Gibraltar: A Reed‐Solomon coding library for storage applications on programmable graphics processors

Abstract

SUMMARYReed-Solomon coding is a method for generating arbitrary amounts of erasure correction information from original data via matrix-vector multiplication in finite fields. Previous work has shown that modern CPUs are not well-matched to this type of computation, requiring applications that depend on Reed-Solomon coding at high speeds (such as high-performance storage arrays) to use hardware implementations. This work demonstrates that high performance is possible with current cost-effective graphics processing units across a wide range of operating conditions and describes how performance will likely evolve in similar architectures. It describes the characteristics of the graphics processing unit architecture that enable high-speed Reed-Solomon coding. A high-performance practical library, Gibraltar, has been prototyped that performs Reed-Solomon coding on graphics processors in a manner suitable for storage arrays, along with applications with similar data resiliency needs. This library enables variably resilient erasure correcting codes to be used in a broad range of applications. Its performance is compared with that of a widely available CPU implementation, and a rationale for its API is presented. Its practicality is demonstrated through a usage example.

Abstract: Extended Abstract for Evaluating Asynchrony in Gibraltar RAID's GPU Reed-Solomon Coding Library

“…In our previous work, we designed libgibraltar [2], a library for Reed-Solomon coding as in [4,5] that uses NVIDIA CUDA. We exploit the DLP characteristics of the algorithm, as its primary operation is a large number of matrix-vector multiplications in a Galois field.…”

“…These operations are slow to compute directly, so lookup tables are instead used to provide log and inverse log information. CUDA-based GPUs have several scratch memories that can be accessed in parallel, resulting in high performance Galois field multiplication, as in [2]. This implementation can be tuned per GPU model to allow optimization of table loading.…”

Poster: Evaluating Asynchrony in Gibraltar RAID's GPU Reed-Solomon Coding Library

“…The Reed-Solomon coding library in Gibraltar RAID, known as libgibraltar [2], previously scheduled coding tasks to use the entire GPU.…”

PErasure: A parallel Cauchy Reed-Solomon coding library for GPUs

“…Another GPU-based RAID6 system has been developed in [20], which uses GPUs to accelerate two RAID6 coding schemes, namely Blaum-Roth and Liberation codes, and achieves up to 3GB/s of coding speed. Gibraltar is so far the most successful GPUbased Reed-Solomon (RS) coding library [21] that uses table lookup operations to implement Galois Field multiplications and achieves 10-fold speedup over single-thread Jerasure [22], the most well-known erasure coding library.…”