]> 2026-09-08T19:23:56+09:00 Lessons 14 ko 2026-07-16T01:56:22Z 2461237.5808102 Lessons Lesson:a case for hardware based demand paging bdf187f5 3000 ko a case for hardware based demand paging bdf187f5 Lesson:a comprehensive analysis of superpage management mechanisms and policies c34f2dbd 3000 ko a comprehensive analysis of superpage management mechanisms and policies c34f2dbd Lesson:a fully associative tagless dram cache f6383680 3000 ko a fully associative tagless dram cache f6383680 Lesson:a hybrid web browser architecture for mobile devices 0a9118ea 3000 ko a hybrid web browser architecture for mobile devices 0a9118ea Lesson:a neural network accelerator for mobile application processors 72ce8850 3000 ko a neural network accelerator for mobile application processors 72ce8850 Lesson:a performance stable numa management scheme for linux based hpc systems 6533e8f2 3000 ko a performance stable numa management scheme for linux based hpc systems 6533e8f2 Lesson:a scalable and overflow tolerant mechanism for minimum virtual time tracking b9b92703 3000 ko a scalable and overflow tolerant mechanism for minimum virtual time tracking b9b92703 Lesson:a secure fast and resource efficient serverless platform with function rewind 6c6658bb 3000 ko a secure fast and resource efficient serverless platform with function rewind 6c6658bb Lesson:accl an fpga based collective engine for distributed applications 896d30fd 3000 ko accl an fpga based collective engine for distributed applications 896d30fd Lesson:achieving low latency graph based vector search via aligning best first search algorithm with ss 77c9550f 3000 ko achieving low latency graph based vector search via aligning best first search algorithm with ss 77c9550f Lesson:achieving microsecond scale tail latency efficiently with approximate optimal scheduling e8d8e302 3000 ko achieving microsecond scale tail latency efficiently with approximate optimal scheduling e8d8e302 Lesson:advocating for key value stores with workload pattern aware dynamic compaction 9489efc9 3000 ko advocating for key value stores with workload pattern aware dynamic compaction 9489efc9 Lesson:aegonkv a high bandwidth low tail latency and low storage cost kv separated lsm store with smart 5a081f42 3000 ko aegonkv a high bandwidth low tail latency and low storage cost kv separated lsm store with smart 5a081f42 Lesson:agile lightweight and efficient asynchronous gpu ssd integration e7527db8 3000 ko agile lightweight and efficient asynchronous gpu ssd integration e7527db8 Lesson:an adaptive zone grouping scheme enabling general purpose file systems on zns ssds c91eb86f 3000 ko an adaptive zone grouping scheme enabling general purpose file systems on zns ssds c91eb86f Lesson:an empirical study on low gpu utilization of deep learning jobs c5389b31 3000 ko an empirical study on low gpu utilization of deep learning jobs c5389b31 Lesson:analysis of virtual machine live migration as a method for power capping 71088a92 3000 ko analysis of virtual machine live migration as a method for power capping 71088a92 Lesson:antipode enforcing cross service causal consistency in distributed applications c02659b0 3000 ko antipode enforcing cross service causal consistency in distributed applications c02659b0 Lesson:application aware swapping for mobile systems f347737b 3000 ko application aware swapping for mobile systems f347737b Lesson:appwatch detecting kernel bug for protecting consumer electronics applications a27fb99c 3000 ko appwatch detecting kernel bug for protecting consumer electronics applications a27fb99c Lesson:archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 3000 ko archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 Lesson:asap fast mobile application switch via adaptive prepaging 3f9602cd 3000 ko asap fast mobile application switch via adaptive prepaging 3f9602cd Lesson:asymmetric raid rethinking raid for ssd heterogeneity bfd97257 3000 ko asymmetric raid rethinking raid for ssd heterogeneity bfd97257 Lesson:asynchronous i o stack a low latency kernel i o stack for ultra low latency ssds 4b00ffc9 3000 ko asynchronous i o stack a low latency kernel i o stack for ultra low latency ssds 4b00ffc9 Lesson:asynchrony and gpus bridging this dichotomy for i o with agio 6fab41bf 3000 ko asynchrony and gpus bridging this dichotomy for i o with agio 6fab41bf Lesson:automatically reasoning about how systems code uses the cpu cache 11306b93 3000 ko automatically reasoning about how systems code uses the cpu cache 11306b93 Lesson:avoiding read stalls on flash storage 34c6809a 3000 ko avoiding read stalls on flash storage 34c6809a Lesson:aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e 3000 ko aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e Lesson:beyond static policies dynamic prac for balanced and efficient rowhammer mitigation edd7af08 3000 ko beyond static policies dynamic prac for balanced and efficient rowhammer mitigation edd7af08 Lesson:bind only vllm rpc sockets to a short private path 4bf9d75f 3000 ko bind only vllm rpc sockets to a short private path 4bf9d75f Lesson:bperf bcoz on cpu off cpu 3b259a81 3000 ko bperf bcoz on cpu off cpu 3b259a81 Lesson:breakhammer enhancing rowhammer mitigations by carefully throttling suspect threads 19eb947b 3000 ko breakhammer enhancing rowhammer mitigations by carefully throttling suspect threads 19eb947b Lesson:bypassd enabling fast userspace access to shared ssds da9e5d79 3000 ko bypassd enabling fast userspace access to shared ssds da9e5d79 Lesson:byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 3000 ko byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 Lesson:cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791 3000 ko cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791 Lesson:cacheblend fast large language model serving for rag with cached knowledge fusion 056a5f5e 3000 ko cacheblend fast large language model serving for rag with cached knowledge fusion 056a5f5e Lesson:calcspar a contract aware lsm store for cloud storage with low latency spikes accc7c9d 3000 ko calcspar a contract aware lsm store for cloud storage with low latency spikes accc7c9d Lesson:can zns ssds be better storage devices for persistent cache 3ff8980a 3000 ko can zns ssds be better storage devices for persistent cache 3ff8980a Lesson:catching two rabbits adaptive real time support for embedded linux ee13b80e 3000 ko catching two rabbits adaptive real time support for embedded linux ee13b80e Lesson:characterizing mobile soc for accelerating heterogeneous llm inference 6b900bb7 3000 ko characterizing mobile soc for accelerating heterogeneous llm inference 6b900bb7 Lesson:chrono meticulous hotness measurement and flexible page migration for memory tiering 840ae980 3000 ko chrono meticulous hotness measurement and flexible page migration for memory tiering 840ae980 Lesson:citadel rethinking memory allocation to safeguard against inter domain rowhammer exploits 8fd39aca 3000 ko citadel rethinking memory allocation to safeguard against inter domain rowhammer exploits 8fd39aca Lesson:cold archives must materialize content addressed model files and cross a storage failure domain 03687d8e 3000 ko cold archives must materialize content addressed model files and cross a storage failure domain 03687d8e Lesson:combining buffered i o and direct i o in distributed file systems b0e268e6 3000 ko combining buffered i o and direct i o in distributed file systems b0e268e6 Lesson:compare identical source envelopes at long run boundaries 5f58511d 3000 ko compare identical source envelopes at long run boundaries 5f58511d Lesson:compressed memory swap for qos of virtualized embedded systems 8e897f83 3000 ko compressed memory swap for qos of virtualized embedded systems 8e897f83 Lesson:constructing and analyzing the lsm compaction design space 1aa4ace5 3000 ko constructing and analyzing the lsm compaction design space 1aa4ace5 Lesson:controlling physical memory fragmentation in mobile systems 0365acff 3000 ko controlling physical memory fragmentation in mobile systems 0365acff Lesson:cornus atomic commit for a cloud dbms with storage disaggregation 279df452 3000 ko cornus atomic commit for a cloud dbms with storage disaggregation 279df452 Lesson:corobase coroutine oriented main memory database engine c4a28018 3000 ko corobase coroutine oriented main memory database engine c4a28018 Lesson:cost efficient large language model serving for multi turn conversations with cachedattention aa200b5c 3000 ko cost efficient large language model serving for multi turn conversations with cachedattention aa200b5c Lesson:cpc coordinated page cache for serverless computing ff3acc8c 3000 ko cpc coordinated page cache for serverless computing ff3acc8c Lesson:crossprefetch accelerating i o prefetching for modern storage 59296dd1 3000 ko crossprefetch accelerating i o prefetching for modern storage 59296dd1 Lesson:d2fq device direct fair queueing for nvme ssds 36293af6 3000 ko d2fq device direct fair queueing for nvme ssds 36293af6 Lesson:daac device reserved memory as an eviction based file cache db4ed198 3000 ko daac device reserved memory as an eviction based file cache db4ed198 Lesson:deltazip efficient serving of multiple full