Performance Potential of an Easy-toProgram PRAM-On-Chip Prototype Versus State-of-the-Art Processor George C.
Download ReportTranscript Performance Potential of an Easy-toProgram PRAM-On-Chip Prototype Versus State-of-the-Art Processor George C.
Performance Potential of an Easy-to Program PRAM-On-Chip Prototype Versus State-of-the-Art Processor George C. Caragea – University of Maryland A. Beliz Saybasili – LCB Branch, NHLBL, NIH Xingzhi Wen – NVIDIA Corporation
Uzi Vishkin – University of Maryland www.umiacs.umd.edu/users/vishkin/XMT
Hardware prototypes of PRAM-On-Chip
64-core, 75MHz FPGA prototype
[SPAA’07, Computing Frontiers’08] Original
explicit multi-threaded (XMT) architecture
[SPAA98] (Cray started to use “XMT” ~7 years later) Interconnection Network for 128-core. 9mmX5mm, IBM90nm process. 400 MHz prototype [HotInterconnects’07] Same design as 64-core FPGA. 10mmX10mm, IBM90nm process. 150 MHz prototype The design scales to 1000+ cores on-chip Objective of current paper Meaningful comparison of 1. Our FPGA design, with 2. State-of-the-Art (Intel) Processor
XMT: A PRAM-On-Chip Vision
• • • • • • Manycores are coming. But 40yrs of parallel computing: Never a successful general-purpose parallel computer (easy to program, good speedups, up&down scalable). IF you could program it great speedups. XMT: Fix the IF XMT: Designed from the ground up to address that for on-chip parallelism Unlike matching current HW (Some other SPAA papers) Tested HW & SW prototypes Builds on PRAM algorithmics. Only really successful parallel algorithmic theory. Latent, though not widespread, knowledgebase •
This paper:
~10X relative to Intel Core 2 Duo
If there is time: Really serious about ease of programming
Objective for programmer’s model
• # ops Emerging: not sure, but the analysis should be work-depth. But, why not design for your analysis? (like serial)
Serial Paradigm
What could I do in parallel
Natural (Parallel) Paradigm
at each step assuming unlimited hardware # ops ..
..
..
..
..
..
..
time time •
Time = Work Work = total #ops Time << Work
XMT: Design for work-depth. Unique among manycores. - 1 operation now. Any #ops next time unit.
- Competitive on nesting. (To be published.) - No need to program for locality.
• •
Programmer’s Model: Engineering Workflow
Arbitrary CRCW Work-depth algorithm. Reason about correctness & complexity in synchronous model SPMD reduced synchrony – Threads advance at own speed, not lockstep – Main construct: spawn-join block. Note: can start any number of – processes at once Prefix-sum (ps). Independence of order semantics (IOS).
• • – – spawn join spawn Circumvents “The problem with threads”, e.g., [Lee].
join Establish correctness & complexity by relating to WD analyses.
Tune (compiler or expert programmer): (i) Length of sequence of round trips to memory, (ii) QRQW, (iii) WD. [VCL07] Trial&error contrast: similar start while insufficient inter-thread bandwidth do{rethink algorithm to take better advantage of cache}
XMT Architecture Overview
• • • • One serial core – master thread control unit (MTCU) Parallel cores (TCUS) grouped in clusters Global memory space evenly partitioned in cache banks using hashing No local caches at TCU – Avoids expensive cache coherence hardware
MTCU Hardware Scheduler/Prefix-Sum Unit Cluster 1 Cluster 2
…
Cluster C Parallel Interconnection Network Memory Bank 1 Memory Bank 2 Shared Memory
…
Memory Bank M DRAM Channel 1
…
DRAM Channel D
Paraleap: XMT PRAM-on-chip silicon
• • • Built FPGA prototype Announced in SPAA’07 Built using 3 FPGA chips – 2 Virtex-4 LX200 – 1 Virtex-4 FX100 Clock rate DRAM size DRAM channels Mem. data rate 75 MHz 1GB 1 0.6GB/s No. TCUs Clusters Cache modules Shared cache 64 8 8 256KB With no prior design experience, X. Wen completed synthesizable Verilog description AND the new FPGA-based XMT computer in slightly more than two years. X. Wen is one person.. simplicity of the XMT architecture simple basic faster time to market, lower implementation cost.
