Jayneel Gandhi

Redundant memory mappings for fast access to large memories

Page-based virtual memory improves programmer productivity, security, and memory utilization, but incurs performance overheads due to costly page table walks after TLB misses. This overhead can reach 50% for modern workloads that access increasingly vast memory with stagnating TLB sizes. To reduce the overhead of virtual memory, this paper proposes Redundant Memory Mappings (RMM), which leverage ranges of pages and provides an efficient, alternative representation of many virtual-to-physical mappings. We define a range be a subset of processs pages that are virtually and physically contiguous. RMM translates each range with a single range table entry, enabling a modest number of entries to translate most of the processs address space. RMM operates in parallel with standard paging and uses a software range table and hardware range TLB with arbitrarily large reach. We modify the operating system to automatically detect ranges and to increase their likelihood with eager page allocation. RMM is thus transparent to applications. We prototype RMM software in Linux and emulate the hardware. RMM performs substantially better than paging alone and huge pages, and improves a wider variety of workloads than direct segments (one range per program), reducing the overhead of virtual memory to less than 1% on average.

Efficient Memory Virtualization: Reducing Dimensionality of Nested Page Walks

Virtualization provides value for many workloads, but its cost rises for workloads with poor memory access locality. This overhead comes from translation look aside buffer (TLB) misses where the hardware performs a 2D page walk (up to 24 memory references on x86-64) rather than a native TLB miss (up to only 4 memory references). The first dimension translates guest virtual addresses to guest physical addresses, while the second translates guest physical addresses to host physical addresses. This paper proposes new hardware using direct segments with three new virtualized modes of operation that significantly speed-up virtualized address translation. Further, this paper proposes two novel techniques to address important limitations of original direct segments. First, self-ballooning reduces fragmentation in physical memory, and addresses the architectural input/output (I/O) gap in x86-64. Second, an escape filter provides alternate translations for exceptional pages within a direct segment (e.g., Physical pages with permanent hard faults). We emulate the proposed hardware and prototype the software in Linux with KVM on x86-64. One mode -- VMM Direct -- reduces address translation overhead to near-native without guest application or OS changes (2% slower than native on average), while a more aggressive mode -- Dual Direct -- on big-memory workloads performs better-than-native with near-zero translation overhead.

FabScalar: Automating Superscalar Core Design

Providing multiple superscalar core types on a chip, each tailored to different classes of instruction-level behavior, is an exciting direction for increasing processor performance and energy efficiency. Unfortunately, processor design and verification effort increases with each additional core type, limiting the microarchitectural diversity that can be practically implemented. FabScalar aims to automate superscalar core design, opening up processor design to microarchitectural diversity and its many opportunities.

Energy-efficient address translation

Address translation is fundamental to processor performance. Prior work focused on reducing Translation Lookaside Buffer (TLB) misses to improve performance and energy, whereas we show that even TLB hits consume a significant amount of dynamic energy. To reduce the energy cost of address translation, we first propose Lite, a mechanism that monitors the performance and utility of L1 TLBs, and adaptively changes their sizes with way-disabling. The resulting TLBLite organization opportunistically reduces the dynamic energy spent in address translation by 23% on average with minimal impact on TLB miss cycles. To further reduce the energy and performance overheads of L1 TLBs, we also propose RMMLite that targets the recently proposed Redundant Memory Mappings (RMM) address-translation mechanism. RMM maps most of a processs address space with arbitrarily large ranges of contiguous pages in both virtual and physical address space using a modest number of entries in a range TLB. RMMLite adds to RMM an L1-range TLB and the Lite mechanism. The high hit ratio of the L1-range TLB allows Lite to downsize the L1-page TLBs more aggressively. RMMLite reduces the dynamic energy spent in address translation by 71% on average. Above the near-zero L2 TLB misses from RMM, RMMLite further reduces the overhead from L1 TLB misses by 99%. These proposed designs target current and future energy-efficient memory system design to meet the ever increasing memory demands of applications.

