Evaluation of AMD EPYC

Total Page:16

File Type:pdf, Size:1020Kb

Evaluation of AMD EPYC Evaluation of AMD EPYC Chris Hollowell <[email protected]> HEPiX Fall 2018, PIC Spain What is EPYC? EPYC is a new line of x86_64 server CPUs from AMD based on their Zen microarchitecture Same microarchitecture used in their Ryzen desktop processors Released June 2017 First new high performance series of server CPUs offered by AMD since 2012 Last were Piledriver-based Opterons Steamroller Opteron products cancelled AMD had focused on low power server CPUs instead x86_64 Jaguar APUs ARM-based Opteron A CPUs Many vendors are now offering EPYC-based servers, including Dell, HP and Supermicro 2 How Does EPYC Differ From Skylake-SP? Intel’s Skylake-SP Xeon x86_64 server CPU line also released in 2017 Both Skylake-SP and EPYC CPU dies manufactured using 14 nm process Skylake-SP introduced AVX512 vector instruction support in Xeon AVX512 not available in EPYC HS06 official GCC compilation options exclude autovectorization Stock SL6/7 GCC doesn’t support AVX512 Support added in GCC 4.9+ Not heavily used (yet) in HEP/NP offline computing Both have models supporting 2666 MHz DDR4 memory Skylake-SP 6 memory channels per processor 3 TB (2-socket system, extended memory models) EPYC 8 memory channels per processor 4 TB (2-socket system) 3 How Does EPYC Differ From Skylake (Cont)? Some Skylake-SP processors include built in Omnipath networking, or FPGA coprocessors Not available in EPYC Both Skylake-SP and EPYC have SMT (HT) support 2 logical cores per physical core (absent in some Xeon Bronze models) Maximum core count (per socket) Skylake-SP – 28 physical / 56 logical (Xeon Platinum 8180M) EPYC – 32 physical / 64 logical (EPYC 7601) Maximum socket count Skylake-SP – 8 (Xeon Platinum) EPYC – 2 Processor Inteconnect Skylake-SP – UltraPath Interconnect (UPI) EYPC – Infinity Fabric (IF) PCIe lanes (2-socket system) Skylake-SP – 96 EPYC – 128 (some used by SoC functionality) Same number available in single socket configuration 4 EPYC: MCM/SoC Design EPYC utilizes an SoC design Many functions normally found in motherboard chipset on the CPU SATA controllers USB controllers etc. Each EPYC processor consists of four CPU dies, interconnected via Infinity Fabric Multi-Chip Module (MCM) architecture ”CPU Complexes” (CCX) Each CCX attached to its own memory 2 memory channels per CCX All Skylake-SP cores are on a single die AMD claims MCM results in a cost reduction by improving yields Believed to scale better than monolithic die approach as core counts continue to increase Drawback: higher memory latency for non-NUMA-aware applications 5 EPYC: MCM/SoC Design (Cont.) # lscpu # lscpu Architecture: x86_64 Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Byte Order: Little Endian CPU(s): 64 CPU(s): 72 On-line CPU(s) list: 0-63 On-line CPU(s) list: 0-71 Thread(s) per