[PATCH 2/3] block-sha1: split the different "hacks" to be individually selected
- From
Nicolas Pitre <nico@cam.org>
- Date
- Aug 12, 2009, 19:46 UTC
- Message-ID
- <alpine.LFD.2.00.0908121545530.10633@xanadu.home>
This is to make it easier for them to be selected individually depending on the architecture instead of the other way around i.e. having each architecture select a list of hacks up front. That makes for clearer documentation as well.
Signed-off-by: Nicolas Pitre <nico@cam.org> --- block-sha1/sha1.c | 23 ++++++++++++++++++----- 1 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/block-sha1/sha1.c b/block-sha1/sha1.c index c3f1ae5..67c9bd0 100644 --- a/block-sha1/sha1.c +++ b/block-sha1/sha1.c @@ -11,10 +11,16 @@ #if defined(__i386__) || defined(__x86_64__) +/* + * Force usage of rol or ror by selecting the one with the smaller constant. + * It _can_ generate slightly smaller code (a constant of 1 is special), but + * perhaps more importantly it's possibly faster on any uarch that does a + * rotate with a loop. + */ + #define SHA_ASM(op, x, n) ({ unsigned int __res; __asm__(op " %1,%0":"=r" (__res):"i" (n), "0" (x)); __res; }) #define SHA_ROL(x,n) SHA_ASM("rol", x, n) #define SHA_ROR(x,n) SHA_ASM("ror", x, n) -#define SMALL_REGISTER_SET #else @@ -24,9 +30,6 @@ #endif -/* This "rolls" over the 512-bit array */ -#define W(x) (array[(x)&15]) - /* * If you have 32 registers or more, the compiler can (and should) * try to change the array[] accesses into registers. However, on @@ -43,13 +46,23 @@ * Ben Herrenschmidt reports that on PPC, the C version comes close * to the optimized asm with this (ie on PPC you don't want that * 'volatile', since there are lots of registers). + * + * On ARM we get the best code generation by forcing a full memory barrier + * between each SHA_ROUND, otherwise gcc happily get wild with spilling and + * the stack frame size simply explode and performance goes down the drain. */ -#ifdef SMALL_REGISTER_SET + +#if defined(__i386__) || defined(__x86_64__) #define setW(x, val) (*(volatile unsigned int *)&W(x) = (val)) +#elif defined(__arm__) + #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0) #else #define setW(x, val) (W(x) = (val)) #endif +/* This "rolls" over the 512-bit array */ +#define W(x) (array[(x)&15]) + /* * Where do we get the source from? The first 16 iterations get it from * the input data, the next mix it from the 512-bit array.
-- 1.6.4.189.g282fa