[PATCH] PPC assembly implementation of SHA1

Here is a SHA1 implementation with the core written in PPC assembly.
On my 2GHz G5, it does 218MB/s, compared to 135MB/s for the openssl
version or 45MB/s for the mozilla version.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 72 insertions, 0 deletions

diff --git a/ppc/sha1.c b/ppc/sha1.c
new file mode 100644
index 0000000000..5ba4fc5259
--- /dev/null
+++ b/ppc/sha1.c
@@ -0,0 +1,72 @@
+/*
+ * SHA-1 implementation.
+ *
+ * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
+ *
+ * This version assumes we are running on a big-endian machine.
+ * It calls an external sha1_core() to process blocks of 64 bytes.
+ */
+#include <stdio.h>
+#include <string.h>
+#include "sha1.h"
+
+extern void sha1_core(uint32_t *hash, const unsigned char *p,
+		      unsigned int nblocks);
+
+int SHA1_Init(SHA_CTX *c)
+{
+	c->hash[0] = 0x67452301;
+	c->hash[1] = 0xEFCDAB89;
+	c->hash[2] = 0x98BADCFE;
+	c->hash[3] = 0x10325476;
+	c->hash[4] = 0xC3D2E1F0;
+	c->len = 0;
+	c->cnt = 0;
+	return 0;
+}
+
+int SHA1_Update(SHA_CTX *c, const void *ptr, unsigned long n)
+{
+	unsigned long nb;
+	const unsigned char *p = ptr;
+
+	c->len += n << 3;
+	while (n != 0) {
+		if (c->cnt || n < 64) {
+			nb = 64 - c->cnt;
+			if (nb > n)
+				nb = n;
+			memcpy(&c->buf.b[c->cnt], p, nb);
+			if ((c->cnt += nb) == 64) {
+				sha1_core(c->hash, c->buf.b, 1);
+				c->cnt = 0;
+			}
+		} else {
+			nb = n >> 6;
+			sha1_core(c->hash, p, nb);
+			nb <<= 6;
+		}
+		n -= nb;
+		p += nb;
+	}
+	return 0;
+}	
+
+int SHA1_Final(unsigned char *hash, SHA_CTX *c)
+{
+	unsigned int cnt = c->cnt;
+
+	c->buf.b[cnt++] = 0x80;
+	if (cnt > 56) {
+		if (cnt < 64)
+			memset(&c->buf.b[cnt], 0, 64 - cnt);
+		sha1_core(c->hash, c->buf.b, 1);
+		cnt = 0;
+	}
+	if (cnt < 56)
+		memset(&c->buf.b[cnt], 0, 56 - cnt);
+	c->buf.l[7] = c->len;
+	sha1_core(c->hash, c->buf.b, 1);
+	memcpy(hash, c->hash, 20);
+	return 0;
+}