model tuned llms 8420449f 3000 ko deltazip efficient serving of multiple full model tuned llms 8420449f Lesson:demand based coordinated scheduling for smp vms a57bd76a 3000 ko demand based coordinated scheduling for smp vms a57bd76a Lesson:development of behavior profilers for multimedia consumer electronics 6a76ba00 3000 ko development of behavior profilers for multimedia consumer electronics 6a76ba00 Lesson:dflop a data driven framework for multimodal llm training pipeline optimization f26871c0 3000 ko dflop a data driven framework for multimodal llm training pipeline optimization f26871c0 Lesson:disaggregated raid storage in modern datacenters 4eb679fe 3000 ko disaggregated raid storage in modern datacenters 4eb679fe Lesson:dlora dynamically orchestrating requests and adapters for lora llm serving 3827bfa3 3000 ko dlora dynamically orchestrating requests and adapters for lora llm serving 3827bfa3 Lesson:dram 8d56adf1 3000 ko dram 8d56adf1 Lesson:dram architecture for efficient data lifetime management f27c8820 3000 ko dram architecture for efficient data lifetime management f27c8820 Lesson:dwkv collinear slo confound 3000 ko dwkv collinear slo confound Lesson:dwkv doomed chase domino 3000 ko dwkv doomed chase domino Lesson:dwkv failed run fail closed 3000 ko dwkv failed run fail closed Lesson:dwkv kv saturation unproven 3000 ko dwkv kv saturation unproven Lesson:dwkv legacy patch not repro 3000 ko dwkv legacy patch not repro Lesson:dwkv metric mismatch 3000 ko dwkv metric mismatch Lesson:dwkv prompt seed bug 3000 ko dwkv prompt seed bug Lesson:dwkv score code contract 3000 ko dwkv score code contract Lesson:efficient footprint caching for tagless dram caches 9317d60c 3000 ko efficient footprint caching for tagless dram caches 9317d60c Lesson:efficient function call tracing with link time binary rewriting for ce devices 0fd13b41 3000 ko efficient function call tracing with link time binary rewriting for ce devices 0fd13b41 Lesson:efficient hybrid polling for ultra low latency storage devices e753019a 3000 ko efficient hybrid polling for ultra low latency storage devices e753019a Lesson:efficient memory deduplication for mobile smart devices fa9b72e9 3000 ko efficient memory deduplication for mobile smart devices fa9b72e9 Lesson:efficient memory overcommitment for i o passthrough enabled vms via fine grained page meta data d32f4845 3000 ko efficient memory overcommitment for i o passthrough enabled vms via fine grained page meta data d32f4845 Lesson:emt an os framework for new memory translation architectures 6d3356f6 3000 ko emt an os framework for new memory translation architectures 6d3356f6 Lesson:enabling high performance and secure userspace nvm file systems with the trio architecture d59d00b6 3000 ko enabling high performance and secure userspace nvm file systems with the trio architecture d59d00b6 Lesson:energy efficient scheduling of real time tasks on multicore processors a70b387a 3000 ko energy efficient scheduling of real time tasks on multicore processors a70b387a Lesson:enhancing network i o performance for a virtualized hadoop cluster d869aae7 3000 ko enhancing network i o performance for a virtualized hadoop cluster d869aae7 Lesson:enlightening the i o path a holistic approach for application performance a3c2b020 3000 ko enlightening the i o path a holistic approach for application performance a3c2b020 Lesson:evendb optimizing key value storage for spatial locality 7beea059 3000 ko evendb optimizing key value storage for spatial locality 7beea059 Lesson:exoflow a universal workflow system for exactly once dags d9d62c90 3000 ko exoflow a universal workflow system for exactly once dags d9d62c90 Lesson:exploiting asymmetric cpu performance for fast startup of subsystem in mobile smart devices c00616ec 3000 ko exploiting asymmetric cpu performance for fast startup of subsystem in mobile smart devices c00616ec Lesson:exploiting gpus in virtual machine for biocloud b3cdd293 3000 ko exploiting gpus in virtual machine for biocloud b3cdd293 Lesson:exploring the asynchrony of slow memory filesystem with easyio 0952deee 3000 ko exploring the asynchrony of slow memory filesystem with easyio 0952deee Lesson:extending applications safely and efficiently 7a5f9f65 3000 ko extending applications safely and efficiently 7a5f9f65 Lesson:extmem enabling application aware virtual memory management for data intensive applications 8a6dc0e4 3000 ko extmem enabling application aware virtual memory management for data intensive applications 8a6dc0e4 Lesson:faasmem improving memory efficiency of serverless computing with memory pool architecture b6ab9eec 3000 ko faasmem improving memory efficiency of serverless computing with memory pool architecture b6ab9eec Lesson:fast core scheduling with userspace process abstraction d1ea9f62 3000 ko fast core scheduling with userspace process abstraction d1ea9f62 Lesson:fast flexible and practical kernel extensions 9eb8897f 3000 ko fast flexible and practical kernel extensions 9eb8897f Lesson:fast on device llm inference with npus deecd917 3000 ko fast on device llm inference with npus deecd917 Lesson:fast trapless kernel probes everywhere 781e739b 3000 ko fast trapless kernel probes everywhere 781e739b Lesson:fetchbpf customizable prefetching policies in linux with ebpf 9756cb90 3000 ko fetchbpf customizable prefetching policies in linux with ebpf 9756cb90 Lesson:fifo queues are all you need for cache eviction ebc30306 3000 ko fifo queues are all you need for cache eviction ebc30306 Lesson:filter lsm tree 89fd8853 3000 ko filter lsm tree 89fd8853 Lesson:fleetio managing multi tenant cloud storage with multi agent reinforcement learning 714ca9fb 3000 ko fleetio managing multi tenant cloud storage with multi agent reinforcement learning 714ca9fb Lesson:flexmem adaptive page profiling and migration for tiered memory 43991e2a 3000 ko flexmem adaptive page profiling and migration for tiered memory 43991e2a Lesson:following the data not the function rethinking function orchestration in serverless computing 5edeca75 3000 ko following the data not the function rethinking function orchestration in serverless computing 5edeca75 Lesson:fully harnessing the performance potential of dram less mobile flash storage ff995292 3000 ko fully harnessing the performance potential of dram less mobile flash storage ff995292 Lesson:gpu c88d9a4d 3000 ko gpu c88d9a4d Lesson:gqa training generalized multi query transformer models from multi head checkpoints a6839ee2 3000 ko gqa training generalized multi query transformer models from multi head checkpoints a6839ee2 Lesson:group based memory oversubscription for virtualized clouds a7129dfa 3000 ko group based memory oversubscription for virtualized clouds a7129dfa Lesson:halfmoon log optimal fault tolerant stateful serverless computing e44c470a 3000 ko halfmoon log optimal fault tolerant stateful serverless computing e44c470a Lesson:harvesting memory bound cpu stall cycles in software with msh 5866da08 3000 ko harvesting memory bound cpu stall cycles in software with msh 5866da08 Lesson:hotrap hot record retention and promotion for lsm trees with tiered storage 849aa350 3000 ko hotrap hot record retention and promotion for lsm trees with tiered storage 849aa350 Lesson:how storage i o affects user perceived latency in mobile apps b59ccb75 3000 ko how storage i o affects user perceived latency in mobile apps b59ccb75 Lesson:how to copy memory coordinated asynchronous copy as a first class os service 8e43b859 3000 ko how to copy memory coordinated asynchronous copy as a first class os service 8e43b859 Lesson:i o passthru upstreaming a flexible and efficient i o path in linux 7b568465 3000 ko i o passthru upstreaming a flexible and efficient i o path in linux 7b568465 Lesson:ic cache efficient large language model serving via in context caching 4f05d8b7 3000 ko ic cache efficient large language model serving via in context caching 4f05d8b7 Lesson:ice collaborating memory and process management for user experience on resource limited mobile d 312e453f 3000 ko ice collaborating memory and process management for user experience on resource limited mobile d 312e453f Lesson:identifying on off cpu bottlenecks together with blocked samples 1f04444a 3000 ko identifying on off cpu bottlenecks together with blocked samples 1f04444a Lesson:impress an importance informed multi tier prefix kv storage system for large language model infe 51b47015 3000 ko impress an importance informed multi tier prefix kv storage system for large language model infe 51b47015 Lesson:improving application launch performance in smartphones using recurrent neural network 8cfcaeb5 3000 ko improving application launch performance in smartphones using recurrent neural network 8cfcaeb5 Lesson:inf2 high throughput generative inference of large language models using near storage processing 3fcead73 3000 ko inf2 high throughput generative inference of large language models using near storage processing 3fcead73 Lesson:infinigen efficient generative inference of large language models with dynamic kv cache manageme a1ca3228 3000 ko infinigen efficient generative inference of large language models with dynamic kv cache manageme a1ca3228 