core: 2 Thread(s) per core: 2 Core(s) per socket: 16 Core(s) per socket: 18 Socket(s): 2 Socket(s): 2 NUMA node(s): 8 NUMA node(s): 2 Vendor ID: AuthenticAMD Vendor ID: GenuineIntel CPU family: 23 CPU family: 6 Model: 1 Model: 85 Model name: AMD EPYC 7351 16-Core Model name: Intel(R) Xeon(R) Gold 6150 CPU @ Processor 2.70GHz Stepping: 2 Stepping: 4 CPU MHz: 2400.000 CPU MHz: 2700.000 CPU max MHz: 2400.0000 BogoMIPS: 5404.41 CPU min MHz: 1200.0000 Virtualization: VT-x BogoMIPS: 4799.41 L1d cache: 32K Virtualization: AMD-V L1i cache: 32K L1d cache: 32K L2 cache: 1024K L1i cache: 64K L3 cache: 25344K L2 cache: 512K NUMA node0 CPU(s): L3 cache: 8192K 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38, NUMA node0 CPU(s): 0-3,32-35 40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70 NUMA node1 CPU(s): 4-7,36-39 NUMA node1 CPU(s): NUMA node2 CPU(s): 8-11,40-43 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39, NUMA node3 CPU(s): 12-15,44-47 41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71 NUMA node4 CPU(s): 16-19,48-51 NUMA node5 CPU(s): 20-23,52-55 NUMA node6 CPU(s): 24-27,56-59 NUMA node7 CPU(s): 28-31,60-63 EPYC vs Skylake-SP (SNC Disabled) NUMA Configuration 6 Socket LGA 3647 & SP3 Skylake SP – Socket LGA 3647 EPYC – Socket SP3 Both CPUs/sockets are quite large Visible quadrants in the SP3 socket for the four CPU complexes in the EPYC processor 7 Skylake and EPYC Model Lineup Comparison Model Base Frequency Cores SMT TDP Memory Retail Xeon Bronze 3104 1.7 GHz (no turbo) 6 No 85W 2133 MHz DDR4 $213 Xeon Silver 4110 2.1 GHz 8 Yes 85W 2400 MHz DDR4 $501 Xeon Gold 5115 2.4 GHz 10 Yes 85W 2666 MHz DDR4 $1,221 Xeon Gold 6130 2.1 GHz 16 Yes 125W 2666 MHz DDR4 $1,900 Xeon Gold 6136 3.0 GHz 12 Yes 150W 2666 MHz DDR4 $2,460 Xeon Gold 6148 2.4 GHz 20 Yes 150W 2666 MHz DDR4 $3,072 Xeon Gold 6150 2.7 GHz 18 Yes 165W 2666 MHz DDR4 $3,358 Xeon Platinum 8170 2.1 GHz 28 Yes 165W 2666 MHz DDR4 $7,405 Xeon Platinum 8180M 2.5 GHz 28 Yes 205W 2666 MHz DDR4 $13,011 EPYC 7251 2.1 GHz 8 Yes 120W 2400 MHz DDR4 $475 EPYC 7351 2.4 GHz 16 Yes 170W 2666 MHz DDR4 $1,110 Uniprocessor (P) - $750 EPYC 7401 2.0 GHz 24 Yes 170W 2666 MHz DDR4 $1,850 Uniprocessor (P) - $1,075 EPYC 7451 2.3 GHz 24 Yes 180W 2666 MHz DDR4 $2,400 EPYC 7551 2.0 GHz 32 Yes 180W 2666 MHz DDR4 $3,400 EPYC 7601 2.2 GHz 32 Yes 180W 2666 MHz DDR4 $4,200 8 EPYC vs Skylake-SP: HEP/NP Performance Benchmarks HEPSPEC06 “all_cpp” subset of SPEC-CPU2006 run in parallel CERN Cloud Benchmark Suite Various benchmarks, run in parallel DB12 Whetstone ATLAS KV Unless noted, memory configured to utilize all 8 channels per CPU on EPYC, and 6 channels per CPU for Skylake-SP, with at least 2 GB RAM/logical core ~11% HS06 performance degradation seen for EPYC 7441 when only populating half of the memory channels All 2666 MHz DDR4 Noted dual rank (DR) DIMMs downclocked to 2400 MHz for EPYC