L1 cache
An L1 cache is the smallest, lowest-latency level of a processor’s cache hierarchy, located closest to a processing core.
GPU Programming with Triton
An L1 cache is a small, hardware-managed cache close to the GPU compute units.
- How it is used
- Explains L1 as a hardware-managed layer that reduces repeated trips to slower GPU memory.
- How deep it goes
- Explains cache placement, reuse, latency, and the shared-memory partitioning trade-off without detailing cache policies.
- Examples
- Uses H100 unified storage and a memory-hierarchy ranking exercise to illustrate L1’s place in the GPU.
- What you can do after
- Evaluate how L1 reuse and shared-memory allocation can affect GPU memory performance.
Latency
An L1 cache is the smallest and fastest cache level located closest to a CPU core.
- How it is used
- Uses L1-cache locality to reason about low-latency execution and data placement on multicore CPUs.
- How deep it goes
- Explains hierarchy, approximate capacities, latency ranges, misses, and tail effects without detailing cache implementation internals.
- Examples
- Uses working-set overflow, instruction fetches, and one-, ten-, and hundred-nanosecond access cases.
- What you can do after
- Evaluate latency-sensitive code by relating working-set size and cache misses to access-time variance and tail latency.
Also covered in
- 100 Go Mistakes and How to Avoid Them
- CUDA for LLMs
- Fast Python: High performance techniques for large datasets
What to know first
- threadA thread is a distinct sequence of execution with its own control flow and state, managed or scheduled by a processor, runtime, or operating system.
- memoryMemory is a storage capability or mechanism for retaining information or computational state for later access or use.
- CPUA central processing unit (CPU) is a computer processor that executes program instructions and performs general-purpose computational operations.
- hardware registerA hardware register is a small, rapidly accessible storage location within a processor or processing device that holds data, addresses, or control information during execution.
Related concepts
- DRAMcontrasts with · DRAM is volatile semiconductor memory that stores each bit in a capacitor-based cell and requires periodic refresh.
- memory hierarchypart of · A memory hierarchy is an arrangement of storage levels with differing capacities, access speeds, latencies, costs, or persistence.
- shared memorycontrasts with · Shared memory is a memory region accessible to multiple processes, threads, or other concurrent execution contexts for sharing data.
- CPU cachekind of · A CPU cache is small, fast memory that stores copies of data or instructions for quicker access by a processor.
- streaming multiprocessorpart of · A streaming multiprocessor is a GPU execution unit that schedules and executes groups of threads using its processing and on-chip memory resources.
- memorycontrasts with · Memory is a storage capability or mechanism for retaining information or computational state for later access or use.
Questions about L1 cache
What is L1 cache?
An L1 cache is the smallest, lowest-latency level of a processor’s cache hierarchy, located closest to a processing core.
Which Manning books explain L1 cache?
GPU Programming with Triton and Latency.
What should I know before learning L1 cache?
Manning books that teach L1 cache usually introduce thread, memory, CPU and hardware register first.
What is the difference between L1 cache and DRAM?
An L1 cache is the smallest, lowest-latency level of a processor’s cache hierarchy, located closest to a processing core. DRAM is volatile semiconductor memory that stores each bit in a capacitor-based cell and requires periodic refresh.
What is L1 cache a kind of?
L1 cache is a kind of CPU cache. A CPU cache is small, fast memory that stores copies of data or instructions for quicker access by a processor.
What is L1 cache part of?
L1 cache is part of memory hierarchy. A memory hierarchy is an arrangement of storage levels with differing capacities, access speeds, latencies, costs, or persistence.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