Lesson:intel accelerator ecosystem an soc oriented perspective bc8f0d20 3000 ko intel accelerator ecosystem an soc oriented perspective bc8f0d20 Lesson:ionia high performance replication for modern disk based kv stores 7cafc97e 3000 ko ionia high performance replication for modern disk based kv stores 7cafc97e Lesson:kal kernel assisted non invasive memory leak tolerance with a general purpose memory allocator 372cd042 3000 ko kal kernel assisted non invasive memory leak tolerance with a general purpose memory allocator 372cd042 Lesson:kangaroo caching billions of tiny objects on flash 90226bd8 3000 ko kangaroo caching billions of tiny objects on flash 90226bd8 Lesson:klotski efficient mixture of expert inference via expert aware multi batch pipeline bae4ea7b 3000 ko klotski efficient mixture of expert inference via expert aware multi batch pipeline bae4ea7b Lesson:kosmo efficient online miss ratio curve generation for eviction policy evaluation 96a524ff 3000 ko kosmo efficient online miss ratio curve generation for eviction policy evaluation 96a524ff Lesson:kvaccel a novel write accelerator for lsm tree based kv stores with host ssd collaboration 968f5966 3000 ko kvaccel a novel write accelerator for lsm tree based kv stores with host ssd collaboration 968f5966 Lesson:kvcache cache in the wild characterizing and optimizing kvcache cache at a large cloud provider 0b39b53c 3000 ko kvcache cache in the wild characterizing and optimizing kvcache cache at a large cloud provider 0b39b53c Lesson:legoos a disseminated distributed os for hardware resource disaggregation d71e3e68 3000 ko legoos a disseminated distributed os for hardware resource disaggregation d71e3e68 Lesson:lesson 0960532f 3000 ko lesson 0960532f Lesson:lesson 0bcd6499 3000 ko lesson 0bcd6499 Lesson:lesson 13ed6bae 3000 ko lesson 13ed6bae Lesson:lesson 3f05b8ca 3000 ko lesson 3f05b8ca Lesson:lesson 5fa267f2 3000 ko lesson 5fa267f2 Lesson:lesson 907f0c60 3000 ko lesson 907f0c60 Lesson:light dedup a light weight inline deduplication framework for non volatile memory file systems 000ae22e 3000 ko light dedup a light weight inline deduplication framework for non volatile memory file systems 000ae22e Lesson:lithos an operating system for efficient machine learning on gpus 76d95512 3000 ko lithos an operating system for efficient machine learning on gpus 76d95512 Lesson:loom efficient capture and querying of high frequency telemetry bbcbd611 3000 ko loom efficient capture and querying of high frequency telemetry bbcbd611 Lesson:lsm tree 060db792 3000 ko lsm tree 060db792 Lesson:lsm tree a7410f58 3000 ko lsm tree a7410f58 Lesson:m5 mastering page migration and memory management for cxl based tiered memory systems 4e752168 3000 ko m5 mastering page migration and memory management for cxl based tiered memory systems 4e752168 Lesson:machine validation receipts should be structurally unable to grant human acceptance 470a7c00 3000 ko machine validation receipts should be structurally unable to grant human acceptance 470a7c00 Lesson:managing gpu buffers for caching more apps in mobile systems afba2ee0 3000 ko managing gpu buffers for caching more apps in mobile systems afba2ee0 Lesson:managing memory tiers with cxl in virtualized environments 357c7cc7 3000 ko managing memory tiers with cxl in virtualized environments 357c7cc7 Lesson:memory deduplication in mobile systems 063e8b2e 3000 ko memory deduplication in mobile systems 063e8b2e Lesson:memsos os guided selective memory mirroring ac9aab48 3000 ko memsos os guided selective memory mirroring ac9aab48 Lesson:midas minimizing write amplification in log structured systems through adaptive group number and 1cac80b9 3000 ko midas minimizing write amplification in log structured systems through adaptive group number and 1cac80b9 Lesson:minflow high performance and cost efficient data passing for i o intensive stateful serverless a 886ce161 3000 ko minflow high performance and cost efficient data passing for i o intensive stateful serverless a 886ce161 Lesson:mitigating application resource overload with targeted task cancellation 90270bf8 3000 ko mitigating application resource overload with targeted task cancellation 90270bf8 Lesson:mitigating resource usage dependency in sorting based kv stores on hybrid storage devices via op 31cbb8ad 3000 ko mitigating resource usage dependency in sorting based kv stores on hybrid storage devices via op 31cbb8ad Lesson:moat securely mitigating rowhammer with per row activation counters 6e5ed0e1 3000 ko moat securely mitigating rowhammer with per row activation counters 6e5ed0e1 Lesson:moe lightning high throughput moe inference on memory constrained gpus e51b6b29 3000 ko moe lightning high throughput moe inference on memory constrained gpus e51b6b29 Lesson:mp bcoz ea8563ba 3000 ko mp bcoz ea8563ba Lesson:nanoflow towards optimal large language model serving throughput f0633332 3000 ko nanoflow towards optimal large language model serving throughput f0633332 Lesson:nap natural app processing for predictive user contexts in mobile smartphones a3c20a54 3000 ko nap natural app processing for predictive user contexts in mobile smartphones a3c20a54 Lesson:nomad non exclusive memory tiering via transactional page migration 3990fa86 3000 ko nomad non exclusive memory tiering via transactional page migration 3990fa86 Lesson:not a dpu in name only unleashing rdma capable dpus in multi tenant serverless clouds with nadin 7031318c 3000 ko not a dpu in name only unleashing rdma capable dpus in multi tenant serverless clouds with nadin 7031318c Lesson:nvme bb91a49b 3000 ko nvme bb91a49b Lesson:nvme driven lazy cache coherence for immutable data with nvme over fabrics c19688e2 3000 ko nvme driven lazy cache coherence for immutable data with nvme over fabrics c19688e2 Lesson:nvme prp zero copy 76cd53aa 3000 ko nvme prp zero copy 76cd53aa Lesson:omnicache collaborative caching for near storage accelerators 303fe963 3000 ko omnicache collaborative caching for near storage accelerators 303fe963 Lesson:on performance stability in lsm based storage systems e473bf0c 3000 ko on performance stability in lsm based storage systems e473bf0c Lesson:optimizing file systems on heterogeneous memory by integrating dram cache with virtual memory ma aaa7aa17 3000 ko optimizing file systems on heterogeneous memory by integrating dram cache with virtual memory ma aaa7aa17 Lesson:optimizing the startup time of embedded systems a case study of digital tv 7f9199bd 3000 ko optimizing the startup time of embedded systems a case study of digital tv 7f9199bd Lesson:orca a distributed serving system for transformer based generative models 6bd2fa60 3000 ko orca a distributed serving system for transformer based generative models 6bd2fa60 Lesson:overcoming the memory wall with cxl enabled ssds ef2155d6 3000 ko overcoming the memory wall with cxl enabled ssds ef2155d6 Lesson:ozz identifying kernel out of order concurrency bugs with in vivo memory access reordering 0b85f639 3000 ko ozz identifying kernel out of order concurrency bugs with in vivo memory access reordering 0b85f639 Lesson:pacar improved buffered i o locality on numa systems with page cache replication adc0c538 3000 ko pacar improved buffered i o locality on numa systems with page cache replication adc0c538 Lesson:pact a criticality first design for tiered memory 20db3445 3000 ko pact a criticality first design for tiered memory 20db3445 Lesson:paella low latency model serving with software defined gpu scheduling 47b175ce 3000 ko paella low latency model serving with software defined gpu scheduling 47b175ce Lesson:papi exploiting dynamic parallelism in large language model decoding with a processing in memory 5f9f53cc 3000 ko papi exploiting dynamic parallelism in large language model decoding with a processing in memory 5f9f53cc Lesson:partial failure resilient memory management system for cxl based distributed shared memory 48948c1d 3000 ko partial failure resilient memory management system for cxl based distributed shared memory 48948c1d Lesson:pegasus tolerating skewed workloads in distributed storage with in network coherence directories a4e8c8ec 3000 ko pegasus tolerating skewed workloads in distributed storage with in network coherence directories a4e8c8ec Lesson:performance optimization of object tracking algorithms in opencv on gpus 8158d2ec 3000 ko performance optimization of object tracking algorithms in opencv on gpus 8158d2ec Lesson:perseus a fail slow detection framework for cloud storage system 4e24f100 3000 ko perseus a fail slow detection framework for cloud storage system 4e24f100 Lesson:pet proactive demotion for efficient tiered memory management e2185da3 3000 ko pet proactive demotion for efficient tiered memory management e2185da3 Lesson:phasedrr read reclaim scheduling without page level access counting 69578f95 3000 ko phasedrr read reclaim scheduling without page level access counting 69578f95 Lesson:pit optimization of dynamic sparse deep learning models via permutation invariant transformation 48509ad0 3000 ko pit optimization of dynamic sparse deep learning models via permutation invariant transformation 48509ad0 Lesson:pivot-b200-20260717-immutable-runtime-a01 3000 ko