All run under SL/CentOS/RHEL 7 SMT/Hyperthreading enabled, unless otherwise indicated Systems are dual CPU, unless noted 9 10 EPYC [email protected] [Uniprocessor - 24threads] EPYC [email protected] [Uniprocessor - 48threads] EPYC [email protected] [32 threads] EPYC [email protected] [64 threads] EPYC [email protected] [48 threads] DDR-2400 EPYC [email protected] [96 threads] DDR-2400 EPYC [email protected] [64 threads] EPYC [email protected] [128 threads] EPYC [email protected] [64 threads] DDR4-2400 EPYC [email protected] [128 threads] DDR4-2400 EPYC 7601 SMT 1296 EPYC 7601 1078 EPYC 7551 SMT 1148 EPYC 7551 872 EPYC 7451 SMT 1101 CPU EPYC 7451 883 EPYC 7351 SMT 780 EPYC 7351 541 EPYC 7401P SMT 489 EPYC 7401P 368 25%+ 25%+ HS06 performance improvement with SMT (“hyperthreading”) enabled 0 200 400 600 800 1000 1200 1400 EPYC HEPSPEC06: SMT Off vs On Off EPYC HEPSPEC06: SMT HS06 11 XeonGold [email protected] GHz [40 threads]+ XeonGold [email protected] GHz [64 threads] XeonGold [email protected] GHz [48 threads] XeonGold [email protected] GHz [80 threads] XeonGold [email protected] GHz [72 threads] [email protected] XeonPlatinum GHz [104 threads] * EPYC [email protected] [Uniprocessor - 48threads] EPYC [email protected] [64 threads] EPYC [email protected] [96 threads]DDR-2400 EPYC [email protected] [128 threads] EPYC [email protected] [128 threads] DDR4-2400 + = System using only 3 memory channels per CPU per channels memory 3 only using System = + CERN by reported * Value = EPYC 7601 1296 EPYC 7551 1148 EPYC 7451 1101 EPYC 7351 780 EPYC 7401P 489 Xeon Platinum 8170 1261 CPU Xeon Gold 6150 1035 Xeon Gold 6148 1068 Xeon Gold 6136 790 Xeon Gold 6130 729 Xeon Gold 5115 394 0 200 400 600 800 1000 1200 1400 EPYC vs Skylake-SP: HEPSPEC06 HS06 EPYC vs Skylake: HEPSPEC06 (Cont.) Larger values are better Similar maximum HS06 (~1,275) performance for the models tested Data for highest level EPYC (7601), but not highest model Skylake-SP (8180M) Can assume Xeon Skylake 8180M would perform better than the 8170 value listed Same number of cores/threads as 8170, but higher clock speed 2.5 GHz vs 2.1 GHz Mid-range model HS06 performance also similar ~700 HS06 - ~1100 HS06 TDP somewhat higher for EPYC CPUs vs Xeon Gold, in general 165 W max Xeon Gold, vs 180 W max EPYC Can likely expect EPYC to use a bit more power as a result 12 13 Xeon Gold [email protected] [40 threads] + Xeon Gold [email protected] [72 threads] EPYC [email protected] [64 threads] EPYC [email protected] [128 threads] + = System using only 3 memory channels per CPU per channels memory 3 only using System = + EPYC 7551 120 EPYC 7351 67 Xeon Gold 6150 65 Events/Sec Xeon Gold 5115 15 ATLAS KV(aggregate) ATLAS EPYC 7551 361 EPYC 7351 210 BWIPS Xeon Gold 6150 262 Xeon Gold 5115 114 Whetstone (aggregate) Whetstone EPYC 7551 1256 EPYC 7351 733 Xeon Gold 6150 998 Dirac HS06 Dirac Est.
