libbb/sha1: shrink x86 hardware accelerated hashing (32-bit)

function                                             old     new   delta
sha1_process_block64_shaNI                           511     507      -4

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

2 files changed, 5 insertions, 7 deletions

diff --git a/libbb/hash_md5_sha_x86-32_shaNI.S b/libbb/hash_md5_sha_x86-32_shaNI.S
index ad814a21b..a61b3cbed 100644
--- a/libbb/hash_md5_sha_x86-32_shaNI.S
+++ b/libbb/hash_md5_sha_x86-32_shaNI.S
@@ -53,8 +53,8 @@ sha1_process_block64_shaNI:
         pshufb          %xmm7, MSG3
 
         /* Save hash values for addition after rounds */
-        movu128         E0, %xmm7
-        /*movu128       ABCD, %xmm8 - NOPE, 32bit has no xmm8 */
+        mova128         E0, %xmm7
+        /*mova128       ABCD, %xmm8 - NOPE, 32bit has no xmm8 */
 
         /* Rounds 0-3 */
                 paddd           MSG0, E0
@@ -207,12 +207,11 @@ sha1_process_block64_shaNI:
         /* Add current hash values with previously saved */
         sha1nexte       %xmm7, E0
         /*paddd         %xmm8, ABCD - 32-bit mode has no xmm8 */
-        movu128         76(%eax), %xmm7         # recreate original ABCD
-        shuf128_32      $0x1B, %xmm7, %xmm7     #  DCBA -> ABCD
-        paddd           %xmm7, ABCD
+        movu128         76(%eax), %xmm7 # get original ABCD (not shuffled)...
 
         /* Write hash values back in the correct order */
         shuf128_32      $0x1B, ABCD, ABCD
+        paddd           %xmm7, ABCD     # ...add it to final ABCD
         movu128         ABCD, 76(%eax)
         extr128_32      $3, E0, 76+4*4(%eax)
 
diff --git a/libbb/hash_md5_sha_x86-64_shaNI.S b/libbb/hash_md5_sha_x86-64_shaNI.S
index fc2ca92e8..b32029360 100644
--- a/libbb/hash_md5_sha_x86-64_shaNI.S
+++ b/libbb/hash_md5_sha_x86-64_shaNI.S
@@ -36,9 +36,8 @@
         .balign 8       # allow decoders to fetch at least 2 first insns
 sha1_process_block64_shaNI:
         /* load initial hash values */
-
-        xor128          E0, E0
         movu128         80(%rdi), ABCD
+        xor128          E0, E0
         pinsrd          $3, 80+4*4(%rdi), E0    # load to uppermost 32-bit word
         shuf128_32      $0x1B, ABCD, ABCD       # DCBA -> ABCD