pivot-b200-20260717-immutable-runtime-a01 Lesson:pivot-b200-20260717-launch-lock-a01 3000 ko pivot-b200-20260717-launch-lock-a01 Lesson:pivot-b200-20260717-native-extension-boundary-a01 3000 ko pivot-b200-20260717-native-extension-boundary-a01 Lesson:pivot-b200-20260717-portability-preflight-a01 3000 ko pivot-b200-20260717-portability-preflight-a01 Lesson:pivot-b200-20260717-portable-pipeline-hash-a01 3000 ko pivot-b200-20260717-portable-pipeline-hash-a01 Lesson:pivot-b200-20260717-tmux-argument-boundary-a01 3000 ko pivot-b200-20260717-tmux-argument-boundary-a01 Lesson:pivot-b200-20260717-venv-launcher-identity-a01 3000 ko pivot-b200-20260717-venv-launcher-identity-a01 Lesson:pivot-b200-20260717-zmq-ipc-path-a01 3000 ko pivot-b200-20260717-zmq-ipc-path-a01 Lesson:pmr fast application response via parallel memory reclaim on mobile devices 4c59e491 3000 ko pmr fast application response via parallel memory reclaim on mobile devices 4c59e491 Lesson:pod attention unlocking full prefill decode overlap for faster llm inference caae5b3e 3000 ko pod attention unlocking full prefill decode overlap for faster llm inference caae5b3e Lesson:polymorphic error correction 25fcf9e1 3000 ko polymorphic error correction 25fcf9e1 Lesson:power consumption prediction and power aware packing in consolidated environments 1bd70150 3000 ko power consumption prediction and power aware packing in consolidated environments 1bd70150 Lesson:predicting future system reliability with a component level dram fault model 1f248bb6 3000 ko predicting future system reliability with a component level dram fault model 1f248bb6 Lesson:prism optimizing key value store for modern heterogeneous storage devices 7e879d0a 3000 ko prism optimizing key value store for modern heterogeneous storage devices 7e879d0a Lesson:pruneoff offloading lsm read path pruning in disaggregated key value stores f03d7e8e 3000 ko pruneoff offloading lsm read path pruning in disaggregated key value stores f03d7e8e Lesson:pvm efficient shadow paging for deploying secure containers in cloud native environment 7fee6654 3000 ko pvm efficient shadow paging for deploying secure containers in cloud native environment 7fee6654 Lesson:rearchitecting buffered i o in the era of high bandwidth ssd 70b23de3 3000 ko rearchitecting buffered i o in the era of high bandwidth ssd 70b23de3 Lesson:request aware cooperative i o scheduling for scale out database applications 25327d2c 3000 ko request aware cooperative i o scheduling for scale out database applications 25327d2c Lesson:request oriented durable write caching for application performance 951bd722 3000 ko request oriented durable write caching for application performance 951bd722 Lesson:research autopilot 20260718t030144z-gpu 3000 ko research autopilot 20260718t030144z-gpu Lesson:research autopilot 20260719t090001z 3000 ko research autopilot 20260719t090001z Lesson:research autopilot 20260719t150001z 3000 ko research autopilot 20260719t150001z Lesson:research autopilot 20260719t210001z 3000 ko research autopilot 20260719t210001z Lesson:research autopilot 20260719t210001z-gpu 3000 ko research autopilot 20260719t210001z-gpu Lesson:research autopilot 20260720t030001z 3000 ko research autopilot 20260720t030001z Lesson:research autopilot 20260720t030001z gpu 3000 ko research autopilot 20260720t030001z gpu Lesson:research autopilot 20260720t030001z-gpu 3000 ko research autopilot 20260720t030001z-gpu Lesson:research autopilot 20260720t090001z 3000 ko research autopilot 20260720t090001z Lesson:research autopilot 20260721t030001z 3000 ko research autopilot 20260721t030001z Lesson:research autopilot 20260721t090001z 3000 ko research autopilot 20260721t090001z Lesson:research autopilot 20260721t150001z 3000 ko research autopilot 20260721t150001z Lesson:research autopilot 20260721t210001z 3000 ko research autopilot 20260721t210001z Lesson:research autopilot 20260722t090001z 3000 ko research autopilot 20260722t090001z Lesson:research autopilot 20260722t210001z 3000 ko research autopilot 20260722t210001z Lesson:research autopilot 20260723t030001z 3000 ko research autopilot 20260723t030001z Lesson:research autopilot 20260723t090001z-gpu 3000 ko research autopilot 20260723t090001z-gpu Lesson:research autopilot 20260726t090001z 3000 ko research autopilot 20260726t090001z Lesson:rfuse modernizing userspace filesystem framework through scalable kernel userspace communication b3196db3 3000 ko rfuse modernizing userspace filesystem framework through scalable kernel userspace communication b3196db3 Lesson:rigorous rental memory management for embedded systems 5632faf0 3000 ko rigorous rental memory management for embedded systems 5632faf0 Lesson:rl watchdog a fast and predictable ssd liveness watchdog on storage systems a9a43b61 3000 ko rl watchdog a fast and predictable ssd liveness watchdog on storage systems a9a43b61 Lesson:rubix randomized line to row mapping for low overhead rowhammer mitigations 4d122313 3000 ko rubix randomized line to row mapping for low overhead rowhammer mitigations 4d122313 Lesson:scalaafa constructing user space all flash array engine with holistic designs 396837bd 3000 ko scalaafa constructing user space all flash array engine with holistic designs 396837bd Lesson:scalable address spaces using concurrent interval skiplist d1f1b9c0 3000 ko scalable address spaces using concurrent interval skiplist d1f1b9c0 Lesson:scalable and effective page table and tlb management on numa systems 92f46a49 3000 ko scalable and effective page table and tlb management on numa systems 92f46a49 Lesson:scalable billion point approximate nearest neighbor search using smartssds 3c4169e5 3000 ko scalable billion point approximate nearest neighbor search using smartssds 3c4169e5 Lesson:scalable far memory balancing faults and evictions edcf1536 3000 ko scalable far memory balancing faults and evictions edcf1536 Lesson:scale and flexibility in distribution of hot content a83ac58f 3000 ko scale and flexibility in distribution of hot content a83ac58f Lesson:scalecache a scalable page cache for multiple solid state drives 60b5c227 3000 ko scalecache a scalable page cache for multiple solid state drives 60b5c227 Lesson:scaleswap a scalable os swap system for all flash swap arrays 4041bd54 3000 ko scaleswap a scalable os swap system for all flash swap arrays 4041bd54 Lesson:scalio scaling up dpu based jbof key value store with nvme of target offload 8db39764 3000 ko scalio scaling up dpu based jbof key value store with nvme of target offload 8db39764 Lesson:scheduler support for video oriented multimedia on client side virtualization c8366be4 3000 ko scheduler support for video oriented multimedia on client side virtualization c8366be4 Lesson:scoz a systemwide causal profiler for multicore systems 7b5e72e2 3000 ko scoz a systemwide causal profiler for multicore systems 7b5e72e2 Lesson:selective memory deduplication for cost efficiency in mobile smart devices 9f3139a0 3000 ko selective memory deduplication for cost efficiency in mobile smart devices 9f3139a0 Lesson:separate semantic replication hashes from provenance bound artifact hashes e7ab7a4e 3000 ko separate semantic replication hashes from provenance bound artifact hashes e7ab7a4e Lesson:serverless in the wild characterizing and optimizing the serverless workload at a large cloud pr f2fa1121 3000 ko serverless in the wild characterizing and optimizing the serverless workload at a large cloud pr f2fa1121 Lesson:serverlessllm low latency serverless inference for large language models 69b8cd6d 3000 ko serverlessllm low latency serverless inference for large language models 69b8cd6d Lesson:shape adaptive attention negative 20260722 3000 ko shape adaptive attention negative 20260722 Lesson:shiftlock mitigate one sided rdma lock contention via handover a5d67e63 3000 ko shiftlock mitigate one sided rdma lock contention via handover a5d67e63 Lesson:sieve is simpler than lru an efficient turn key eviction algorithm for web caches 86f86293 3000 ko sieve is simpler than lru an efficient turn key eviction algorithm for web caches 86f86293 Lesson:silk preventing latency spikes in log structured merge key value stores 8576916f 3000 ko silk preventing latency spikes in log structured merge key value stores 8576916f Lesson:siloz leveraging dram isolation domains to prevent inter vm rowhammer 9d15762c 3000 ko siloz leveraging dram isolation domains to prevent inter vm rowhammer 9d15762c Lesson:smartlmk a memory reclamation scheme for improving user perceived app launch time d60522c6 3000 ko smartlmk a memory reclamation scheme for improving user perceived app launch time d60522c6 Lesson:specinfer accelerating generative large language model serving with tree based speculative infer e609aa25 3000 ko specinfer accelerating generative large language model serving with tree based speculative infer e609aa25 Lesson:speculative multi level access in lsm tree based kv store 72e42f29 3000 ko speculative multi level access in lsm tree based kv store 72e42f29 Lesson:speed is all you need on device acceleration of large diffusion models via gpu aware optimizatio c53959fd 3000 ko speed is all you need on device acceleration of large diffusion models via gpu aware optimizatio c53959fd