From d0a34aeedff187873e1b42e0902d9dfbba08a1f4 Mon Sep 17 00:00:00 2001 From: Giorgio Vazzana Date: Sat, 18 May 2013 13:53:52 +0200 Subject: [PATCH] md5: optimize second round by using 4-operation form of G() 4-operation form is preferred over 3-operation because it breaks a long dependency chain, thus allowing a superscalar processor to execute more operations in parallel. The idea was taken from: http://www.zorinaq.com/papers/md5-amd64.html AMD Athlon(tm) II X3 450 Processor, x86_64 $ for i in $(seq 1 4); do ./avutil_md5_test2; done size: 1048576 runs: 1024 time: 5.821 +- 0.019 size: 1048576 runs: 1024 time: 5.822 +- 0.019 size: 1048576 runs: 1024 time: 5.841 +- 0.018 size: 1048576 runs: 1024 time: 5.821 +- 0.018 $ for i in $(seq 1 4); do ./avutil_md5_test2; done size: 1048576 runs: 1024 time: 5.646 +- 0.019 size: 1048576 runs: 1024 time: 5.646 +- 0.018 size: 1048576 runs: 1024 time: 5.642 +- 0.019 size: 1048576 runs: 1024 time: 5.641 +- 0.019 Signed-off-by: Michael Niedermayer --- libavutil/md5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavutil/md5.c b/libavutil/md5.c index 7375ce55a5..e3c4981217 100644 --- a/libavutil/md5.c +++ b/libavutil/md5.c @@ -84,7 +84,7 @@ static const uint32_t T[64] = { // T[i]= fabs(sin(i+1)<<32) \ if (i < 32) { \ if (i < 16) a += (d ^ (b & (c ^ d))) + X[ i & 15]; \ - else a += (c ^ (d & (c ^ b))) + X[(1 + 5*i) & 15]; \ + else a += ((d & b) | (~d & c))+ X[(1 + 5*i) & 15]; \ } else { \ if (i < 48) a += (b ^ c ^ d) + X[(5 + 3*i) & 15]; \ else a += (c ^ (b | ~d)) + X[( 7*i) & 15]; \