Recommended publications
  • Effective Virtual CPU Configuration with QEMU and Libvirt
    Effective Virtual CPU Configuration with QEMU and libvirt Kashyap Chamarthy <[email protected]> Open Source Summit Edinburgh, 2018 1 / 38 Timeline of recent CPU flaws, 2018 (a) Jan 03 • Spectre v1: Bounds Check Bypass Jan 03 • Spectre v2: Branch Target Injection Jan 03 • Meltdown: Rogue Data Cache Load May 21 • Spectre-NG: Speculative Store Bypass Jun 21 • TLBleed: Side-channel attack over shared TLBs 2 / 38 Timeline of recent CPU flaws, 2018 (b) Jun 29 • NetSpectre: Side-channel attack over local network Jul 10 • Spectre-NG: Bounds Check Bypass Store Aug 14 • L1TF: "L1 Terminal Fault" ... • ? 3 / 38 Related talks in the ‘References’ section Out of scope: Internals of various side-channel attacks How to exploit Meltdown & Spectre variants Details of performance implications What this talk is not about 4 / 38 Related talks in the ‘References’ section What this talk is not about Out of scope: Internals of various side-channel attacks How to exploit Meltdown & Spectre variants Details of performance implications 4 / 38 What this talk is not about Out of scope: Internals of various side-channel attacks How to exploit Meltdown & Spectre variants Details of performance implications Related talks in the ‘References’ section 4 / 38 OpenStack, et al. libguestfs Virt Driver (guestfish) libvirtd QMP QMP QEMU QEMU VM1 VM2 Custom Disk1 Disk2 Appliance ioctl() KVM-based virtualization components Linux with KVM 5 / 38 OpenStack, et al. libguestfs Virt Driver (guestfish) libvirtd QMP QMP Custom Appliance KVM-based virtualization components QEMU QEMU VM1 VM2 Disk1 Disk2 ioctl() Linux with KVM 5 / 38 OpenStack, et al. libguestfs Virt Driver (guestfish) Custom Appliance KVM-based virtualization components libvirtd QMP QMP QEMU QEMU VM1 VM2 Disk1 Disk2 ioctl() Linux with KVM 5 / 38 libguestfs (guestfish) Custom Appliance KVM-based virtualization components OpenStack, et al.
    [Show full text]
  • Microprocessor
    MICROPROCESSOR www.MPRonline.com THE REPORTINSIDER’S GUIDE TO MICROPROCESSOR HARDWARE EEMBC’S MULTIBENCH ARRIVES CPU Benchmarks: Not Just For ‘Benchmarketing’ Any More By Tom R. Halfhill {7/28/08-01} Imagine a world without measurements or statistical comparisons. Baseball fans wouldn’t fail to notice that a .300 hitter is better than a .100 hitter. But would they welcome a trade that sends the .300 hitter to Cleveland for three .100 hitters? System designers and software developers face similar quandaries when making trade-offs EEMBC’s role has evolved over the years, and Multi- with multicore processors. Even if a dual-core processor Bench is another step. Originally, EEMBC was conceived as an appears to be better than a single-core processor, how much independent entity that would create benchmark suites and better is it? Twice as good? Would a quad-core processor be certify the scores for accuracy, allowing vendors and customers four times better? Are more cores worth the additional cost, to make valid comparisons among embedded microproces- design complexity, power consumption, and programming sors. (See MPR 5/1/00-02, “EEMBC Releases First Bench- difficulty? marks.”) EEMBC still serves that role. But, as it turns out, most The Embedded Microprocessor Benchmark Consor- EEMBC members don’t openly publish their scores. Instead, tium (EEMBC) wants to help answer those questions. they disclose scores to prospective customers under an NDA or EEMBC’s MultiBench 1.0 is a new benchmark suite for use the benchmarks for internal testing and analysis. measuring the throughput of multiprocessor systems, Partly for this reason, MPR rarely cites EEMBC scores including those built with multicore processors.