Lesson:ssdstreamer specializing i o stack for large scale machine learning 6b597ff1 3000 ko ssdstreamer specializing i o stack for large scale machine learning 6b597ff1 Lesson:stem streaming based fpga acceleration for large scale compactions in lsm kv d204166c 3000 ko stem streaming based fpga acceleration for large scale compactions in lsm kv d204166c Lesson:sti turbocharge nlp inference at the edge via elastic pipelining 99bb4c50 3000 ko sti turbocharge nlp inference at the edge via elastic pipelining 99bb4c50 Lesson:swam revisiting swap and oomk for improving application responsiveness on mobile devices 79b3b8a3 3000 ko swam revisiting swap and oomk for improving application responsiveness on mobile devices 79b3b8a3 Lesson:symbiosis the art of application and kernel cache cooperation 168e4171 3000 ko symbiosis the art of application and kernel cache cooperation 168e4171 Lesson:taming throughput latency tradeoff in llm inference with sarathi serve cf395778 3000 ko taming throughput latency tradeoff in llm inference with sarathi serve cf395778 Lesson:task aware virtual machine scheduling for i o performance f431ccbe 3000 ko task aware virtual machine scheduling for i o performance f431ccbe Lesson:technical review 56ee25b0 3000 ko technical review 56ee25b0 Lesson:technical review 5b128265 3000 ko technical review 5b128265 Lesson:technical review a case for hardware based demand paging 163a61b2 3000 ko technical review a case for hardware based demand paging 163a61b2 Lesson:technical review a fully associative tagless dram cache 8377cc32 3000 ko technical review a fully associative tagless dram cache 8377cc32 Lesson:technical review a hybrid web browser architecture for mobile devices 19197da7 3000 ko technical review a hybrid web browser architecture for mobile devices 19197da7 Lesson:technical review a neural network accelerator for mobile application processors d4383cb5 3000 ko technical review a neural network accelerator for mobile application processors d4383cb5 Lesson:technical review a performance stable numa management scheme for linux based hpc systems e846c351 3000 ko technical review a performance stable numa management scheme for linux based hpc systems e846c351 Lesson:technical review a scalable and overflow tolerant mechanism for minimum virtual time tracking 7a68da61 3000 ko technical review a scalable and overflow tolerant mechanism for minimum virtual time tracking 7a68da61 Lesson:technical review a secure fast and resource efficient serverless platform with function rewind 588a4b15 3000 ko technical review a secure fast and resource efficient serverless platform with function rewind 588a4b15 Lesson:technical review an adaptive zone grouping scheme enabling general purpose file systems on zns s 21d78705 3000 ko technical review an adaptive zone grouping scheme enabling general purpose file systems on zns s 21d78705 Lesson:technical review analysis of virtual machine live migration as a method for power capping b973b1aa 3000 ko technical review analysis of virtual machine live migration as a method for power capping b973b1aa Lesson:technical review application aware swapping for mobile systems 3dd6bfc2 3000 ko technical review application aware swapping for mobile systems 3dd6bfc2 Lesson:technical review appwatch detecting kernel bug for protecting consumer electronics applications 779775f3 3000 ko technical review appwatch detecting kernel bug for protecting consumer electronics applications 779775f3 Lesson:technical review asap fast mobile application switch via adaptive prepaging 3ea3e879 3000 ko technical review asap fast mobile application switch via adaptive prepaging 3ea3e879 Lesson:technical review asynchronous i o stack a low latency kernel i o stack for ultra low latency ssd 3852c43e 3000 ko technical review asynchronous i o stack a low latency kernel i o stack for ultra low latency ssd 3852c43e Lesson:technical review bdff2f7c 3000 ko technical review bdff2f7c Lesson:technical review beyond static policies dynamic prac for balanced and efficient rowhammer mitiga 185f5688 3000 ko technical review beyond static policies dynamic prac for balanced and efficient rowhammer mitiga 185f5688 Lesson:technical review bperf bcoz on cpu off cpu 7ecf409a 3000 ko technical review bperf bcoz on cpu off cpu 7ecf409a Lesson:technical review cache scheme of shared buffer mappings for energy efficiency of mobile devices f1dee859 3000 ko technical review cache scheme of shared buffer mappings for energy efficiency of mobile devices f1dee859 Lesson:technical review catching two rabbits adaptive real time support for embedded linux 07b12680 3000 ko technical review catching two rabbits adaptive real time support for embedded linux 07b12680 Lesson:technical review compressed memory swap for qos of virtualized embedded systems 1bbb61cb 3000 ko technical review compressed memory swap for qos of virtualized embedded systems 1bbb61cb Lesson:technical review controlling physical memory fragmentation in mobile systems 863971bc 3000 ko technical review controlling physical memory fragmentation in mobile systems 863971bc Lesson:technical review cpc coordinated page cache for serverless computing a8af4792 3000 ko technical review cpc coordinated page cache for serverless computing a8af4792 Lesson:technical review d2fq device direct fair queueing for nvme ssds c60d73e1 3000 ko technical review d2fq device direct fair queueing for nvme ssds c60d73e1 Lesson:technical review daac device reserved memory as an eviction based file cache f0f149f0 3000 ko technical review daac device reserved memory as an eviction based file cache f0f149f0 Lesson:technical review demand based coordinated scheduling for smp vms 3d4e78ab 3000 ko technical review demand based coordinated scheduling for smp vms 3d4e78ab Lesson:technical review development of behavior profilers for multimedia consumer electronics f30d374c 3000 ko technical review development of behavior profilers for multimedia consumer electronics f30d374c Lesson:technical review dflop a data driven framework for multimodal llm training pipeline optimization 9bf046db 3000 ko technical review dflop a data driven framework for multimodal llm training pipeline optimization 9bf046db Lesson:technical review dram 0a5cae63 3000 ko technical review dram 0a5cae63 Lesson:technical review dram architecture for efficient data lifetime management 0f2dfdbe 3000 ko technical review dram architecture for efficient data lifetime management 0f2dfdbe Lesson:technical review e0205794 3000 ko technical review e0205794 Lesson:technical review efficient footprint caching for tagless dram caches 5090e3ab 3000 ko technical review efficient footprint caching for tagless dram caches 5090e3ab Lesson:technical review efficient function call tracing with link time binary rewriting for ce devices 0c5c62cb 3000 ko technical review efficient function call tracing with link time binary rewriting for ce devices 0c5c62cb Lesson:technical review efficient hybrid polling for ultra low latency storage devices 545391d6 3000 ko technical review efficient hybrid polling for ultra low latency storage devices 545391d6 Lesson:technical review efficient memory deduplication for mobile smart devices 6603ecf1 3000 ko technical review efficient memory deduplication for mobile smart devices 6603ecf1 Lesson:technical review energy efficient scheduling of real time tasks on multicore processors cc0782cd 3000 ko technical review energy efficient scheduling of real time tasks on multicore processors cc0782cd Lesson:technical review enhancing network i o performance for a virtualized hadoop cluster 41abd407 3000 ko technical review enhancing network i o performance for a virtualized hadoop cluster 41abd407 Lesson:technical review enlightening the i o path a holistic approach for application performance dabf0f9c 3000 ko technical review enlightening the i o path a holistic approach for application performance dabf0f9c Lesson:technical review exploiting asymmetric cpu performance for fast startup of subsystem in mobile s f33a336a 3000 ko technical review exploiting asymmetric cpu performance for fast startup of subsystem in mobile s f33a336a Lesson:technical review exploiting gpus in virtual machine for biocloud 9e8875c0 3000 ko technical review exploiting gpus in virtual machine for biocloud 9e8875c0 Lesson:technical review f0ce02c2 3000 ko technical review f0ce02c2 Lesson:technical review fd6afd43 3000 ko technical review fd6afd43 Lesson:technical review filter lsm tree 4641bf5f 3000 ko technical review filter lsm tree 4641bf5f Lesson:technical review fully harnessing the performance potential of dram less mobile flash storage d4449ca9 3000 ko technical review fully harnessing the performance potential of dram less mobile flash storage d4449ca9 Lesson:technical review gpu e130421c 3000 ko technical review gpu e130421c Lesson:technical review group based memory oversubscription for virtualized clouds c7cc40cd 3000 ko technical review group based memory oversubscription for virtualized clouds c7cc40cd Lesson:technical review how storage i o affects user perceived latency in mobile apps ac1dc0d2 3000 ko technical review how storage i o affects user perceived latency in mobile