BadgerTrap: a tool to instrument x86-64 TLB misses

The overheads of memory management units (MMUs) have gained importance in todays systems. Detailed simulators may be too slow to gain insights into micro-architectural techniques that improve MMU efficiency. To address this issue, we propose a novel tool, BadgerTrap, which allows online instrumentation of TLB misses. It allows first-order analysis of new hardware techniques to improve MMU efficiency. The tool helps to create and analyze x86-64 TLB miss trace. We describe example studies to show various ways this tool can be applied to gain new research insights.

Agile paging: exceeding the best of nested and shadow paging

Virtualization provides benefits for many workloads, but the overheads of virtualizing memory are not universally low. The cost comes from managing two levels of address translation - one in the guest virtual machine (VM) and the other in the host virtual machine monitor (VMM) - with either nested or shadow paging. Nested paging directly performs a two-level page walk that makes TLB misses slower than unvirtualized native, but enables fast page tables changes. Alternatively, shadow paging restores native TLB miss speeds, but requires costly VMM intervention on page table updates. This paper proposes agile paging that combines both techniques and exceeds the best of both. A virtualized page walk starts with shadow paging and optionally switches in the same page walk to nested paging where frequent page table updates would cause costly VMM interventions. Agile paging enables most TLB misses to be handled as fast as native while most page table changes avoid VMM intervention. It requires modest changes to hardware (e.g., demark when to switch) and VMM policies (e.g., predict good switching opportunities). We emulate the proposed hardware and prototype the software in Linux with KVM on x86-64. Agile paging performs more than 12% better than the best of the two techniques and comes within 4% of native execution for all workloads.

Mosaic: a GPU memory manager with application-transparent support for multiple page sizes

Contemporary discrete GPUs support rich memory management features such as virtual memory and demand paging. These features simplify GPU programming by providing a virtual address space abstraction similar to CPUs and eliminating manual memory management, but they introduce high performance overheads during (1) address translation and (2) page faults. A GPU relies on high degrees of thread-level parallelism (TLP) to hide memory latency. Address translation can undermine TLP, as a single miss in the translation lookaside buffer (TLB) invokes an expensive serialized page table walk that often stalls multiple threads. Demand paging can also undermine TLP, as multiple threads often stall while they wait for an expensive data transfer over the system I/O (e.g., PCIe) bus when the GPU demands a page. In modern GPUs, we face a trade-o on how the page size used for memory management affects address translation and demand paging. The address translation overhead is lower when we employ a larger page size (e.g., 2MB large pages, compared with conventional 4KB base pages), which increases TLB coverage and thus reduces TLB misses. Conversely, the demand paging overhead is lower when we employ a smaller page size, which decreases the system I/O bus transfer latency. Support for multiple page sizes can help relax the page size trade-o so that address translation and demand paging optimizations work together synergistically. However, existing page coalescing (i.e., merging base pages into a large page) and splintering (i.e., splitting a large page into base pages) policies require costly base page migrations that undermine the benefits multiple page sizes provide. In this paper, we observe that GPGPU applications present an opportunity to support multiple page sizes without costly data migration, as the applications perform most of their memory allocation en masse (i.e., they allocate a large number of base pages at once). We show that this en masse allocation allows us to create intelligent memory allocation policies which ensure that base pages that are contiguous in virtual memory are allocated to contiguous physical memory pages. As a result, coalescing and splintering operations no longer need to migrate base pages. We introduce Mosaic, a GPU memory manager that provides application-transparent support for multiple page sizes. Mosaic uses base pages to transfer data over the system I/O bus, and allocates physical memory in a way that (1) preserves base page contiguity and (2) ensures that a large page frame contains pages from only a single memory protection domain. We take advantage of this allocation strategy to design a novel in-place page size selection mechanism that avoids data migration. This mechanism allows the TLB to use large pages, reducing address translation overhead. During data transfer, this mechanism enables the GPU to transfer only the base pages that are needed by the application over the system I/O bus, keeping demand paging overhead low. Our evaluations show that Mosaic reduces address translation overheads while efficiently achieving the benefits of demand paging, compared to a contemporary GPU that uses only a 4KB page size. Relative to a state-of-the-art GPU memory manager, Mosaic improves the performance of homogeneous and heterogeneous multi-application workloads by 55.5% and 29.7% on average, respectively, coming within 6.8% and 15.4% of the performance of an ideal TLB where all TLB requests are hits. CCS CONCEPTS • Computer systems organization → Parallel architectures;

