27 Facts About L2 cache

1.

CPU cache is a hardware cache used by the central processing unit of a computer to reduce the average cost to access data from the main memory.

FactSnippet No. 1,584,030
2.

The L2 cache memory is typically implemented with static random-access memory, in modern CPUs by far the largest part of them by chip area, but SRAM is not always used for all levels, or even any level, sometimes some latter or all levels are implemented with eDRAM.

FactSnippet No. 1,584,031
3.

Split L1 L2 cache started in 1976 with the IBM 801 CPU, became mainstream in the late 1980s, and in 1997 entered the embedded CPU market with the ARMv5TE.

FactSnippet No. 1,584,032
4.

The L2 cache is usually not split and acts as a common repository for the already split L1 cache.

FactSnippet No. 1,584,033
5.

L4 L2 cache is currently uncommon, and is generally on dynamic random-access memory, rather than on static random-access memory, on a separate die or chip.

FactSnippet No. 1,584,034
6.

Alternatively, in a write-back or copy-back L2 cache, writes are not immediately mirrored to the main memory, and the L2 cache instead tracks which locations have been written over, marking them as dirty.

FactSnippet No. 1,584,035
7.

The L2 cache hit rate and the L2 cache miss rate play an important role in determining this performance.

FactSnippet No. 1,584,036
8.

One benefit of this scheme is that the tags stored in the L2 cache do not have to include that part of the main memory address which is implied by the L2 cache memory's index.

FactSnippet No. 1,584,037
9.

Since the L2 cache tags have fewer bits, they require fewer transistors, take less space on the processor circuit board or on the microprocessor chip, and can be read and compared faster.

FactSnippet No. 1,584,038
10.

An effective memory address which goes along with the L2 cache line is split into the tag, the index and the block offset.

FactSnippet No. 1,584,039
11.

An instruction L2 cache requires only one flag bit per L2 cache row entry: a valid bit.

FactSnippet No. 1,584,040
12.

The first hardware L2 cache used in a computer system was not actually a data or instruction L2 cache, but rather a TLB.

FactSnippet No. 1,584,041
13.

Alternatively, if L2 cache entries are allowed on pages not mapped by the TLB, then those entries will have to be flushed when the access rights on those pages are changed in the page table.

FactSnippet No. 1,584,042
14.

Also, during miss processing, the alternate ways of the L2 cache line indexed have to be probed for virtual aliases and any matches evicted.

FactSnippet No. 1,584,043
15.

Since virtual hints have fewer bits than virtual tags distinguishing them from one another, a virtually hinted L2 cache suffers more conflict misses than a virtually tagged L2 cache.

FactSnippet No. 1,584,044
16.

Cache entry replacement policy is determined by a L2 cache algorithm selected to be implemented by the processor designers.

FactSnippet No. 1,584,045
17.

The victim L2 cache is usually fully associative, and is intended to reduce the number of conflict misses.

FactSnippet No. 1,584,046
18.

The main disadvantage of the trace L2 cache, leading to its power inefficiency, is the hardware complexity required for its heuristic deciding on caching and reusing dynamically created instruction traces.

FactSnippet No. 1,584,047
19.

Smart L2 cache is a level 2 or level 3 caching method for multiple execution cores, developed by Intel.

FactSnippet No. 1,584,048
20.

Furthermore, the shared L2 cache makes it faster to share memory among different execution cores.

FactSnippet No. 1,584,049
21.

Typically, sharing the L1 L2 cache is undesirable because the resulting increase in latency would make each core run considerably slower than a single-core chip.

FactSnippet No. 1,584,050
22.

An associative L2 cache is more complicated, because some form of tag must be read to determine which entry of the L2 cache to select.

FactSnippet No. 1,584,051
23.

An N-way set-associative level-1 L2 cache usually reads all N possible tags and N data in parallel, and then chooses the data associated with the matching tag.

FactSnippet No. 1,584,052
24.

Early history of L2 cache technology is closely tied to the invention and use of virtual memory.

FactSnippet No. 1,584,053
25.

The popularity of on-motherboard L2 cache continued through the Pentium MMX era but was made obsolete by the introduction of SDRAM and the growing disparity between bus clock rates and CPU clock rates, which caused on-motherboard L2 cache to be only slightly faster than main memory.

FactSnippet No. 1,584,054
26.

Early L2 cache designs focused entirely on the direct cost of L2 cache and RAM and average execution speed.

FactSnippet No. 1,584,055
27.

Multi-ported L2 cache is a L2 cache which can serve more than one request at a time.

FactSnippet No. 1,584,056