question on cache eviction

King_Crimson — Sun, 17 Jan 2016 03:57:09 GMT

I'm experimenting on cache eviction in my code using _mm_clevict(), and have the following observations:

(1) if data are evicted from L1 alone (_MM_HINT_T0), the code is slowed by ~30%.

(2) if data are evicted from L2 alone (_MM_HINT_T1), the code is slowed by ~70%.

(3) if data are evicted from both L1 and L2, the code is still slowed by ~70%.

I'm confused by (3), as I think some additional loads should miss both L1 and L2 compared to (2), which should cause further latency. Any thoughts? Thanks!

The caches are inclusive,

James_C_Intel2 — Mon, 18 Jan 2016 09:47:16 GMT

The caches are inclusive, therefore eviction from the L2$ implies eviction from the L1$ too. Your last two cases are therefore identical (give or take the extra eviction instructions you execute!)

topic question on cache eviction in Software Archive

question on cache eviction

The caches are inclusive,