DaCache: Memory Divergence-Aware GPU Cache Management
DaCache: Memory Divergence-Aware GPU Cache Management
复制标题
DOI：
10.1145/2751205.2751239
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Bin Wang;Weikuan Yu;Xian-He Sun;Xinning Wang
中科院分区：
文献类型：
--
作者：
Bin Wang;Weikuan Yu;Xian-He Sun;Xinning Wang
GPU的锁步执行模型需要一个线程束在执行前拥有所有线程的数据块。然而，缺乏可以识别在线程束级别管理GPU高速缓存块以增加准备好执行的线程束数量的需要的突出高速缓存机制。此外，线程束调度对于特定于GPU的缓存管理非常重要，可以减少线程束内和线程束间冲突并最大限度地提高数据局部性。在本文中，我们提出了一个Divergence-Aware Cache（DaCache）管理，可以编排L1 D缓存管理和warp调度在一起的GPGPU。在DaCache中，传入数据块的插入位置取决于获取线程束的调度优先级。具有较低优先级的线程束块被插入得更靠近LRU链的LRU位置，使得它们在高速缓存中具有较短的生命周期。这种细粒度的插入策略被扩展为将一致性负载优先于发散性负载，使得一致性负载不太容易受到线程束间和线程束内颠簸的影响。DaCache还采用L1 D旁路的约束替换策略来维持完全缓存Warp（FCW）的良好供应，沿着动态机制来在运行时调整FCW。我们的实验表明，DaCache实现了40.4%的性能提高，比基线GPU和两个国家的最先进的抗颠簸技术RRIP和DIP的40%和24.9%，分别。
The lock-step execution model of GPU requires a warp to have the data blocks for all its threads before execution. However, there is a lack of salient cache mechanisms that can recognize the need of managing GPU cache blocks at the warp level for increasing the number of warps ready for execution. In addition, warp scheduling is very important for GPU-specific cache management to reduce both intra- and inter-warp conflicts and maximize data locality. In this paper, we propose a Divergence-Aware Cache (DaCache) management that can orchestrate L1D cache management and warp scheduling together for GPGPUs. In DaCache, the insertion position of an incoming data block depends on the fetching warp's scheduling priority. Blocks of warps with lower priorities are inserted closer to the LRU position of the LRU-chain so that they have shorter lifetime in cache. This fine-grained insertion policy is extended to prioritize coherent loads over divergent loads so that coherent loads are less vulnerable to both inter- and intra-warp thrashing. DaCache also adopts a constrained replacement policy with L1D bypassing to sustain a good supply of Fully Cached Warps (FCW), along with a dynamic mechanism to adjust FCW during runtime. Our experiments demonstrate that DaCache achieves 40.4% performance improvement over the baseline GPU and outperforms two state-of-the-art thrashing-resistant techniques RRIP and DIP by 40% and 24.9%, respectively.