apps ac1dc0d2 Lesson:technical review identifying on off cpu bottlenecks together with blocked samples 2f1283b1 3000 ko technical review identifying on off cpu bottlenecks together with blocked samples 2f1283b1 Lesson:technical review improving application launch performance in smartphones using recurrent neural 47c597b7 3000 ko technical review improving application launch performance in smartphones using recurrent neural 47c597b7 Lesson:technical review kal kernel assisted non invasive memory leak tolerance with a general purpose m e42adf12 3000 ko technical review kal kernel assisted non invasive memory leak tolerance with a general purpose m e42adf12 Lesson:technical review lsm tree 76287e58 3000 ko technical review lsm tree 76287e58 Lesson:technical review lsm tree da534157 3000 ko technical review lsm tree da534157 Lesson:technical review managing gpu buffers for caching more apps in mobile systems 46ece2ab 3000 ko technical review managing gpu buffers for caching more apps in mobile systems 46ece2ab Lesson:technical review memory deduplication in mobile systems 9c6aec68 3000 ko technical review memory deduplication in mobile systems 9c6aec68 Lesson:technical review memsos os guided selective memory mirroring 4aec983d 3000 ko technical review memsos os guided selective memory mirroring 4aec983d Lesson:technical review mp bcoz 4fde17b0 3000 ko technical review mp bcoz 4fde17b0 Lesson:technical review nap natural app processing for predictive user contexts in mobile smartphones df34aff8 3000 ko technical review nap natural app processing for predictive user contexts in mobile smartphones df34aff8 Lesson:technical review nvme d8da4781 3000 ko technical review nvme d8da4781 Lesson:technical review nvme driven lazy cache coherence for immutable data with nvme over fabrics 4d6bc037 3000 ko technical review nvme driven lazy cache coherence for immutable data with nvme over fabrics 4d6bc037 Lesson:technical review nvme prp zero copy cb4e87d1 3000 ko technical review nvme prp zero copy cb4e87d1 Lesson:technical review optimizing the startup time of embedded systems a case study of digital tv cd15688d 3000 ko technical review optimizing the startup time of embedded systems a case study of digital tv cd15688d Lesson:technical review performance optimization of object tracking algorithms in opencv on gpus 09f20f75 3000 ko technical review performance optimization of object tracking algorithms in opencv on gpus 09f20f75 Lesson:technical review power consumption prediction and power aware packing in consolidated environmen 58907b8a 3000 ko technical review power consumption prediction and power aware packing in consolidated environmen 58907b8a Lesson:technical review request aware cooperative i o scheduling for scale out database applications fe4a3e09 3000 ko technical review request aware cooperative i o scheduling for scale out database applications fe4a3e09 Lesson:technical review request oriented durable write caching for application performance 34a30cbb 3000 ko technical review request oriented durable write caching for application performance 34a30cbb Lesson:technical review rigorous rental memory management for embedded systems 1b4e69c5 3000 ko technical review rigorous rental memory management for embedded systems 1b4e69c5 Lesson:technical review scheduler support for video oriented multimedia on client side virtualization 69d0c186 3000 ko technical review scheduler support for video oriented multimedia on client side virtualization 69d0c186 Lesson:technical review scoz a system wide causal profiler for multicore systems 9ddaf48a 3000 ko technical review scoz a system wide causal profiler for multicore systems 9ddaf48a Lesson:technical review selective memory deduplication for cost efficiency in mobile smart devices ef7d0fd2 3000 ko technical review selective memory deduplication for cost efficiency in mobile smart devices ef7d0fd2 Lesson:technical review smartlmk a memory reclamation scheme for improving user perceived app launch ti e990e433 3000 ko technical review smartlmk a memory reclamation scheme for improving user perceived app launch ti e990e433 Lesson:technical review speculative multi level access in lsm tree based kv store 733f947b 3000 ko technical review speculative multi level access in lsm tree based kv store 733f947b Lesson:technical review ssdstreamer specializing i o stack for large scale machine learning 5d1f4a63 3000 ko technical review ssdstreamer specializing i o stack for large scale machine learning 5d1f4a63 Lesson:technical review task aware virtual machine scheduling for i o performance 26a8da47 3000 ko technical review task aware virtual machine scheduling for i o performance 26a8da47 Lesson:technical review transparent and selective real time interrupt services for performance improvem b78f264b 3000 ko technical review transparent and selective real time interrupt services for performance improvem b78f264b Lesson:technical review transparent smartphone memory expansion f1adb2b8 3000 ko technical review transparent smartphone memory expansion f1adb2b8 Lesson:technical review transparently bridging semantic gap in cpu management for virtualized environme ddf55f9b 3000 ko technical review transparently bridging semantic gap in cpu management for virtualized environme ddf55f9b Lesson:technical review transparently exploiting device reserved memory for application performance in d2f8d46b 3000 ko technical review transparently exploiting device reserved memory for application performance in d2f8d46b Lesson:technical review twob a two tier web browser architecture optimized for mobile network 448d8064 3000 ko technical review twob a two tier web browser architecture optimized for mobile network 448d8064 Lesson:technical review ufs a8ea798b 3000 ko technical review ufs a8ea798b Lesson:technical review virtual asymmetric multiprocessor for interactive performance of consolidated d 70c3d6f5 3000 ko technical review virtual asymmetric multiprocessor for interactive performance of consolidated d 70c3d6f5 Lesson:technical review z journal scalable per core journaling 1f19a370 3000 ko technical review z journal scalable per core journaling 1f19a370 Lesson:technical review zero copying i o stack for low latency ssds fbe45009 3000 ko technical review zero copying i o stack for low latency ssds fbe45009 Lesson:tectonic shift a composite storage fabric for large scale ml training 38266738 3000 ko tectonic shift a composite storage fabric for large scale ml training 38266738 Lesson:telescope telemetry for gargantuan memory footprint applications 6a766ffb 3000 ko telescope telemetry for gargantuan memory footprint applications 6a766ffb Lesson:the cost of dynamic reasoning demystifying ai agents and test time scaling from an ai infrastruc 6d6dff58 3000 ko the cost of dynamic reasoning demystifying ai agents and test time scaling from an ai infrastruc 6d6dff58 Lesson:the design and implementation of a capacity variant storage system 91c1817e 3000 ko the design and implementation of a capacity variant storage system 91c1817e Lesson:tiered memory management access latency is the key aaf24437 3000 ko tiered memory management access latency is the key aaf24437 Lesson:tiered memory management beyond hotness 6ad152df 3000 ko tiered memory management beyond hotness 6ad152df Lesson:tierscape harnessing multiple compressed tiers to tame server memory tco 9ed9ed0d 3000 ko tierscape harnessing multiple compressed tiers to tame server memory tco 9ed9ed0d Lesson:towards efficient flash caches with emerging nvme flexible data placement ssds 8683a6eb 3000 ko towards efficient flash caches with emerging nvme flexible data placement ssds 8683a6eb Lesson:translation pass through for near native paging performance in vms c096bffc 3000 ko translation pass through for near native paging performance in vms c096bffc Lesson:transparent and selective real time interrupt services for performance improvement 6b173779 3000 ko transparent and selective real time interrupt services for performance improvement 6b173779 Lesson:transparent smartphone memory expansion 5ad5fd6a 3000 ko transparent smartphone memory expansion 5ad5fd6a Lesson:transparently bridging semantic gap in cpu management for virtualized environments 2485a772 3000 ko transparently bridging semantic gap in cpu management for virtualized environments 2485a772 Lesson:transparently exploiting device reserved memory for application performance in mobile systems 43e55454 3000 ko transparently exploiting device reserved memory for application performance in mobile systems 43e55454 Lesson:twinpilots a new computing paradigm for gpu cpu parallel llm inference aa39d085 3000 ko twinpilots a new computing paradigm for gpu cpu parallel llm inference aa39d085 Lesson:twob a two tier web browser architecture optimized for mobile network 1b67a324 3000 ko twob a two tier web browser architecture optimized for mobile network 1b67a324 Lesson:ufs bbe26b78 3000 ko ufs bbe26b78 Lesson:ugache a unified gpu cache for embedding based deep learning 227e7c8f 3000 ko ugache a unified gpu cache for embedding based deep learning 227e7c8f Lesson:understanding and mitigating covert and side channel vulnerabilities introduced by rowhammer