The security of computer systems fundamentally relies on memory isolation, e.g., kernel address ranges are marked as non-accessible and are protected from user access. In this paper, we present Meltdown. Meltdown exploits side effects of out-of-order execution on modern processors to read arbitrary kernel-memory locations including personal data and passwords. Out-of-order execution is an indispensable performance feature and present in a wide range of modern processors. The attack is independent of the operating system, and it does not rely on any software vulnerabilities. Meltdown breaks all security guarantees provided by address space isolation as well as paravirtualized environments and, thus, every security mechanism building upon this foundation. On affected systems, Meltdown enables an adversary to read memory of other processes or virtual machines in the cloud without any permissions or privileges, affecting millions of customers and virtually every user of a personal computer. We show that the KAISER defense mechanism for KASLR has the important (but inadvertent) side effect of impeding Meltdown. We stress that KAISER must be deployed immediately to prevent large-scale exploitation of this severe information leakage.

/pdf/meltdown-reading-kernel-memory-from-user-space-3p8fk9md7j.pdf

Meltdown: reading kernel memory from user space

Serverless computing is a rapidly growing cloud application model, popularized by Amazon's Lambda platform. Serverless cloud services provide fine-grained provisioning of resources, which scale automatically with user demand. Function-as-a-Service (FaaS) applications follow this serverless model, with the developer providing their application as a set of functions which are executed in response to a user- or system-generated event. Functions are designed to be short-lived and execute inside containers or virtual machines, introducing a range of system-level overheads. This paper studies the architectural implications of this emerging paradigm. Using the commercial-grade Apache OpenWhisk FaaS platform on real servers, this work investigates and identifies the architectural implications of FaaS serverless computing. The workloads, along with the way that FaaS inherently interleaves short functions from many tenants frustrates many of the locality-preserving architectural structures common in modern processors. In particular, we find that: FaaS containerization brings up to 20x slowdown compared to native execution, cold-start can be over 10x a short function's execution time, branch mispredictions per kilo-instruction are 20x higher for short functions, memory bandwidth increases by 6x due to the invocation pattern, and IPC decreases by as much as 35% due to inter-function interference. We open-source FaaSProfiler, the FaaS testing and profiling platform that we developed for this work.

https://dl.acm.org/doi/pdf/10.1145/3352460.3358296

Architectural Implications of Function-as-a-Service Computing

Despite its success in many areas, deep learning is a poor fit for use in hardware predictors because these models are impractically large and slow, but this paper shows how we can use deep learning to help design a new cache replacement policy. We first show that for cache replacement, a powerful LSTM learning model can in an offline setting provide better accuracy than current hardware predictors. We then perform analysis to interpret this LSTM model, deriving a key insight that allows us to design a simple online model that matches the offline model's accuracy with orders of magnitude lower cost. The result is the Glider cache replacement policy, which we evaluate on a set of 33 memory-intensive programs from the SPEC 2006, SPEC 2017, and GAP (graph-processing) benchmark suites. In a single-core setting, Glider outperforms top finishers from the 2nd Cache Replacement Championship, reducing the miss rate over LRU by 8.9%, compared to reductions of 7.1% for Hawkeye, 6.5% for MPPPB, and 7.5% for SHiP++. On a four-core system, Glider improves IPC over LRU by 14.7%, compared with improvements of 13.6% (Hawkeye), 13.2% (MPPPB), and 11.4% (SHiP++).

Applying Deep Learning to the Cache Replacement Problem

Hardware prefetching is an effective technique for hiding cache miss latencies in modern processor designs. Prefetcher performance can be characterized by two main metrics that are generally at odds with one another: coverage, the fraction of baseline cache misses which the prefetcher brings into the cache; and accuracy, the fraction of prefetches which are ultimately used. An overly aggressive prefetcher may improve coverage at the cost of reduced accuracy. Thus, performance may be harmed by this over-aggressiveness because many resources are wasted, including cache capacity and bandwidth. An ideal prefetcher would have both high coverage and accuracy. In this paper, we introduce Perceptron-based Prefetch Filtering (PPF) as a way to increase the coverage of the prefetches generated by an underlying prefetcher without negatively impacting accuracy. PPF enables more aggressive tuning of the underlying prefetcher, leading to increased coverage by filtering out the growing numbers of inaccurate prefetches such an aggressive tuning implies. We also explore a range of features to use to train PPF's perceptron layer to identify inaccurate prefetches. PPF improves performance on a memory-intensive subset of the SPEC CPU 2017 benchmarks by 3.78% for a single-core configuration, and by 11.4% for a 4-core configuration, compared to the underlying prefetcher alone.

