libbb/sha256: code shrink in 32-bit x86

function                                             old     new   delta
sha256_process_block64_shaNI                         697     676     -21

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
diff --git a/libbb/hash_md5_sha256_x86-32_shaNI.S b/libbb/hash_md5_sha256_x86-32_shaNI.S
index a849dfc..846230e 100644
--- a/libbb/hash_md5_sha256_x86-32_shaNI.S
+++ b/libbb/hash_md5_sha256_x86-32_shaNI.S
@@ -34,16 +34,18 @@
 
 #define XMMTMP		%xmm7
 
+#define SHUF(a,b,c,d) $(a+(b<<2)+(c<<4)+(d<<6))
+
 	.balign	8	# allow decoders to fetch at least 2 first insns
 sha256_process_block64_shaNI:
-	movu128		76+0*16(%eax), STATE0
-	movu128		76+1*16(%eax), STATE1
 
-	shuf128_32	$0xB1, STATE0, STATE0		/* CDAB */
-	shuf128_32	$0x1B, STATE1, STATE1		/* EFGH */
+	movu128		76+0*16(%eax), STATE1 /* DCBA (msb-to-lsb: 3,2,1,0) */
+	movu128		76+1*16(%eax), STATE0 /* HGFE */
+/* shufps takes dwords 0,1 from *2nd* operand, and dwords 2,3 from 1st one */
 	mova128		STATE0, XMMTMP
-	palignr		$8, STATE1, STATE0		/* ABEF */
-	pblendw		$0xF0, XMMTMP, STATE1		/* CDGH */
+	shufps		SHUF(1,0,1,0), STATE1, STATE0 /* ABEF */
+	shufps		SHUF(3,2,3,2), STATE1, XMMTMP /* CDGH */
+	mova128		XMMTMP, STATE1
 
 /* XMMTMP holds flip mask from here... */
 	mova128		PSHUFFLE_BSWAP32_FLIP_MASK, XMMTMP
@@ -231,18 +233,19 @@
 		sha256rnds2	STATE1, STATE0
 
 	/* Write hash values back in the correct order */
-	shuf128_32	$0x1B, STATE0, STATE0		/* FEBA */
-	shuf128_32	$0xB1, STATE1, STATE1		/* DCHG */
+	/* STATE0: ABEF (msb-to-lsb: 3,2,1,0) */
+	/* STATE1: CDGH */
 	mova128		STATE0, XMMTMP
-	pblendw		$0xF0, STATE1, STATE0		/* DCBA */
-	palignr		$8, XMMTMP, STATE1		/* HGFE */
+/* shufps takes dwords 0,1 from *2nd* operand, and dwords 2,3 from 1st one */
+	shufps		SHUF(3,2,3,2), STATE1, STATE0 /* DCBA */
+	shufps		SHUF(1,0,1,0), STATE1, XMMTMP /* HGFE */
 	/* add current hash values to previous ones */
-	movu128		76+0*16(%eax), XMMTMP
-	paddd		XMMTMP, STATE0
-	movu128		76+1*16(%eax), XMMTMP
-	movu128		STATE0, 76+0*16(%eax)
+	movu128		76+1*16(%eax), STATE1
 	paddd		XMMTMP, STATE1
 	movu128		STATE1, 76+1*16(%eax)
+	movu128		76+0*16(%eax), XMMTMP
+	paddd		XMMTMP, STATE0
+	movu128		STATE0, 76+0*16(%eax)
 
 	ret
 	.size	sha256_process_block64_shaNI, .-sha256_process_block64_shaNI