Benchmarks
• • • Sparse Matrix – Vector Multiplication (SpMV) – Matrix stored in Compact Sparse Row (CSR) format – Serial version: iterate through rows – Parallel version: one thread per row 1-D FFT – Fixed-point arithmetic implementation – Serial version: Radix-2 Cooley-Tukey Algorithm – Parallel version: Parallelized each stage of serial algorithm Quicksort – Serial version: standard textbook implementation – Parallel version: two phases • Phase 1: For large sub-arrays, parallelize partitioning operation using atomic prefix-sum • Phase 2: Process all partitions in parallel using serial partitioning algorithm
Experimental Platforms
Processor 1 MTCU, 64 TCUs
Clock Cache DRAM Data rate Compiler XMT Paraleap FPGA
75 MHz 256KB shared L1 cache 1GB DDR2 0.6GB/s XMTCC (GCC 4.0.2-based)
Compiler Optim.
-O3, data prefetch, read-only buffers
Intel Core 2 Duo
Dual Core, E6300 1.86GHz
2x64KB L1, 2x2MB L2 2GB DDR2 6.4GB/s GCC 4.1.0
Intel C++ Professional Compiler (ICC) v11 -O3, SSE3 SIMD, data prefetching, auto parallelization For meaningful comparison: compare cycle count
Input Datasets
small large
Program SpMV FFT N
22K 8K
Footprint
200KB 192KB
N
4M 4M
Footprint
33MB 96MB • •
Quicksort
Large dataset represents realistic input sizes – – 100K 781KB 20M 153MB Recommended by Intel engineer for comparison Gives Intel Core 2 advantage because of larger cache Small dataset – – Fits in both Paraleap and Intel Core 2 cache Provides most fair comparison for current XMT generation
•
Clock-Cycle Speedup
Computed as: speedup = #ClockCycles for Core 2 / #ClockCylces for Paraleap • • • •
Program
SpMV
small
6.7
Core 2 – ICC
large
3.3
small
6.3
Core 2 - GCC
large
3.26
FFT 9.51
2.51
8.76
2.71
Quicksort(*) 13.07
7.75
13.89
8.18
Paraleap outperforms Intel Core 2 on all benchmarks Lower speed-ups for Large dataset because of smaller cache size – Will not be an issue for future implementations of XMT Silicon area of 64-TCU XMT roughly the same as one core of Intel Core 2 Duo No reason for clock frequency of XMT to fall behind
Conclusion
• • • XMT provides viable answer to biggest challenges for the field – Ease of programming – Scalability (up&down) Preliminary evaluation shows good result of XMT architecture versus state-of-the art Intel Core 2 platform ICPP’08 paper compares with GPUs.
Software release
Allows to use your own computer for programming on an XMT environment and experimenting with it, including: (i)Cycle-accurate simulator of the XMT machine (ii)Compiler from XMTC to that machine Also provided, extensive material for teaching or self-studying parallelism, including (i)Tutorial + manual for XMTC (150 pages) (ii)Classnotes on parallel algorithms (100 pages) (iii)Video recording of 9/15/07 HS tutorial (300 minutes) (iv) Video recording of grad Parallel Algorithms lectures (30+hours) www.umiacs.umd.edu/users/vishkin/XMT/sw-release.html
Next Major Objective
Industry-grade chip. Requires 10X in funding.
Ease of Programming
• Benchmark: can any CS major program your manycore? - cannot really avoid it. Teachability demonstrated so far: - To freshman class with 11 non-CS students. Some prog. assignments: merge-sort, integer-sort & samples-sort. Other teachers: - Magnet HS teacher. Downloaded simulator, assignments, class notes, from XMT page. Self-taught. Recommends: Teach XMT first. Easiest to set up (simulator), program, analyze: ability to anticipate performance (as in serial). Can do not just for embarrassingly parallel. Teaches also OpenMP, MPI, CUDA. Lookup keynote at CS4HS’09@CMU + interview with teacher.
- High school & Middle School (some 10 year olds) students from underrepresented groups by HS Math teacher.