    [Show full text]
  • Owner's Manual
    Dell Latitude 3330 Owner's Manual Regulatory Model: P18S Regulatory Type: P18S002 Notes, Cautions, and Warnings NOTE: A NOTE indicates important information that helps you make better use of your computer. CAUTION: A CAUTION indicates either potential damage to hardware or loss of data and tells you how to avoid the problem. WARNING: A WARNING indicates a potential for property damage, personal injury, or death. © 2013 Dell Inc. Trademarks used in this text: Dell™, the Dell logo, Dell Boomi™, Dell Precision™ , OptiPlex™, Latitude™, PowerEdge™, PowerVault™, PowerConnect™, OpenManage™, EqualLogic™, Compellent™, KACE™, FlexAddress™, Force10™ and Vostro™ are trademarks of Dell Inc. Intel®, Pentium®, Xeon®, Core® and Celeron® are registered trademarks of Intel Corporation in the U.S. and other countries. AMD® is a registered trademark and AMD Opteron™, AMD Phenom™ and AMD Sempron™ are trademarks of Advanced Micro Devices, Inc. Microsoft®, Windows®, Windows Server®, Internet Explorer®, MS-DOS®, Windows Vista® and Active Directory® are either trademarks or registered trademarks of Microsoft Corporation in the United States and/or other countries. Red Hat® and Red Hat® Enterprise Linux® are registered trademarks of Red Hat, Inc. in the United States and/or other countries. Novell® and SUSE® are registered trademarks of Novell Inc. in the United States and other countries. Oracle® is a registered trademark of Oracle Corporation and/or its affiliates. Citrix®, Xen®, XenServer® and XenMotion® are either registered trademarks or trademarks of Citrix Systems, Inc. in the United States and/or other countries. VMware®, Virtual SMP®, vMotion®, vCenter® and vSphere® are registered trademarks or trademarks of VMware, Inc. in the United States or other countries.
    [Show full text]
  • H242-Z10 Edge Server - AMD up 2U 4 Nodes
    H242-Z10 Edge Server - AMD UP 2U 4 Nodes Features • Supports 5G network infrastructure • 2U - 4 nodes rear access server system for Edge Computing • Single AMD EPYC™ 7002 series processor family • 4 x LGA 4094 sockets • 8-Channel RDIMM/LRDIMM DDR4, 32 x DIMMs • 8 x 1Gb/s LAN ports (Intel® I350-AM2) • 4 x 2.5" NVMe hot-swappable SSD bays • 8 x M.2 with PCIe Gen3 x4 interface • 8 x Low profile PCIe x16 expansion slots • 4 x OCP 2.0 Gen3 x16 mezzanine slots • Aspeed® AST2500 remote management controller • 2+0 1200W 80 PLUS Platinum power supply AMD EPYC™ 7002 Series Processor (Rome) The next generation of AMD EPYC has arrived, providing incredible compute, IO and bandwidth capability – designed to meet the huge demand for more compute in big data analytics, HPC and cloud computing. Built on 7nm advanced process technology, allowing for denser compute capabilities with lower power consumption Up to 64 core per CPU, built using Zen 2 high performance cores and AMD’s innovative chiplet architecture Supporting PCIe Gen 4.0 with a bandwidth of up to 64GB/s, twice of PCIe Gen 3.0 Embedded security protection to help defend your CPU, applications, and data Optional CMC / Ring Topology Module GIGABYTE’s H242-Series servers include support for an optional CMC / Ring Topology Module, featuring an Aspeed CMC (Central Management Controller), LAN hub and dual MLAN ports for multi-node management (including iKVM support) by connecting internally to Aspeed BMCs integrated on each node. This results only in one MLAN connection required to perform manage- ment of all four nodes, resulting in less ToR (Top of Rack) cabling and switch connections.
    [Show full text]
  • AMD EPYC™ 7371 Processors Accelerating HPC Innovation
    AMD EPYC™ 7371 Processors Solution Brief Accelerating HPC Innovation March, 2019 AMD EPYC 7371 processors (16 core, 3.1GHz): Exceptional Memory Bandwidth AMD EPYC server processors deliver 8 channels of memory with support for up The right choice for HPC to 2TB of memory per processor. Designed from the ground up for a new generation of solutions, AMD EPYC™ 7371 processors (16 core, 3.1GHz) implement a philosophy of Standards Based AMD is committed to industry standards, choice without compromise. The AMD EPYC 7371 processor delivers offering you a choice in x86 processors outstanding frequency for applications sensitive to per-core with design innovations that target the performance such as those licensed on a per-core basis. evolving needs of modern datacenters. No Compromise Product Line Compute requirements are increasing, datacenter space is not. AMD EPYC server processors offer up to 32 cores and a consistent feature set across all processor models. Power HPC Workloads Tackle HPC workloads with leading performance and expandability. AMD EPYC 7371 processors are an excellent option when license costs Accelerate your workloads with up to dominate the overall solution cost. In these scenarios the performance- 33% more PCI Express® Gen 3 lanes. per-dollar of the overall solution is usually best with a CPU that can Optimize Productivity provide excellent per-core performance. Increase productivity with tools, resources, and communities to help you “code faster, faster code.” Boost AMD EPYC processors’ innovative architecture translates to tremendous application performance with Software performance. More importantly, the performance you’re paying for can Optimization Guides and Performance be matched to the appropriate to the performance you need.
