Open POWER Innovation Redefining HPC Bradley Mc Credie

Open. POWER Innovation: Redefining HPC Bradley Mc. Credie VP/IBM Fellow POWER Systems Development President Open. POWER Foundation mccredie@us. ibm. com

Price/Performance History of Computing Relays / Mechanical Tubes Moore’s Law written Bipolar Integrated Circuits CMOS Multicore Bradley Mc. Credie - 2/26/2015 2

Oct 10, 2003 – Expected Processor Freq Path 3 Bradley Mc. Credie - 2/26/2015 3

Nov 11, 2004 – Modified Path, One Year Later 4 Bradley Mc. Credie - 2/26/2015 4

Power Systems Development of Commercial Aviation 10, 000 Aircraft Speed (mph) Concorde Boeing 707 De. Haviland Comet 1, 000 Speed of Sound in Air Boeing Stratoliner Boeing 247 Ford Trimotor 100 DC-3 Curtiss Flying Boat 10 Wright Brothers 1 1900 1920 1940 1960 1980 2000 Source: F. M. Schellenberg, UCB Bodega Bay, 5 -10 -2007 5 © 2014 IBM Corporation 2020

Power Systems Commercial Aviation 10, 000 Aircraft Speed (mph) Concorde Boeing 707 De. Haviland Comet 1, 000 Speed of Sound in Air Boeing Stratoliner Boeing 247 Ford Trimotor 777 747 767 A-320 DC-10 MD-90 100 DC-3 Curtiss Flying Boat 10 Wright Brothers 1 1900 1920 1940 1960 1980 2000 Source: F. M. Schellenberg, UCB Bodega Bay, 5 -10 -2007 6 © 2014 IBM Corporation 2020

Power Systems 7 425 HP 425 ci Hemi 425 HP 6. 1 L Hemi

Power Systems FM Radio Front Disc Brakes Lap Belts Only 6. 5 MPG 8 © 2014 IBM Corporation AM/FM/CD/DVD + 30 G Storage + i. Pod Keyless Entry w/Remote Start Navigation System, Voice Activated Run Flat Tires (no spare) 4 Wheel Disc Antilock Brakes + Air Bags Lighted Cup Holders, Center Console 14 MPG

Power Systems Industry Trends Generate New Opportunities Microprocessors are no longer driving sufficient Cost/Performance improvements (Core cost/perf) Processors Semiconductor Technology At constant technology costs 9 © 2014 IBM Corporation IBM Confidential

Industry trends drive innovation beyond the chip… Microprocessors alone no longer drive sufficient Price/Performance improvements System Stack Applications and Services Mo o re’ s La Processors Systems Management & Cloud Deployment Semiconductor Technology Systems Acceleration & HW/SW Optimization Firmware, Operating System and Hypervisor w Processors Use Cases • • Workload Acceleration Services Delivery Model Advanced Memory Tech Network & I/O Accel Semiconductor Technology POWER 8 Linux Open. POWER System stack innovations are required to drive Price/Performance Bradley Mc. Credie - 2/26/2015 10

Fueling an Open Development Community Implementation / HPC / Research System / Software / Integration I/O / Storage / Acceleration Boards / Systems Chip / SOC Complete member list at www. openpowerfoundation. org

Innovation with POWER Technology GPU/Other NVLINK POWER Processors CAPI/PCI • 12 DMI Memory Interface Control Server Class Memory IBM & Partner Devices Innovation with IBM and Partners is taking place on all interfaces • Wide variety of innovation strategies (Many not depicted) • Leveraging different aspects of system design • All targeting price/performance leadership IBM Confidential

Open. POWER Innovations Targeting HPC Altera FPGA acceleration and IBM CAPI Monte Carlo 250 x faster than POWER 8 core alone, reduced C code 40 x over non-CAPI FPGA Data Engine for No. SQL 24: 1 server consolidation, 3 x lower cost per user, 40 TB CAPI-attached flash US Dept of Energy $325 M super computing contract awarded to IBM, Mellanox, and NVIDIA Do. E systems for science and stockpile stewardship Sierra and Summit systems to be >100 PF, 2 GB/core main memory, local NVRAM, and science performance 4 x-8 x Titan or Sequoia CAPI dev kit with FPGA card from Nallatech NVIDIA acceleration built into IBM Power S 824 L Tyan Open. POWER Customer Reference System 8 x faster than x 86 Ivy Bridge on pattern extraction 82 x faster for Cognos BI and DB 2 BLU 13 © 2014 Open. POWER Foundation