def 0e272653 3000 ko understanding and mitigating covert and side channel vulnerabilities introduced by rowhammer def 0e272653 Lesson:understanding silent data corruptions in a large production cpu population 56bebc4c 3000 ko understanding silent data corruptions in a large production cpu population 56bebc4c Lesson:unfaasner latency and cost aware offloading of functions from serverless platforms bc32c3a4 3000 ko unfaasner latency and cost aware offloading of functions from serverless platforms bc32c3a4 Lesson:unicom a universally high performant i o completion mechanism for modern computer systems 9172fe3e 3000 ko unicom a universally high performant i o completion mechanism for modern computer systems 9172fe3e Lesson:unimem redesigning disaggregated memory within a unified local remote memory hierarchy 4e1d18c6 3000 ko unimem redesigning disaggregated memory within a unified local remote memory hierarchy 4e1d18c6 Lesson:usher holistic interference avoidance for resource optimized ml inference 74231fc1 3000 ko usher holistic interference avoidance for resource optimized ml inference 74231fc1 Lesson:using one sided rdma reads to build a fast cpu efficient key value store 64f77356 3000 ko using one sided rdma reads to build a fast cpu efficient key value store 64f77356 Lesson:utopia fast and efficient address translation via hybrid restrictive flexible virtual to physica 796873cf 3000 ko utopia fast and efficient address translation via hybrid restrictive flexible virtual to physica 796873cf Lesson:vfpio a virtual i o abstraction for fpga accelerated i o devices dcc63d73 3000 ko vfpio a virtual i o abstraction for fpga accelerated i o devices dcc63d73 Lesson:virtual asymmetric multiprocessor for interactive performance of consolidated desktops ec394686 3000 ko virtual asymmetric multiprocessor for interactive performance of consolidated desktops ec394686 Lesson:wasp workload aware self replicating page tables for numa servers cd871a6f 3000 ko wasp workload aware self replicating page tables for numa servers cd871a6f Lesson:we ain t afraid of no file fragmentation causes and prevention of its performance impact on mode 9a366dfb 3000 ko we ain t afraid of no file fragmentation causes and prevention of its performance impact on mode 9a366dfb Lesson:what you cant forget exploiting parallelism for zoned namespaces 8d6c7c8e 3000 ko what you cant forget exploiting parallelism for zoned namespaces 8d6c7c8e Lesson:xfaas hyperscale and low cost serverless functions at meta bffb729a 3000 ko xfaas hyperscale and low cost serverless functions at meta bffb729a Lesson:xrp in kernel storage functions with ebpf 49cdd043 3000 ko xrp in kernel storage functions with ebpf 49cdd043 Lesson:z journal scalable per core journaling 2aea3506 3000 ko z journal scalable per core journaling 2aea3506 Lesson:zero copying i o stack for low latency ssds dc409093 3000 ko zero copying i o stack for low latency ssds dc409093 Lesson:a case for hardware based demand paging bdf187f5 3000 ko a case for hardware based demand paging bdf187f5 Lesson:a comprehensive analysis of superpage management mechanisms and policies c34f2dbd 3000 ko a comprehensive analysis of superpage management mechanisms and policies c34f2dbd Lesson:a fully associative tagless dram cache f6383680 3000 ko a fully associative tagless dram cache f6383680 Lesson:a hybrid web browser architecture for mobile devices 0a9118ea 3000 ko a hybrid web browser architecture for mobile devices 0a9118ea Lesson:a neural network accelerator for mobile application processors 72ce8850 3000 ko a neural network accelerator for mobile application processors 72ce8850 Lesson:a performance stable numa management scheme for linux based hpc systems 6533e8f2 3000 ko a performance stable numa management scheme for linux based hpc systems 6533e8f2 Lesson:a scalable and overflow tolerant mechanism for minimum virtual time tracking b9b92703 3000 ko a scalable and overflow tolerant mechanism for minimum virtual time tracking b9b92703 Lesson:a secure fast and resource efficient serverless platform with function rewind 6c6658bb 3000 ko a secure fast and resource efficient serverless platform with function rewind 6c6658bb Lesson:accl an fpga based collective engine for distributed applications 896d30fd 3000 ko accl an fpga based collective engine for distributed applications 896d30fd Lesson:achieving low latency graph based vector search via aligning best first search algorithm with ss 77c9550f 3000 ko achieving low latency graph based vector search via aligning best first search algorithm with ss 77c9550f Lesson:achieving microsecond scale tail latency efficiently with approximate optimal scheduling e8d8e302 3000 ko achieving microsecond scale tail latency efficiently with approximate optimal scheduling e8d8e302 Lesson:advocating for key value stores with workload pattern aware dynamic compaction 9489efc9 3000 ko advocating for key value stores with workload pattern aware dynamic compaction 9489efc9 Lesson:aegonkv a high bandwidth low tail latency and low storage cost kv separated lsm store with smart 5a081f42 3000 ko aegonkv a high bandwidth low tail latency and low storage cost kv separated lsm store with smart 5a081f42 Lesson:agile lightweight and efficient asynchronous gpu ssd integration e7527db8 3000 ko agile lightweight and efficient asynchronous gpu ssd integration e7527db8 Lesson:an adaptive zone grouping scheme enabling general purpose file systems on zns ssds c91eb86f 3000 ko an adaptive zone grouping scheme enabling general purpose file systems on zns ssds c91eb86f Lesson:an empirical study on low gpu utilization of deep learning jobs c5389b31 3000 ko an empirical study on low gpu utilization of deep learning jobs c5389b31 Lesson:analysis of virtual machine live migration as a method for power capping 71088a92 3000 ko analysis of virtual machine live migration as a method for power capping 71088a92 Lesson:antipode enforcing cross service causal consistency in distributed applications c02659b0 3000 ko antipode enforcing cross service causal consistency in distributed applications c02659b0 Lesson:application aware swapping for mobile systems f347737b 3000 ko application aware swapping for mobile systems f347737b Lesson:appwatch detecting kernel bug for protecting consumer electronics applications a27fb99c 3000 ko appwatch detecting kernel bug for protecting consumer electronics applications a27fb99c Lesson:archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 3000 ko archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 Lesson:asap fast mobile application switch via adaptive prepaging 3f9602cd 3000 ko asap fast mobile application switch via adaptive prepaging 3f9602cd Lesson:asymmetric raid rethinking raid for ssd heterogeneity bfd97257 3000 ko asymmetric raid rethinking raid for ssd heterogeneity bfd97257 Lesson:asynchronous i o stack a low latency kernel i o stack for ultra low latency ssds 4b00ffc9 3000 ko asynchronous i o stack a low latency kernel i o stack for ultra low latency ssds 4b00ffc9 Lesson:asynchrony and gpus bridging this dichotomy for i o with agio 6fab41bf 3000 ko asynchrony and gpus bridging this dichotomy for i o with agio 6fab41bf Lesson:automatically reasoning about how systems code uses the cpu cache 11306b93 3000 ko automatically reasoning about how systems code uses the cpu cache 11306b93 Lesson:avoiding read stalls on flash storage 34c6809a 3000 ko avoiding read stalls on flash storage 34c6809a Lesson:aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e 3000 ko aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e Lesson:beyond static policies dynamic prac for balanced and efficient rowhammer mitigation edd7af08 3000 ko beyond static policies dynamic prac for balanced and efficient rowhammer mitigation edd7af08 Lesson:bind only vllm rpc sockets to a short private path 4bf9d75f 3000 ko bind only vllm rpc sockets to a short private path 4bf9d75f Lesson:bperf bcoz on cpu off cpu 3b259a81 3000 ko bperf bcoz on cpu off cpu 3b259a81 Lesson:breakhammer enhancing rowhammer mitigations by carefully throttling suspect threads 19eb947b 3000 ko breakhammer enhancing rowhammer mitigations by carefully throttling suspect threads 19eb947b Lesson:bypassd enabling fast userspace access to shared ssds da9e5d79 3000 ko bypassd enabling fast userspace access to shared ssds da9e5d79 Lesson:byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 3000 ko byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 Lesson:cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791 3000 ko cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791 Lesson:cacheblend fast large language model serving for rag with cached knowledge fusion 056a5f5e 3000 ko cacheblend fast large language model serving for rag with cached knowledge fusion 056a5f5e Lesson:calcspar a contract aware lsm store for cloud storage with low latency spikes accc7c9d 3000 ko calcspar a contract aware lsm store for cloud storage with low latency spikes accc7c9d Lesson:can zns ssds be better storage devices for persistent cache 3ff8980a 3000 ko can zns ssds be better storage devices for persistent cache 3ff8980a Lesson:catching two rabbits adaptive real time support for