    [Show full text]
  • Load Testing, Benchmarking, and Application Performance Management for the Web
    Published in the 2002 Computer Measurement Group (CMG) Conference, Reno, NV, Dec. 2002. LOAD TESTING, BENCHMARKING, AND APPLICATION PERFORMANCE MANAGEMENT FOR THE WEB Daniel A. Menascé Department of Computer Science and E-center of E-Business George Mason University Fairfax, VA 22030-4444 [email protected] Web-based applications are becoming mission-critical for many organizations and their performance has to be closely watched. This paper discusses three important activities in this context: load testing, benchmarking, and application performance management. Best practices for each of these activities are identified. The paper also explains how basic performance results can be used to increase the efficiency of load testing procedures. infrastructure depends on the traffic it expects to see 1. Introduction at its site. One needs to spend enough but no more than is required in the IT infrastructure. Besides, Web-based applications are becoming mission- resources need to be spent where they will generate critical to most private and governmental the most benefit. For example, one should not organizations. The ever-increasing number of upgrade the Web servers if most of the delay is in computers connected to the Internet and the fast the database server. So, in order to maximize the growing number of Web-enabled wireless devices ROI, one needs to know when and how to upgrade create incentives for companies to invest in Web- the IT infrastructure. In other words, not spending at based infrastructures and the associated personnel the right time and spending at the wrong place will to maintain them. By establishing a Web presence, a reduce the cost-benefit of the investment.
    [Show full text]
  • Overview of the SPEC Benchmarks
    9 Overview of the SPEC Benchmarks Kaivalya M. Dixit IBM Corporation “The reputation of current benchmarketing claims regarding system performance is on par with the promises made by politicians during elections.” Standard Performance Evaluation Corporation (SPEC) was founded in October, 1988, by Apollo, Hewlett-Packard,MIPS Computer Systems and SUN Microsystems in cooperation with E. E. Times. SPEC is a nonprofit consortium of 22 major computer vendors whose common goals are “to provide the industry with a realistic yardstick to measure the performance of advanced computer systems” and to educate consumers about the performance of vendors’ products. SPEC creates, maintains, distributes, and endorses a standardized set of application-oriented programs to be used as benchmarks. 489 490 CHAPTER 9 Overview of the SPEC Benchmarks 9.1 Historical Perspective Traditional benchmarks have failed to characterize the system performance of modern computer systems. Some of those benchmarks measure component-level performance, and some of the measurements are routinely published as system performance. Historically, vendors have characterized the performances of their systems in a variety of confusing metrics. In part, the confusion is due to a lack of credible performance information, agreement, and leadership among competing vendors. Many vendors characterize system performance in millions of instructions per second (MIPS) and millions of floating-point operations per second (MFLOPS). All instructions, however, are not equal. Since CISC machine instructions usually accomplish a lot more than those of RISC machines, comparing the instructions of a CISC machine and a RISC machine is similar to comparing Latin and Greek. 9.1.1 Simple CPU Benchmarks Truth in benchmarking is an oxymoron because vendors use benchmarks for marketing purposes.
