Latest update

crypto/sha/asm/keccak1600-armv8.pl

@@ -731,7 +731,7 @@ $code.=<<___;
 	blo	.Lprocess_block_ce
 	ldr	d31,[$inp],#8		// *inp++
 #ifdef	__AARCH64EB__
-	rev	v31.16b,v31.16b
+	rev64	v31.16b,v31.16b
 #endif
 	eor	$A[$j/5][$j%5],$A[$j/5][$j%5],v31.16b
 	beq	.Lprocess_block_ce
@@ -740,7 +740,7 @@ ___
 $code.=<<___;
 	ldr	d31,[$inp],#8		// *inp++
 #ifdef	__AARCH64EB__
-	rev	v31.16b,v31.16b
+	rev64	v31.16b,v31.16b
 #endif
 	eor	$A[4][4],$A[4][4],v31.16b
 

crypto/sha/asm/sha512-sparcv9.pl

@@ -27,7 +27,7 @@
 # over 2x than 32-bit code. X[16] resides on stack, but access to it
 # is scheduled for L2 latency and staged through 32 least significant
 # bits of %l0-%l7. The latter is done to achieve 32-/64-bit ABI
-# duality. Nevetheless it's ~40% faster than SHA256, which is pretty
+# duality. Nevertheless it's ~40% faster than SHA256, which is pretty
 # good [optimal coefficient is 50%].
 #
 # SHA512 on UltraSPARC T1.