embedded linux ee13b80e 3000 ko catching two rabbits adaptive real time support for embedded linux ee13b80e Lesson:characterizing mobile soc for accelerating heterogeneous llm inference 6b900bb7 3000 ko characterizing mobile soc for accelerating heterogeneous llm inference 6b900bb7 Lesson:chrono meticulous hotness measurement and flexible page migration for memory tiering 840ae980 3000 ko chrono meticulous hotness measurement and flexible page migration for memory tiering 840ae980 Lesson:citadel rethinking memory allocation to safeguard against inter domain rowhammer exploits 8fd39aca 3000 ko citadel rethinking memory allocation to safeguard against inter domain rowhammer exploits 8fd39aca Lesson:cold archives must materialize content addressed model files and cross a storage failure domain 03687d8e 3000 ko cold archives must materialize content addressed model files and cross a storage failure domain 03687d8e Lesson:combining buffered i o and direct i o in distributed file systems b0e268e6 3000 ko combining buffered i o and direct i o in distributed file systems b0e268e6 Lesson:compare identical source envelopes at long run boundaries 5f58511d 3000 ko compare identical source envelopes at long run boundaries 5f58511d Lesson:compressed memory swap for qos of virtualized embedded systems 8e897f83 3000 ko compressed memory swap for qos of virtualized embedded systems 8e897f83 Lesson:constructing and analyzing the lsm compaction design space 1aa4ace5 3000 ko constructing and analyzing the lsm compaction design space 1aa4ace5 Lesson:controlling physical memory fragmentation in mobile systems 0365acff 3000 ko controlling physical memory fragmentation in mobile systems 0365acff Lesson:cornus atomic commit for a cloud dbms with storage disaggregation 279df452 3000 ko cornus atomic commit for a cloud dbms with storage disaggregation 279df452 Lesson:corobase coroutine oriented main memory database engine c4a28018 3000 ko corobase coroutine oriented main memory database engine c4a28018 Lesson:cost efficient large language model serving for multi turn conversations with cachedattention aa200b5c 3000 ko cost efficient large language model serving for multi turn conversations with cachedattention aa200b5c Lesson:cpc coordinated page cache for serverless computing ff3acc8c 3000 ko cpc coordinated page cache for serverless computing ff3acc8c Lesson:crossprefetch accelerating i o prefetching for modern storage 59296dd1 3000 ko crossprefetch accelerating i o prefetching for modern storage 59296dd1 Lesson:d2fq device direct fair queueing for nvme ssds 36293af6 3000 ko d2fq device direct fair queueing for nvme ssds 36293af6 Lesson:daac device reserved memory as an eviction based file cache db4ed198 3000 ko daac device reserved memory as an eviction based file cache db4ed198 Lesson:deltazip efficient serving of multiple full model tuned llms 8420449f 3000 ko deltazip efficient serving of multiple full model tuned llms 8420449f Lesson:demand based coordinated scheduling for smp vms a57bd76a 3000 ko demand based coordinated scheduling for smp vms a57bd76a Lesson:development of behavior profilers for multimedia consumer electronics 6a76ba00 3000 ko development of behavior profilers for multimedia consumer electronics 6a76ba00 Lesson:dflop a data driven framework for multimodal llm training pipeline optimization f26871c0 3000 ko dflop a data driven framework for multimodal llm training pipeline optimization f26871c0 Lesson:disaggregated raid storage in modern datacenters 4eb679fe 3000 ko disaggregated raid storage in modern datacenters 4eb679fe Lesson:dlora dynamically orchestrating requests and adapters for lora llm serving 3827bfa3 3000 ko dlora dynamically orchestrating requests and adapters for lora llm serving 3827bfa3 Lesson:dram 8d56adf1 3000 ko dram 8d56adf1 Lesson:dram architecture for efficient data lifetime management f27c8820 3000 ko dram architecture for efficient data lifetime management f27c8820 Lesson:dwkv collinear slo confound 3000 ko dwkv collinear slo confound Lesson:dwkv doomed chase domino 3000 ko dwkv doomed chase domino Lesson:dwkv failed run fail closed 3000 ko dwkv failed run fail closed Lesson:dwkv kv saturation unproven 3000 ko dwkv kv saturation unproven Lesson:dwkv legacy patch not repro 3000 ko dwkv legacy patch not repro Lesson:dwkv metric mismatch 3000 ko dwkv metric mismatch Lesson:dwkv prompt seed bug 3000 ko dwkv prompt seed bug Lesson:dwkv score code contract 3000 ko dwkv score code contract Lesson:efficient footprint caching for tagless dram caches 9317d60c 3000 ko efficient footprint caching for tagless dram caches 9317d60c Lesson:efficient function call tracing with link time binary rewriting for ce devices 0fd13b41 3000 ko efficient function call tracing with link time binary rewriting for ce devices 0fd13b41 Lesson:efficient hybrid polling for ultra low latency storage devices e753019a 3000 ko efficient hybrid polling for ultra low latency storage devices e753019a Lesson:efficient memory deduplication for mobile smart devices fa9b72e9 3000 ko efficient memory deduplication for mobile smart devices fa9b72e9 Lesson:efficient memory overcommitment for i o passthrough enabled vms via fine grained page meta data d32f4845 3000 ko efficient memory overcommitment for i o passthrough enabled vms via fine grained page meta data d32f4845 Lesson:emt an os framework for new memory translation architectures 6d3356f6 3000 ko emt an os framework for new memory translation architectures 6d3356f6 Lesson:enabling high performance and secure userspace nvm file systems with the trio architecture d59d00b6 3000 ko enabling high performance and secure userspace nvm file systems with the trio architecture d59d00b6 Lesson:energy efficient scheduling of real time tasks on multicore processors a70b387a 3000 ko energy efficient scheduling of real time tasks on multicore processors a70b387a Lesson:enhancing network i o performance for a virtualized hadoop cluster d869aae7 3000 ko enhancing network i o performance for a virtualized hadoop cluster d869aae7 Lesson:enlightening the i o path a holistic approach for application performance a3c2b020 3000 ko enlightening the i o path a holistic approach for application performance a3c2b020 Lesson:evendb optimizing key value storage for spatial locality 7beea059 3000 ko evendb optimizing key value storage for spatial locality 7beea059 Lesson:exoflow a universal workflow system for exactly once dags d9d62c90 3000 ko exoflow a universal workflow system for exactly once dags d9d62c90 Lesson:exploiting asymmetric cpu performance for fast startup of subsystem in mobile smart devices c00616ec 3000 ko exploiting asymmetric cpu performance for fast startup of subsystem in mobile smart devices c00616ec Lesson:exploiting gpus in virtual machine for biocloud b3cdd293 3000 ko exploiting gpus in virtual machine for biocloud b3cdd293 Lesson:exploring the asynchrony of slow memory filesystem with easyio 0952deee 3000 ko exploring the asynchrony of slow memory filesystem with easyio 0952deee Lesson:extending applications safely and efficiently 7a5f9f65 3000 ko extending applications safely and efficiently 7a5f9f65 Lesson:extmem enabling application aware virtual memory management for data intensive applications 8a6dc0e4 3000 ko extmem enabling application aware virtual memory management for data intensive applications 8a6dc0e4 Lesson:faasmem improving memory efficiency of serverless computing with memory pool architecture b6ab9eec 3000 ko faasmem improving memory efficiency of serverless computing with memory pool architecture b6ab9eec Lesson:fast core scheduling with userspace process abstraction d1ea9f62 3000 ko fast core scheduling with userspace process abstraction d1ea9f62 Lesson:fast flexible and practical kernel extensions 9eb8897f 3000 ko fast flexible and practical kernel extensions 9eb8897f Lesson:fast on device llm inference with npus deecd917 3000 ko fast on device llm inference with npus deecd917 Lesson:fast trapless kernel probes everywhere 781e739b 3000 ko fast trapless kernel probes everywhere 781e739b Lesson:fetchbpf customizable prefetching policies in linux with ebpf 9756cb90 3000 ko fetchbpf customizable prefetching policies in linux with ebpf 9756cb90 Lesson:fifo queues are all you need for cache eviction ebc30306 3000 ko fifo queues are all you need for cache eviction ebc30306 Lesson:filter lsm tree 89fd8853 3000 ko filter lsm tree 89fd8853 Lesson:fleetio managing multi tenant cloud storage with multi agent reinforcement learning 714ca9fb 3000 ko fleetio managing multi tenant cloud storage with multi agent reinforcement learning 714ca9fb Lesson:flexmem adaptive page profiling and migration for tiered memory 43991e2a 3000 ko flexmem adaptive page profiling and migration for tiered memory 43991e2a Lesson:following the data not the function rethinking function orchestration in serverless computing 5edeca75 3000 ko following the data not the function rethinking function orchestration in serverless computing 5edeca75 Lesson:fully harnessing the performance potential of dram less mobile flash storage ff995292 3000 ko fully harnessing the performance potential of dram less mobile flash storage ff995292 INST 102 ko INST