    [Show full text]
  • Opportunities and Open Problems for Static and Dynamic Program Analysis Mark Harman∗, Peter O’Hearn∗ ∗Facebook London and University College London, UK
    1 From Start-ups to Scale-ups: Opportunities and Open Problems for Static and Dynamic Program Analysis Mark Harman∗, Peter O’Hearn∗ ∗Facebook London and University College London, UK Abstract—This paper1 describes some of the challenges and research questions that target the most productive intersection opportunities when deploying static and dynamic analysis at we have yet witnessed: that between exciting, intellectually scale, drawing on the authors’ experience with the Infer and challenging science, and real-world deployment impact. Sapienz Technologies at Facebook, each of which started life as a research-led start-up that was subsequently deployed at scale, Many industrialists have perhaps tended to regard it unlikely impacting billions of people worldwide. that much academic work will prove relevant to their most The paper identifies open problems that have yet to receive pressing industrial concerns. On the other hand, it is not significant attention from the scientific community, yet which uncommon for academic and scientific researchers to believe have potential for profound real world impact, formulating these that most of the problems faced by industrialists are either as research questions that, we believe, are ripe for exploration and that would make excellent topics for research projects. boring, tedious or scientifically uninteresting. This sociological phenomenon has led to a great deal of miscommunication between the academic and industrial sectors. I. INTRODUCTION We hope that we can make a small contribution by focusing on the intersection of challenging and interesting scientific How do we transition research on static and dynamic problems with pressing industrial deployment needs. Our aim analysis techniques from the testing and verification research is to move the debate beyond relatively unhelpful observations communities to industrial practice? Many have asked this we have typically encountered in, for example, conference question, and others related to it.
    [Show full text]
  • Intel/AMD CPU Release Dates, 2018
    Release dates of desktop microprocessors (2018) http://www.cpu-world.com/Releases/Desktop_CPU_releases_(2018).html News • CPUs / Chips • Benchmarks • Information • Forum • Links • About Identification • Pinouts • S-Spec numbers • Glossary Search the site / Ident CPU / Quick CPU looku Release dates of desktop microprocessors (2018) 2017 2019 AMD Intel Desktop CPU releases January 2004 February First Zen-based desktop APUs 2005 14nm, 4 cores, Radeon Vega graphics 2006 2007 Ryzen 3 2200G 2008 3.5GHz / 4MB L3 / 4 cores / Unlocked / Socket AM4 2009 Ryzen 5 2400G 2010 3.6GHz / 4MB L3 / 4 cores / Unlocked / Socket AM4 2011 Other markets: March April 2nd Generation Zen CPUs 8th Generation lineup launch 2018 embedded CPUs 2018 mobile CPUs "Pinnacle Ridge", 12nm, up to 8 cores Coffee Lake-S, 14nm, Up to 6 cores 2018 server CPUs Ryzen 5 2600X Celeron G4900T 3.6GHz / 16MB L3 / 6 cores / Unlocked / Socket AM4 2.9GHz / 2MB L3 / 2 cores / Socket 1151 Ryzen 5 2600 Celeron G4900 3.4GHz / 16MB L3 / 6 cores / Unlocked / Socket AM4 3.1GHz / 2MB L3 / 2 cores / Socket 1151 Ryzen 7 2700X Celeron G4920 3.7GHz / 16MB L3 / 8 cores / Unlocked / Socket AM4 3.2GHz / 2MB L3 / 2 cores / Socket 1151 Ryzen 7 2700 Core i3-8100T 3.2GHz / 16MB L3 / 8 cores / Unlocked / Socket AM4 3.1GHz / 6MB L3 / 4 cores / Socket 1151 Core i3-8300T Ryzen 3 2200GE 3.2GHz / 8MB L3 / 4 cores / Socket 1151 3.2GHz / 4MB L3 / 4 cores / Unlocked / Socket AM4 Core i3-8300 Ryzen 5 2400GE 3.7GHz / 8MB L3 / 4 cores / Socket 1151 3.2GHz / 4MB L3 / 4 cores / Unlocked / Socket AM4 Core i5-8400T 1.7GHz
    [Show full text]
  • Multiprocessing Contents
    Multiprocessing Contents 1 Multiprocessing 1 1.1 Pre-history .............................................. 1 1.2 Key topics ............................................... 1 1.2.1 Processor symmetry ...................................... 1 1.2.2 Instruction and data streams ................................. 1 1.2.3 Processor coupling ...................................... 2 1.2.4 Multiprocessor Communication Architecture ......................... 2 1.3 Flynn’s taxonomy ........................................... 2 1.3.1 SISD multiprocessing ..................................... 2 1.3.2 SIMD multiprocessing .................................... 2 1.3.3 MISD multiprocessing .................................... 3 1.3.4 MIMD multiprocessing .................................... 3 1.4 See also ................................................ 3 1.5 References ............................................... 3 2 Computer multitasking 5 2.1 Multiprogramming .......................................... 5 2.2 Cooperative multitasking ....................................... 6 2.3 Preemptive multitasking ....................................... 6 2.4 Real time ............................................... 7 2.5 Multithreading ............................................ 7 2.6 Memory protection .......................................... 7 2.7 Memory swapping .......................................... 7 2.8 Programming ............................................. 7 2.9 See also ................................................ 8 2.10 References .............................................
