Stafford Horne f5d45dc911 openrisc: Add optimized memcpy routine ... The generic memcpy routine provided in kernel does only byte copies. Using word copies we can lower boot time and cycles spend in memcpy quite significantly. Booting on my de0 nano I see boot times go from 7.2 to 5.6 seconds. The avg cycles in memcpy during boot go from 6467 to 1887. I tested several algorithms (see code in previous patch mails) The implementations I tested and avg cycles: - Word Copies + Loop Unrolls + Non Aligned 1882 - Word Copies + Loop Unrolls 1887 - Word Copies 2441 - Byte Copies + Loop Unrolls 6467 - Byte Copies 7600 In the end I ended up going with Word Copies + Loop Unrolls as it provides best tradeoff between simplicity and boot speedups. Signed-off-by: Stafford Horne <shorne@gmail.com>		2017-02-25 04:14:36 +09:00
..
bitops	openrisc: add atomic bitops	2017-02-25 04:12:38 +09:00
Kbuild	openrisc: add futex_atomic_* implementations	2017-02-25 04:14:23 +09:00
asm-offsets.h	…
atomic.h	openrisc: add optimized atomic operations	2017-02-25 04:14:06 +09:00
bitops.h	openrisc: add atomic bitops	2017-02-25 04:12:38 +09:00
cache.h	…
cmpxchg.h	openrisc: add cmpxchg and xchg implementations	2017-02-25 04:14:00 +09:00
cpuinfo.h	…
delay.h	…
dma-mapping.h	…
elf.h	…
fixmap.h	…
futex.h	openrisc: add futex_atomic_* implementations	2017-02-25 04:14:23 +09:00
io.h	…
irq.h	…
irqflags.h	…
linkage.h	…
mmu.h	…
mmu_context.h	…
page.h	…
pgalloc.h	…
pgtable.h	…
processor.h	…
ptrace.h	…
serial.h	…
spinlock.h	…
spr.h	…
spr_defs.h	openrisc: Fix the bitmask for the unit present register	2017-02-25 04:14:34 +09:00
string.h	openrisc: Add optimized memcpy routine	2017-02-25 04:14:36 +09:00
syscall.h	…
syscalls.h	…
thread_info.h	…
timex.h	…
tlb.h	…
tlbflush.h	…
uaccess.h	…
unaligned.h	…