System Hardware Design NVLink Interconnect Differences Graphics Memory 16+16 GB/s CPU Graphics Memory System Memory 40+40 GB/s GPU PCIe Connection NVLink GPU NV 40+ Link 40 G B/s P 8’ k Lin NV GB/s 40 40+ GPU System Memory Graphics Memory Current GPU Attach Future NVLink GPU Attachment “NVLink will help improve GPU-GPU peer-to-peer communications, eliminating the need to transfer data via the PCIe bus. It would also allow one or more GPUs to access the system RAM much quicker. The new protocol will debut in 2016 with Pascal, which was revealed to be NVidia's next GPU architecture. ”

CAPI vs. I/O Device Driver: Data Prep Typical I/O Model Flow: Total ~13µs for data prep Copy or Pin Source Data DD Call 300 Instructions MMIO Notify Accelerator 10, 000 Instructions 7. 9µs Acceleration Application Dependent, but Equal to below Poll / Interrupt Completion Copy or Unpin Result Data 1, 000 Instructions 3, 000 Instructions 1, 000 Instructions 4. 9µs Flow with a Coherent Model: Total 0. 36µs Shared Mem. Notify Accelerator 400 Instructions 0. 3µs Acceleration Application Dependent, but Equal to above Ret. From DD Completion Shared Memory Completion 100 Instructions 0. 06µs

Coherent Accelerator Processor Interface (CAPI) Overview CAPI FPGA IBM-Supplied POWER Service Layer CAPP PCIe Accelerator Function Unit (AFU) POWER 8 Processor Typical I/O model flow DD Call Copy or Pin Source Data MMIO Notify Accelerator Acceleration Poll / Interrupt Completion Copy or Unpin Result Data Ret. From DD Completion Flow with a coherent model Shared Mem. Notify Accelerator Acceleration Shared Memory Completion Advantages of coherent attachment over I/O attachment § Virtual addressing and data caching – Shared memory – Lower latency for highly referenced data § Easier, more natural programming model – Traditional thread-level programming – Long latency of I/O typically requires restructuring of application § Enables applications not possible on I/O – Pointer chasing, and so on

CAPI and Networking Opportunities

Paving the Road to Exascale with Open. POWER Technology IBM / Mellanox / NVIDIA Collaboration Landscape CUDA 5. 5 Programming Model P 8 Tuleta - 4 U 2 P 8 (+ 2 GPU) PCIe Gen 3 CAPI Power Systems CUDA 7 Open MP 4. 0 CUDA 8 Open ACC Open MP 4. 0 Firestone - 2 U 2 P 8 + 2 GPU PCIe Gen 3 CAPI HPC Next - 2 U CAPI NVLink CUDA 9 Open. MP 4. x HPC Future- 2 U Enhanced CAPI Enhanced NVLink HPC Future - 2 U Enhanced CAPI Enhanced NVLink Air/Water Cooled Mellanox Interconnect Technology Adapters Connect-IB Connect. X-4 Connect. X-5 Switches FDR Infini. Band EDR Infini. Band HDR Infini. Band CPU Links 2014 Chip Technology Air Cooled GPUs CPU Power 8 (dual ports) PCI-express Gen 3 (dual ports) CAPI over PCI-express Gen 3 NVIDIA GPU 2015 (GK 210) Power 8 2016 GPU NVIDIA (GP 100) Power Next NVLink JDA 2014 2015 2016 Enhanced CAPI over PCI-express Gen 4 2017 GPU NVIDIA (GV 100) Power Future Enhanced NVLink 2017 Road to Exascale

Summary • The IT industry is being disrupted and being driven by disruptions • Open hardware and open systems will be one of those disruptions • Technology innovations will come from many unpredictable places • POWER technology is well positioned to exploit these new trends