Remote memory in the age of fast networks

As the latency of the network approaches that of memory, it becomes increasingly attractive for applications to use remote memory---random-access memory at another computer that is accessed using the virtual memory subsystem. This is an old idea whose time has come, in the age of fast networks. To work effectively, remote memory must address many technical challenges. In this paper, we enumerate these challenges, discuss their feasibility, explain how some of them are addressed by recent work, and indicate other promising ways to tackle them. Some challenges remain as open problems, while others deserve more study. In this paper, we hope to provide a broad research agenda around this topic, by proposing more problems than solutions.

Range Translations for Fast Virtual Memory

Modern workloads suffer high execution-time overhead due to page-based virtual memory. The authors introduce range translations that map arbitrary-sized virtual memory ranges to contiguous physical memory pages while retaining the flexibility of paging. A range translation reduces address translation to a range lookup that delivers near zero virtual memory overhead.

MASK: Redesigning the GPU Memory Hierarchy to Support Multi-Application Concurrency

Graphics Processing Units (GPUs) exploit large amounts of threadlevel parallelism to provide high instruction throughput and to efficiently hide long-latency stalls. The resulting high throughput, along with continued programmability improvements, have made GPUs an essential computational resource in many domains. Applications from different domains can have vastly different compute and memory demands on the GPU. In a large-scale computing environment, to efficiently accommodate such wide-ranging demands without leaving GPU resources underutilized, multiple applications can share a single GPU, akin to how multiple applications execute concurrently on a CPU. Multi-application concurrency requires several support mechanisms in both hardware and software. One such key mechanism is virtual memory, which manages and protects the address space of each application. However, modern GPUs lack the extensive support for multi-application concurrency available in CPUs, and as a result suffer from high performance overheads when shared by multiple applications, as we demonstrate. We perform a detailed analysis of which multi-application concurrency support limitations hurt GPU performance the most. We find that the poor performance is largely a result of the virtual memory mechanisms employed in modern GPUs. In particular, poor address translation performance is a key obstacle to efficient GPU sharing. State-of-the-art address translation mechanisms, which were designed for single-application execution, experience significant inter-application interference when multiple applications spatially share the GPU. This contention leads to frequent misses in the shared translation lookaside buffer (TLB), where a single miss can induce long-latency stalls for hundreds of threads. As a result, the GPU often cannot schedule enough threads to successfully hide the stalls, which diminishes system throughput and becomes a first-order performance concern. Based on our analysis, we propose MASK, a new GPU framework that provides low-overhead virtual memory support for the concurrent execution of multiple applications. MASK consists of three novel address-translation-aware cache and memory management mechanisms that work together to largely reduce the overhead of address translation: (1) a token-based technique to reduce TLB contention, (2) a bypassing mechanism to improve the effectiveness of cached address translations, and (3) an application-aware memory scheduling scheme to reduce the interference between address translation and data requests. Our evaluations show that MASK restores much of the throughput lost to TLB contention. Relative to a state-of-the-art GPU TLB, MASK improves system throughput by 57.8%, improves IPC throughput by 43.4%, and reduces applicationlevel unfairness by 22.4%. MASKs system throughput is within 23.2% of an ideal GPU system with no address translation overhead.