All of lore.kernel.org
 help / color / mirror / Atom feed
From: Linus Torvalds <torvalds@linux-foundation.org>
To: Git Mailing List <git@vger.kernel.org>,
	Junio C Hamano <gitster@pobox.com>
Subject: [PATCH 2/7] block-sha1: try to use rol/ror appropriately
Date: Thu, 6 Aug 2009 08:16:52 -0700 (PDT)	[thread overview]
Message-ID: <alpine.LFD.2.01.0908060815430.3390@localhost.localdomain> (raw)
In-Reply-To: <alpine.LFD.2.01.0908060814050.3390@localhost.localdomain>



From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Aug 2009 19:42:15 -0700
Subject: [PATCH 2/7] block-sha1: try to use rol/ror appropriately

Use 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.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---

Ok, this is the hackiest of the bunch. I considered dropping it. But I do 
suspect we want something like this, even if we might end up massaging the 
asm for different compilers etc.

 block-sha1/sha1.c |   32 ++++++++++++++++++++++----------
 1 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/block-sha1/sha1.c b/block-sha1/sha1.c
index eef32f7..a45a3de 100644
--- a/block-sha1/sha1.c
+++ b/block-sha1/sha1.c
@@ -80,7 +80,19 @@ void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
 		((unsigned int *)hashout)[i] = htonl(ctx->H[i]);
 }
 
-#define SHA_ROT(X,n) (((X) << (n)) | ((X) >> (32-(n))))
+#if defined(__i386__) || defined(__x86_64__)
+
+#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)
+
+#else
+
+#define SHA_ROT(X,n)	(((X) << (l)) | ((X) >> (r)))
+#define SHA_ROL(X,n)	SHA_ROT(X,n,32-(n))
+#define SHA_ROR(X,n)	SHA_ROT(X,32-(n),n)
+
+#endif
 
 static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 {
@@ -93,7 +105,7 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 
 	/* Unroll it? */
 	for (t = 16; t <= 79; t++)
-		W[t] = SHA_ROT(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
+		W[t] = SHA_ROL(W[t-3] ^ W[t-8] ^ W[t-14] ^ W[t-16], 1);
 
 	A = ctx->H[0];
 	B = ctx->H[1];
@@ -102,8 +114,8 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 	E = ctx->H[4];
 
 #define T_0_19(t) \
-	TEMP = SHA_ROT(A,5) + (((C^D)&B)^D)     + E + W[t] + 0x5a827999; \
-	E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+	TEMP = SHA_ROL(A,5) + (((C^D)&B)^D)     + E + W[t] + 0x5a827999; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	T_0_19( 0); T_0_19( 1); T_0_19( 2); T_0_19( 3); T_0_19( 4);
 	T_0_19( 5); T_0_19( 6); T_0_19( 7); T_0_19( 8); T_0_19( 9);
@@ -111,8 +123,8 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 	T_0_19(15); T_0_19(16); T_0_19(17); T_0_19(18); T_0_19(19);
 
 #define T_20_39(t) \
-	TEMP = SHA_ROT(A,5) + (B^C^D)           + E + W[t] + 0x6ed9eba1; \
-	E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+	TEMP = SHA_ROL(A,5) + (B^C^D)           + E + W[t] + 0x6ed9eba1; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	T_20_39(20); T_20_39(21); T_20_39(22); T_20_39(23); T_20_39(24);
 	T_20_39(25); T_20_39(26); T_20_39(27); T_20_39(28); T_20_39(29);
@@ -120,8 +132,8 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 	T_20_39(35); T_20_39(36); T_20_39(37); T_20_39(38); T_20_39(39);
 
 #define T_40_59(t) \
-	TEMP = SHA_ROT(A,5) + ((B&C)|(D&(B|C))) + E + W[t] + 0x8f1bbcdc; \
-	E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+	TEMP = SHA_ROL(A,5) + ((B&C)|(D&(B|C))) + E + W[t] + 0x8f1bbcdc; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	T_40_59(40); T_40_59(41); T_40_59(42); T_40_59(43); T_40_59(44);
 	T_40_59(45); T_40_59(46); T_40_59(47); T_40_59(48); T_40_59(49);
@@ -129,8 +141,8 @@ static void blk_SHA1Block(blk_SHA_CTX *ctx, const unsigned int *data)
 	T_40_59(55); T_40_59(56); T_40_59(57); T_40_59(58); T_40_59(59);
 
