Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

New posts in cpu-architecture

Why is acquire semantics only for reads, not writes? How can an LL/SC acquire CAS take a lock without the store reordering with the critical section?

ARM: Why only 12 bits for immediate constants?

Pipeline diagram, Can ID start if previous EX is using same register?

Does processor stall during cache coherence operation

Why is branch prediction quite accurate?

Is it possible to perform some computations within the RAM?

Calculating average time for a memory access

Why push first decreases the stack pointer?

x86-64 do address calculating mov i.e mov i(r, r, i), r execute on on port 1? Or is it still p0156?

Why do L1 and L2 Cache waste space saving the same data?

Instruction which results in 0 but isn't dependency-breaking [duplicate]

Why is it not possible to read an unaligned word in one step?

Why does std::atomic_compare_exchange update the expected value?

Regarding instruction ordering in executions of cache-miss loads before cache-hit stores on x86

MIPS pipeline timing diagram

Why is this jump instruction so expensive when performing pointer chasing?

Is it possible to implement subroutine call without a stack nor indirect addressing?

Why are 'opcode' field and 'funct' field apart in MIPS?

Why should prefetch queue be invalidated after entering protected mode?

gcc using `lea` instead of `add`