[git commit] libbb/sha256: code shrink in x86 assembly

[Denys Vlasenko]

commit: https://git.busybox.net/busybox/commit/?id=caa9c4f707b661cf398f2c2d66f54f5b0d8adfe2
branch: https://git.busybox.net/busybox/commit/?id=refs/heads/master

function                                             old     new   delta
sha256_process_block64_shaNI 32-bit                  676     673      -3
sha256_process_block64_shaNI 64-bit                  680     677      -3

Signed-off-by: Denys Vlasenko <vda.linux at googlemail.com>
---
 libbb/hash_md5_sha256_x86-32_shaNI.S | 11 +++++------
 libbb/hash_md5_sha256_x86-64_shaNI.S | 11 +++++------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/libbb/hash_md5_sha256_x86-32_shaNI.S b/libbb/hash_md5_sha256_x86-32_shaNI.S
index 846230e3e..aa68193bd 100644
--- a/libbb/hash_md5_sha256_x86-32_shaNI.S
+++ b/libbb/hash_md5_sha256_x86-32_shaNI.S
@@ -39,13 +39,12 @@
 	.balign	8	# allow decoders to fetch at least 2 first insns
 sha256_process_block64_shaNI:
 
-	movu128		76+0*16(%eax), STATE1 /* DCBA (msb-to-lsb: 3,2,1,0) */
-	movu128		76+1*16(%eax), STATE0 /* HGFE */
+	movu128		76+0*16(%eax), XMMTMP /* DCBA (msb-to-lsb: 3,2,1,0) */
+	movu128		76+1*16(%eax), STATE1 /* HGFE */
 /* shufps takes dwords 0,1 from *2nd* operand, and dwords 2,3 from 1st one */
-	mova128		STATE0, XMMTMP
-	shufps		SHUF(1,0,1,0), STATE1, STATE0 /* ABEF */
-	shufps		SHUF(3,2,3,2), STATE1, XMMTMP /* CDGH */
-	mova128		XMMTMP, STATE1
+	mova128		STATE1, STATE0
+	shufps		SHUF(1,0,1,0), XMMTMP, STATE0 /* ABEF */
+	shufps		SHUF(3,2,3,2), XMMTMP, STATE1 /* CDGH */
 
 /* XMMTMP holds flip mask from here... */
 	mova128		PSHUFFLE_BSWAP32_FLIP_MASK, XMMTMP
diff --git a/libbb/hash_md5_sha256_x86-64_shaNI.S b/libbb/hash_md5_sha256_x86-64_shaNI.S
index bc063b9cc..4663f750a 100644
--- a/libbb/hash_md5_sha256_x86-64_shaNI.S
+++ b/libbb/hash_md5_sha256_x86-64_shaNI.S
@@ -42,13 +42,12 @@
 	.balign	8	# allow decoders to fetch at least 2 first insns
 sha256_process_block64_shaNI:
 
-	movu128		80+0*16(%rdi), STATE1 /* DCBA (msb-to-lsb: 3,2,1,0) */
-	movu128		80+1*16(%rdi), STATE0 /* HGFE */
+	movu128		80+0*16(%rdi), XMMTMP /* DCBA (msb-to-lsb: 3,2,1,0) */
+	movu128		80+1*16(%rdi), STATE1 /* HGFE */
 /* shufps takes dwords 0,1 from *2nd* operand, and dwords 2,3 from 1st one */
-	mova128		STATE0, XMMTMP
-	shufps		SHUF(1,0,1,0), STATE1, STATE0 /* ABEF */
-	shufps		SHUF(3,2,3,2), STATE1, XMMTMP /* CDGH */
-	mova128		XMMTMP, STATE1
+	mova128		STATE1, STATE0
+	shufps		SHUF(1,0,1,0), XMMTMP, STATE0 /* ABEF */
+	shufps		SHUF(3,2,3,2), XMMTMP, STATE1 /* CDGH */
 
 /* XMMTMP holds flip mask from here... */
 	mova128		PSHUFFLE_BSWAP32_FLIP_MASK(%rip), XMMTMP