Capital Markets: Low-Latency Trading
Time is money in the quest for speed
In front-office trading, the ability to process large amounts of data in fractions of a second has become the difference between making the trade and losing it to a competitor. Intel understands the need for speed in this exacting context. The new generations of Intel processors—the Intel® Xeon® processor E5 family and Intel® Xeon® processor E7 family—reduce latency from low microseconds to tens of nanoseconds.1
Intel® Xeon® processor E5 family
Delivering ideal performance for trade execution, the Intel Xeon processor E5 family can boost server performance by up to 80 percent over previous-generation Intel Xeon processor-based servers.2,3
Intel’s latest processor further streamlines your trading process with these benefits:
- Reduced latency: Intel® Integrated I/O can reduce I/O latency up to [placeholder: 30 percent]3,4 while support for PCIe 3.0 specification can improve I/O bandwidth up to [placeholder: 2x].3,5
- Adaptive. Efficient. Secure: The Intel Xeon processor automatically boosts performance when you need it for single and multi-threaded applications, including increased floating-point performance for high-performance computing workloads.6,7 Meanwhile, Intel® Turbo Boost Technology 2.0 delivers up to two times more performance on demand than previous-generation turbo boost technology.3,6,8 It does all this while offering built-in security features that help keep your data safe, even in the cloud.
Intel® Xeon® processor E7 family
- Superior for high volumes of data: Scales to handle complex market data or interconnected and dependent processes on the same hardware box.
- World-record performance: Delivers improved scalability and advanced reliability.
- Do more with less: Enables banks to spread processing over more available cores to handle larger peaks more efficiently, without slowing response times. More cores, more memory, and a four-socket system means the Intel® Xeon® processor E7 family allows firms to host more trading algorithms on each server.
Learn more about the Intel® Xeon® processor E7 family >
Architecture does make a difference
These value-adding elements of Intel® architecture are now also being applied to the trading function.
- Intel® 10 Gigabit Ethernet Media Access Controller and NetEffectTM Ethernet Mezzanine Cluster Adapters focus on acceleration via the network card.
- Intel® I/O Acceleration Technology for I/O-sensitive applications; improves data flow across the platform to increase system performance.
Catalyst for cost savings in the data center
Thanks to their ability to regulate power consumption by intelligently adjusting server performance, Intel® Xeon® processors can help reduce costs and increase energy efficiency within the data center.
- Intel® Xeon® processor E7 series: Easily scales to meet your firm’s demands in real time by directing performance where it is needed. Use all cores or just half of them, depending on which applications are needed.
- Intel Xeon processor E5 family: Saves firms hundreds of thousands of dollars by migrating older systems to new ones. In addition to reducing latency through intelligent performance, these processors can help build a flexible, efficient, and secure data center, all while scaling for cloud delivery.
Learn more about the entire Intel® Xeon® processor family >
Additional information: 9,10
1. www.intel.com/pressroom/archive/releases/20100330comp_sm.htm#story Average of 3x performance claim based on geometric mean of four industry-standard, common enterprise benchmarks (SPECjbb*2005, SPECint*_rate_base2006, SPECfp*_rate_base2006, and TPC Benchmark* E) comparing best published/submitted results on 4-socket (4S) Intel® Xeon® processor X7560 -based server platform to best published 4S Intel® Xeon® processor X7460 -based server platform as of March 26, 2010. See www.intel.com/content/www/us/en/benchmarks/server/xeon-e7-summary.html for more details.
2. Source: Performance comparison using geometric mean of SPECint*_rate_base2006, SPECfp*_rate_base2006, STREAM*_MP Triad, and Linpack* benchmark results. Baseline geometric mean score of 166.75 on previous-generation 2S Intel® Xeon® processor X5690 platform based on best published SPECrate* scores to www.spec.org and best Intel internal measurements on STREAM*_MP Triad and Linpack as of December 5, 2011. New geometric mean score of 306.74 based on Intel internal measured estimates using an Intel platform with two Intel® Xeon® processor E5-2690, Intel® Turbo Boost Technology and Enhanced Intel SpeedStep® Technology enabled, with Intel® Hyper-Threading Technology (Intel® HT Technology), 128 GB RAM, Red Hat* Enterprise Linux* Server 6.1 beta for x86_6, Intel® Compiler 12.1, THP disabled for SPECfp*_rate_base2006 and THP enabled for SPECint*_rate_base2006.
3. Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests, such as SYSmark* and MobileMark*, are measured using specific computer systems, components, software, operations, and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products.
4. Intel measurements of average time for an I/O device read to local system memory under idle conditions. Improvement compares Intel® Xeon® processor E5-2600 product family vs. Intel® Xeon® processor 5600 series.
5. 8 GT/s and 128b/130b encoding in PCIe* 3.0 specification is estimated to double the interconnect bandwidth over the PCIe 2.0 specification. Source: http://www.pcisig.com/news_room/November_18_2010_Press_Release/.
6. Requires a system with Intel® Turbo Boost Technology. Intel® Turbo Boost Technology and Intel® Turbo Boost Technology 2.0 are only available on select Intel® processors. Consult your PC manufacturer. Performance varies depending on hardware, software, and system configuration. For more information, visit www.intel.com/content/www/za/en/architecture-and-technology/turbo-boost/turbo-boost-technology.html.
7. Requires an Intel® Hyper-Threading Technology (Intel® HT Technology)-enabled system, check with your PC manufacturer. Performance will vary depending on the specific hardware and software used. Not available on the Intel® Core™ i5-750. For more information, including details on which processors support HT technology, visit www.intel.com/content/www/us/en/architecture-and-technology/hyper-threading/hyper-threading-technology.html.
8. Source: Performance comparison using SPECint*_rate_base2006 benchmark with Intel® Turbo Boost Technology enabled and disabled. Baseline scores of 390 (Intel® Turbo Boost Technology enabled) and 3XX (Intel® Turbo Boost Technology disabled) based on Intel internal measured estimates as of August 4, 2011 using a Supermicro* X8DTN+ system with two Intel® Xeon® processor X5690, Intel® Turbo Boost Technology enabled or Intel® Turbo Boost Technology disabled, Enhanced Intel SpeedStep® Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 48 GB RAM, Red Hat Enterprise Linux* Server 6.1 beta for x86_6. New scores of 593 (Intel® Turbo Boost Technology enabled) and 529 (Intel® Turbo Boost Technology disabled) based on Intel internal measured estimates using an Intel platform with two Intel® Xeon® processor E5-2680, Intel® Turbo Boost Technology enabled or Intel® Turbo Boost Technology disabled, Enhanced Intel SpeedStep® Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64 GB RAM, Red Hat Enterprise Linux* Server 6.1 beta for x86_6.
9. Up to 60 percent performance gain compared to Intel® Xeon® processor 5500 series claim supported by a Black Scholes* benchmark. Intel internal measurement (Feb 25, 2010). Configuration details: Black Scholes* Baseline Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5570 (2.93 GHz, 8 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat EL* 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 18.74 seconds. New Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5680 (3.33 GHz, 12 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat EL* 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 11.51 seconds.
10. Up to 25% better virtual machine performance claim based on SPECvirt_sc2010 benchmark comparing next-generation Intel® Xeon® processor E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QuickPath Interconnect (Intel® QPI), code named Westmere-EX) scoring 2,540 @ 162VMs to X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI, formerly code named Nehalem-EX) scoring 2,024 @ 126VMs. Source: Intel SSG TR#1118.