    [Show full text]
  • The Wysiwyg and Vivien Hardware Guide
    The wysiwyg and Vivien Hardware Guide [Updated June 5, 2019] This guide describes the principles of selecting hardware components for a wysiwyg or Vivien workstation, and it is meant to be a guideline for choosing the right hardware for your intended use of the software. As such, actual hardware models are not specified for most components, but based on the information provided below, you will be able to decide on these yourself. Once you have, if you wish to confirm the components you selected, our Technical Support Department will be happy to look over your list; please see the end of this article for information on how to get in touch with us. Before discussing the various components and the criteria for selecting them, there are four important things to note. It strongly recommended that you read all this information and follow the advice before considering the purchase of new hardware. 1. Geometry must always be properly optimized, in all files, regardless of their complexity. Even the best/fastest/most expensive hardware will not be able to properly- handle a file that is not optimized and therefore contains inefficient geometry. If you haven’t done so already, please read through this thread on our Forum, in order to learn how to optimize your files. The key to understanding the optimization principles described here lies with the articles mentioned in the first paragraph of the first message, “Part 1” and “Part 2”; please ensure that you also click those links and read the information they reveal. 2. Even in an optimized file performance can be poor if your video card driver is out-of-date and/or your video card’s settings and/or Shaded View options are inappropriate.
    [Show full text]
  • Solaris 10 OS on AMD Opteron Processor-Based Systems
    Solaris™ 10 OS on AMD Opteron™ Processor-based Systems < A powerful combination for your business Sun and AMD take x64 computing to a new level with the breakthrough performance of AMD Opteron™ processor-based systems combined with the Solaris™ 10 OS — the most advanced operating system on the planet. By combining the best of free and open source software with the most powerful industry-standard platforms, customers can take advantage of the most robust and secure, yet economical Web, database, and application servers. A unique partnership Price/performance Coengineering and technology collaboration World-record performance Sun and AMD software engineers work jointly Leveraging more than 20 years of Symmetric on a range of codevelopment efforts including Multiprocessing (SMP) expertise, Sun has future development of HyperTransport, virtu- tuned and optimized Solaris 10 for the AMD alization, fault management, compiler perform- Opteron platform to deliver exceptional ance, and other ways Solaris may take advantage performance and near-linear scalability. For Highlights of the AMD Opteron architecture. Solaris 10 enterprises with demanding compute, net- • Supports the latest generation 5/08 also includes support for the latest gener- work, and Web applications, the combination of AMD x64 processors ation of AMD x64 processors and UltraSPARC of Solaris 10 and AMD Opteron processor-based • PowerNow! enhancements CMT systems. systems is often an ideal fit. Dozens of perform- provide additional power man- ance and price/performance world record agement capabilities Growing the Solaris™ OS ecosystem for AMD64 benchmarks demonstrate this exceptional • Remote client display virtualiztion Sun and AMD are working together with key combination. Solaris 10 has set more than • Solaris Trusted Extensions optimi- target ISVs, system builders, and independent 50 world records, employing various industry- zations for better interoperability hardware vendors (IHVs) to fuel growth of the standard benchmarks or workload scenarios and security Solaris 10 ecosystem around AMD64.
    [Show full text]