Download video

ASPLOS'23 - Session 5C - FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks

330 views

ACM SIGARCH

2 years ago

ASPLOS'23 - Session 5C - FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks

ASPLOS'23 - Session 5C - FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks

ASPLOS'23 - Session 5C - FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks
12:09
ASPLOS'23 - Session 5C - FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks
by ACM SIGARCH
ASPLOS'23 - Session 2A - Graphene: An IR for Optimized Tensor Computations on GPUs
14:40
ASPLOS'23 - Session 2A - Graphene: An IR for Optimized Tensor Computations on GPUs
by ACM SIGARCH
ASPLOS'23 - Session 2B - Scoped Buffered Persistency Model for GPUs
14:25
ASPLOS'23 - Session 2B - Scoped Buffered Persistency Model for GPUs
by ACM SIGARCH
ASPLOS'23 - Session 5C - TLP: A Deep Learning-based Cost Model for Tensor Program Tuning
10:33
ASPLOS'23 - Session 5C - TLP: A Deep Learning-based Cost Model for Tensor Program Tuning
by ACM SIGARCH
ASPLOS'23 - Session 5B - Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices
11:35
ASPLOS'23 - Session 5B - Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices
by ACM SIGARCH
ASPLOS'23 - Session 2A - TiLT: A Time-Centric Approach for Stream Query Optimization and Paralleliza
11:40
ASPLOS'23 - Session 2A - TiLT: A Time-Centric Approach for Stream Query Optimization and Paralleliza
by ACM SIGARCH
ASPLOS'23 - Session 5C - TensorIR: An Abstraction for Automatic Tensorized Program Optimization
11:13
ASPLOS'23 - Session 5C - TensorIR: An Abstraction for Automatic Tensorized Program Optimization
by ACM SIGARCH
ASPLOS'23 - Session 2B - DefT: Boosting Scalability of Deformable Convolution Operations on GPUs
14:42
ASPLOS'23 - Session 2B - DefT: Boosting Scalability of Deformable Convolution Operations on GPUs
by ACM SIGARCH
Portugal vs Spain 2-2 (PEN 5-3) Highlights \& All Goals 2025 HD
12:02
Portugal vs Spain 2-2 (PEN 5-3) Highlights \& All Goals 2025 HD
by MONCIF | منصف
ASPLOS'23 - Keynote by by Abhishek Bhattacharjee, Yale University
57:56
ASPLOS'23 - Keynote by by Abhishek Bhattacharjee, Yale University
by ACM SIGARCH
ASPLOS'24 - Session 11D - More Processing-In-Memory
1:02:56
ASPLOS'24 - Session 11D - More Processing-In-Memory
by ACM SIGARCH
ASPLOS'23 - Session 5B - RAIZN: Redundant Array of Independent Zoned Namespaces
11:14
ASPLOS'23 - Session 5B - RAIZN: Redundant Array of Independent Zoned Namespaces
by ACM SIGARCH
ASPLOS'23 - Session 7B - Going Beyond the Limits of SFI: Flexible Hardware-Assisted In-Process Isola
13:02
ASPLOS'23 - Session 7B - Going Beyond the Limits of SFI: Flexible Hardware-Assisted In-Process Isola
by ACM SIGARCH
ASPLOS'23 - Session 2C - AQUATOPE: QoS-and-Uncertainty-Aware Resource Management for Multi-stage Ser
11:34
ASPLOS'23 - Session 2C - AQUATOPE: QoS-and-Uncertainty-Aware Resource Management for Multi-stage Ser
by ACM SIGARCH
ASPLOS'23 - Session 5A - Compilation Consistency Modulo Debug Information
11:42
ASPLOS'23 - Session 5A - Compilation Consistency Modulo Debug Information
by ACM SIGARCH
ASPLOS'23 - Session 7B - Protect the System Call, Protect (most of) the World with BASTION
11:46
ASPLOS'23 - Session 7B - Protect the System Call, Protect (most of) the World with BASTION
by ACM SIGARCH
ASPLOS'23 - Session 2B - MSCCLang: Microsoft Collective Communication Language
14:02
ASPLOS'23 - Session 2B - MSCCLang: Microsoft Collective Communication Language
by ACM SIGARCH
ASPLOS'23 - Session 5C - Mobius: Fine Tuning Large-scale Models on Commodity GPU Servers
12:07
ASPLOS'23 - Session 5C - Mobius: Fine Tuning Large-scale Models on Commodity GPU Servers
by ACM SIGARCH
ASPLOS'23 - Session 3A - Junkyard Computing: Repurposing Discarded Smartphones to Minimize Carbon
12:41
ASPLOS'23 - Session 3A - Junkyard Computing: Repurposing Discarded Smartphones to Minimize Carbon
by ACM SIGARCH
ASPLOS'23 - Session 2A - Beyond Static Parallel Loops: Supporting Dynamic Task Parallelism on Manyco
12:02
ASPLOS'23 - Session 2A - Beyond Static Parallel Loops: Supporting Dynamic Task Parallelism on Manyco
by ACM SIGARCH
ASPLOS'23 - Session 4B - Revisiting Log-structured Merging for KV Stores in Hybrid Memory Systems
11:59
ASPLOS'23 - Session 4B - Revisiting Log-structured Merging for KV Stores in Hybrid Memory Systems
by ACM SIGARCH
ASPLOS'23 - Session 2C - BeeHive: Sub-second Elasticity for Web Services with Semi-FaaS Execution
11:33
ASPLOS'23 - Session 2C - BeeHive: Sub-second Elasticity for Web Services with Semi-FaaS Execution
by ACM SIGARCH