Perceptron-based prefetch filtering

The disparity between last-level cache and memory latencies motivates the search for efficient cache management policies. Recent work in predicting reuse of cache blocks enables optimizations that significantly improve cache performance and efficiency. However, the accuracy of the prediction mechanisms limits the scope of optimization. This paper proposes perceptron learning for reuse prediction. The proposed predictor greatly improves accuracy over previous work. For multi- programmed workloads, the average false positive rate of the proposed predictor is 3.2%, while sampling dead block prediction (SDBP) and signature-based hit prediction (SHiP) yield false positive rates above 7%. The improvement in accuracy translates directly into performance. For single-thread workloads and a 4MB lastlevel cache, reuse prediction with perceptron learning enables a replacement and bypass optimization to achieve a geometric mean speedup of 6.1%, compared with 3.8% for SHiP and 3.5% for SDBP on the SPEC CPU 2006 benchmarks. On a memory-intensive subset of SPEC, perceptron learning yields 18.3% speedup, versus 10.5% for SHiP and 7.7% for SDBP. For multi- programmed workloads and a 16MB cache, the proposed technique doubles the efficiency of the cache over LRU and yields a geometric mean normalized weighted speedup of 7.4%, compared with 4.4% for SHiP and 4.2% for SDBP.

Perceptron learning for reuse prediction

The disparity between last-level cache and memory latencies motivates the search for efficient cache management policies. Recent work in predicting reuse of cache blocks enables optimizations that significantly improve cache performance and e ciency. However, the accuracy of the prediction mechanisms limits the scope of optimization. This paper introduces multiperspective reuse prediction, a technique that predicts the future reuse of cache blocks using several different types of features. The accuracy of the multiperspective technique is superior to previous work. We demonstrate the technique using a placement, promotion, and bypass optimization that outperforms state-of-the-art policies using a low overhead. On a set of single-thread benchmarks, the technique yields a geometric mean 9.0% speedup over LRU, compared with 5.1% for Hawkeye and 6.3% for Perceptron. On multi-programmed workloads, the technique gives a geometric mean weighted speedup of 8.3% over LRU, compared with 5.2% for Hawkeye and 5.8% for Perceptron. CCS CONCEPTS • Computer systems organization $\rightarrow$ Multicore architectures; • Hardware $\rightarrow$ Static memory;

Multiperspective reuse prediction

Data prefetching and cache replacement algorithms have been intensively studied in the design of high performance microprocessors. Typically, the data prefetcher operates in the private caches and does not interact with the replacement policy in the shared Last-Level Cache (LLC). Similarly, most replacement policies do not consider demand and prefetch requests as different types of requests. In particular, program counter (PC)-based replacement policies cannot learn from prefetch requests since the data prefetcher does not generate a PC value. PC-based policies can also be negatively affected by compiler optimizations. In this paper, we propose a holistic cache management technique called Kill-the-PC (KPC) that overcomes the weaknesses of traditional prefetching and replacement policy algorithms. KPC cache management has three novel contributions. First, a prefetcher which approximates the future use distance of prefetch requests based on its prediction confidence. Second, a simple replacement policy provides similar or better performance than current state-of-the-art PC-based prediction using global hysteresis. Third, KPC integrates prefetching and replacement policy into a whole system which is greater than the sum of its parts. Information from the prefetcher is used to improve the performance of the replacement policy and vice-versa. Finally, KPC removes the need to propagate the PC through entire on-chip cache hierarchy while providing a holistic cache management approach with better performance than state-of-the-art PC-, and non-PC-based schemes. Our evaluation shows that KPC provides 8% better performance than the best combination of existing prefetcher and replacement policy for multi-core workloads.

https://dl.acm.org/doi/pdf/10.1145/3037697.3037701

Kill the Program Counter: Reconstructing Program Behavior in the Processor Cache Hierarchy

Cache replacement policies often order blocks into distinct positions. A block is placed into a set in some initial position. A re-referenced block is promoted into a higher position while other blocks may move into lower positions. A block in the lowest position is a candidate for replacement. Tree-based PseudoLRU is a well-known space-efficient replacement policy based on representing block positions as distinct paths in a binary tree. We find that a placement or promotion for one block often needlessly disturbs the non-promoted blocks. Guided by the principle of minimal disturbance, i.e. that a policy should seek to disturb the order of non-promoted blocks to the smallest extent possible, we develop a simple modification to PseudoLRU resulting in a policy that improves performance over previous techniques while retaining the low cost of PseudoLRU. The result is a minimal disturbance placement and promotion (MDPP) policy. We first give a static formulation of MDPP and show that it provides superior performance to LRU, PseudoLRU and matches performance for SRRIP for both single-threaded and multi-core workloads. We then give a dynamic formulation that uses dead block prediction for placement and bypass and show that it meets or exceeds state-of-the-art performance with lower overhead. For single-threaded workloads, dynamic MDPP matches the 5.9% speedup over LRU of the state-of-the-art policy SHiP. For multi-core workloads, dynamic MDPP gives a normalized weighted speedup of 14.3% over LRU, compared with SHiP that yields a speedup of 12.3% over LRU and requires double the storage overhead per set. We show that minimal disturbance policies can reduce the frequency of a costly read-modify-write cycle for replacement state, making them potentially suitable for future work in DRAM caches.

Elvira Teran

Papers

Perceptron learning for reuse prediction

Perceptron-based prefetch filtering

Multiperspective reuse prediction

Kill the Program Counter: Reconstructing Program Behavior in the Processor Cache Hierarchy

Minimal disturbance placement and promotion