 #define T_60_79(t) \
-	TEMP = SHA_ROT(A,5) + (B^C^D)           + E + W[t] + 0xca62c1d6; \
-	E = D; D = C; C = SHA_ROT(B, 30); B = A; A = TEMP;
+	TEMP = SHA_ROL(A,5) + (B^C^D)           + E + W[t] + 0xca62c1d6; \
+	E = D; D = C; C = SHA_ROR(B, 2); B = A; A = TEMP;
 
 	T_60_79(60); T_60_79(61); T_60_79(62); T_60_79(63); T_60_79(64);
 	T_60_79(65); T_60_79(66); T_60_79(67); T_60_79(68); T_60_79(69);
-- 
1.6.4.31.g154b2.dirty

  reply	other threads:[~2009-08-06 15:17 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-06 15:13 [PATCH 0/7] block-sha1: improved SHA1 hashing Linus Torvalds
2009-08-06 15:15 ` [PATCH 1/7] block-sha1: add new optimized C 'block-sha1' routines Linus Torvalds
2009-08-06 15:16   ` Linus Torvalds [this message]
2009-08-06 15:18     ` [PATCH 3/7] block-sha1: make the 'ntohl()' part of the first SHA1 loop Linus Torvalds
2009-08-06 15:20       ` [PATCH 4/7] block-sha1: re-use the temporary array as we calculate the SHA1 Linus Torvalds
2009-08-06 15:22         ` [PATCH 5/7] block-sha1: macroize the rounds a bit further Linus Torvalds
2009-08-06 15:24           ` [PATCH 6/7] block-sha1: Use '(B&C)+(D&(B^C))' instead of '(B&C)|(D&(B|C))' in round 3 Linus Torvalds
2009-08-06 15:25             ` [PATCH 7/7] block-sha1: get rid of redundant 'lenW' context Linus Torvalds
2009-08-06 18:25     ` [PATCH 2/7] block-sha1: try to use rol/ror appropriately Bert Wesarg
2009-08-06 17:22 ` [PATCH 0/7] block-sha1: improved SHA1 hashing Artur Skawina
2009-08-06 18:09   ` Linus Torvalds
2009-08-06 19:10     ` Artur Skawina
2009-08-06 19:41       ` Linus Torvalds
2009-08-06 20:08         ` Artur Skawina
2009-08-06 20:53           ` Linus Torvalds
2009-08-06 21:24             ` Linus Torvalds
2009-08-06 21:39             ` Artur Skawina
2009-08-06 21:52               ` Artur Skawina
2009-08-06 22:27                 ` Linus Torvalds
2009-08-06 22:33                   ` Linus Torvalds
2009-08-06 23:19                     ` Artur Skawina
2009-08-06 23:42                       ` Linus Torvalds
2009-08-06 22:55                   ` Artur Skawina
2009-08-06 23:04                     ` Linus Torvalds
2009-08-06 23:25                       ` Linus Torvalds
2009-08-07  0:13                         ` Linus Torvalds
2009-08-07  1:30                           ` Artur Skawina
2009-08-07  1:55                             ` Linus Torvalds
2009-08-07  0:53                         ` Artur Skawina
2009-08-07  2:23                   ` Linus Torvalds
2009-08-07  4:16                     ` Artur Skawina
     [not found]                     ` <alpine.LFD.2.01.0908071614310.3288@localhost.localdomain>
     [not found]                       ` <4A7CBD28.6070306@gmail.com>
     [not found]                         ` <4A7CBF47.9000903@gmail.com>
     [not found]                           ` <alpine.LFD.2.01.0908071700290.3288@localhost.localdomain>
     [not found]                             ` <4A7CC380.3070008@gmail.com>
2009-08-08  4:16                               ` Linus Torvalds
2009-08-08  5:34                                 ` Artur Skawina
2009-08-08 17:10                                   ` Linus Torvalds
2009-08-08 18:12                                     ` Artur Skawina
2009-08-08 22:58                                   ` Artur Skawina
2009-08-08 23:36                                     ` Artur Skawina

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.LFD.2.01.0908060815430.3390@localhost.localdomain \
    --to=torvalds@linux-foundation.org \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.