Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHALCONE : A Hardware-Level Timestamp-based Cache Coherence Scheme for Multi-GPU systems
136
0
0.0
(
0
)
Added by
Md Saiful Arefin Mojumder
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
While multi-GPU (MGPU) systems are extremely popular for compute-intensive workloads, several inefficiencies in the memory hierarchy and data movement result in a waste of GPU resources and difficulties in programming MGPU systems. First, due to the lack of hardware-level coherence, the MGPU programming model requires the programmer to replicate and repeatedly transfer data between the GPUs memory. This leads to inefficient use of precious GPU memory. Second, to maintain coherency across an MGPU system, transferring data using low-bandwidth and high-latency off-chip links leads to degradation in system performance. Third, since the programmer needs to manually maintain data coherence, the programming of an MGPU system to maximize its throughput is extremely challenging. To address the above issues, we propose a novel lightweight timestamp-based coherence protocol, HALCONE, for MGPU systems and modify the memory hierarchy of the GPUs to support physically shared memory. HALCONE replaces the Compute Unit (CU) level logical time counters with cache level logical time counters to reduce coherence traffic. Furthermore, HALCONE introduces a novel timestamp storage unit (TSU) with no additional performance overhead in the main memory to perform coherence actions. Our proposed HALCONE protocol maintains the data coherence in the memory hierarchy of the MGPU with minimal performance overhead (less than 1%). Using a set of standard MGPU benchmarks, we observe that a 4-GPU MGPU system with shared memory and HALCONE performs, on average, 4.6$times$ and 3$times$ better than a 4-GPU MGPU system with existing RDMA and with the recently proposed HMG coherence protocol, respectively. We demonstrate the scalability of HALCONE using different GPU counts (2, 4, 8, and 16) and different CU counts (32, 48, and 64 CUs per GPU) for 11 standard benchmarks.
rate research
Read More
In recent years, machine intelligence (MI) applications have emerged as a major driver for the computing industry. Optimizing these workloads is important but complicated. As memory demands grow and data movement overheads increasingly limit performance, determining the best GPU caching policy to use for a diverse range of MI workloads represents one important challenge. To study this, we evaluate 17 MI applications and characterize their behaviors using a range of GPU caching strategies. In our evaluations, we find that the choice of caching policy in GPU caches involves multiple performance trade-offs and interactions, and there is no one-size-fits-all GPU caching policy for MI workloads. Based on detailed simulation results, we motivate and evaluate a set of cache optimizations that consistently match the performance of the best static GPU caching policies.
Cache coherence protocols such as MESI that use writer-initiated invalidation have high complexity and sometimes have poor performance and energy usage, especially under false sharing. Such protocols require numerous transient states, a shared directory, and support for core-to-core communication, while also suffering under false sharing. An alternative to MESIs writer-initiated invalidation is self-invalidation, which achieves lower complexity than MESI but adds high performance costs or relies on programmer annotations or specific data access patterns. This paper presents Neat, a low-complexity, efficient cache coherence protocol. Neat uses self-invalidation, thus avoiding MESIs transient states, directory, and core-to-core communication requirements. Neat uses novel mechanisms that effectively avoid many unnecessary self-invalidations. An evaluation shows that Neat is simple and has lower verification complexity than the MESI protocol. Neat not only outperforms state-of-the-art self-invalidation protocols, but its performance and energy consumption are comparable to MESIs, and it outperforms MESI under false sharing.
Carbon nanotube field-effect transistors (CNFET) emerge as a promising alternative to CMOS transistors for the much higher speed and energy efficiency, which makes the technology particularly suitable for building the energy-hungry last level cache (LLC). However, the process variations (PVs) in CNFET caused by the imperfect fabrication lead to large timing variation and the worst-case timing dramatically limits the LLC operation speed. Particularly, we observe that the CNFET-based cache latency distribution is closely related to the LLC layouts. For the two typical LLC layouts that have the CNT growth direction aligned to the cache way direction and cache set direction respectively, we proposed variation-aware set aligned (VASA) cache and variation-aware way aligned (VAWA) cache in combination with corresponding cache optimizations such as data shuffling and page mapping to enable low-latency cache for frequently used data. According to our experiments, the optimized LLC reduces the average access latency by 32% and 45% compared to the baseline designs on the two different CNFET layouts respectively while it improves the overall performance by 6% and 9% and reduces the energy consumption by 4% and 8% respectively. In addition, with both the architecture induced latency variation and PV incurred latency variation considered in a unified model, we extended the VAWA and VASA cache design for the CNFET-based NUCA and the proposed NUCA achieves both significant performance improvement and energy saving compared to the straightforward variation-aware NUCA.
Virtually indexed and virtually tagged (VIVT) caches are an attractive option for micro-processor level-1 caches, because of their fast response time and because they are cheaper to implement than more complex caches such as virtually-indexed physical-tagged (VIPT) caches. The level-1 VIVT cache becomes even simpler to construct if it is implemented as a direct-mapped cache (VIVT-DM cache). However, VIVT and VIVT-DM caches have some drawbacks. When the number of sets in the cache is larger than the smallest page size, there is a possibility of synonyms (two or more virtual addresses mapped to the same physical address) existing in the cache. Further, maintenance of cache coherence across multiple processors requires a physical to virtual translation mechanism in the hardware. We describe a simple, efficient reverse lookup table based approach to address the synonym and the coherence problems in VIVT (both set associative and direct-mapped) caches. In particular, the proposed scheme does not disturb the critical memory access paths in a typical micro-processor, and requires a low overhead for its implementation. We have implemented and validated the scheme in the AJIT 32-bit microprocessor core (an implementation of the SPARC-V8 ISA) and the implementation uses approximately 2% of the gates and 5.3% of the memory bits in the processor core.
The use of multi-chip modules (MCM) and/or multi-socket boards is the most suitable approach to increase the computation density of servers while keep chip yield attained. This paper introduces a new coherence protocol suitable, in terms of complexity and scalability, for this class of systems. The proposal uses two complementary ideas: (1) A mechanism that dissociates complexity from performance by means of colored-token counting, (2) A construct that optimizes performance and cost by means of two functionally symmetrical modules working in the last level cache of each chip (D|F-LLC) and each memory controller (D|F-MEM). Each of these structures is divided into two parts: (2.1) The first one consists of a small loosely inclusive sparse directory where only the most actively shared data are tracked in the chip (D-LLC) from each memory controller (D-MEM) and, (2.2) The second is a d-left Counting Bloom Filter which stores approximate information about the blocks allocated, either inside the chip (F-LLC) or in the home memory controller (F-MEM). The coordinated work of both structures minimizes the coherence-related effects on the average memory latency perceived by the processor. Our proposal is able to improve on the performance of a HyperTransport-like coherence protocol by from 25%-to-60%.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
