solutions, but also provides a framework for both optimized and traditional

More information

I/O and virtualization

I/O and virtualization I/O and virtualization CSE-C3200 Operating systems Autumn 2015 (I), Lecture 8 Vesa Hirvisalo Today I/O management Control of I/O Data transfers, DMA (Direct Memory Access) Buffering Single buffering Double

More information

QCVS Frame Distributor Wizard User Guide

QCVS Frame Distributor Wizard User Guide NXP Semiconductors Document Number: QCVS_FDW_User_Guide User's Guide Rev. 4.x, 02/2017 QCVS Frame Distributor Wizard User Guide Contents Contents Chapter 1 Frame Distributor Wizard...3 1.1 Introduction...

More information

Practical Hardware Debugging: Quick Notes On How to Simulate Altera s Nios II Multiprocessor Systems Using Mentor Graphics ModelSim

Practical Hardware Debugging: Quick Notes On How to Simulate Altera s Nios II Multiprocessor Systems Using Mentor Graphics ModelSim Practical Hardware Debugging: Quick Notes On How to Simulate Altera s Nios II Multiprocessor Systems Using Mentor Graphics ModelSim Ray Duran Staff Design Specialist FAE, Altera Corporation 408-544-7937

More information

LINUX CONTAINERS. Where Enterprise Meets Embedded Operating Environments WHEN IT MATTERS, IT RUNS ON WIND RIVER

LINUX CONTAINERS. Where Enterprise Meets Embedded Operating Environments WHEN IT MATTERS, IT RUNS ON WIND RIVER Where Enterprise Meets Embedded Operating Environments WHEN IT MATTERS, IT RUNS ON WIND RIVER EXECUTIVE SUMMARY Flexible and connected platforms are core components in leading computing fields, including

More information

The Nios II Family of Configurable Soft-core Processors

The Nios II Family of Configurable Soft-core Processors The Nios II Family of Configurable Soft-core Processors James Ball August 16, 2005 2005 Altera Corporation Agenda Nios II Introduction Configuring your CPU FPGA vs. ASIC CPU Design Instruction Set Architecture

More information

RapidIO.org Update.

RapidIO.org Update. RapidIO.org Update rickoco@rapidio.org June 2015 2015 RapidIO.org 1 Outline RapidIO Overview Benefits Interconnect Comparison Ecosystem System Challenges RapidIO Markets Data Center & HPC Communications

More information

Heterogeneous Software Architecture with OpenAMP

Heterogeneous Software Architecture with OpenAMP Heterogeneous Software Architecture with OpenAMP Shaun Purvis, Xilinx Agenda Heterogeneous SoCs Linux and OpenAMP OpenAMP for HSA Heterogeneous SoCs A System-on-Chip that integrates multiple processor

More information