From 41e2d8784195d4a1c730fea9f3c197f34a11cb97 Mon Sep 17 00:00:00 2001
From: Deepankar Bhattacharjee <deepankar.b@in.ibm.com>
Date: Mon, 20 Sep 2021 10:45:15 -0400
Subject: chacha20 performance optimizations for ppc64le with 8x lanes,
 Performance increase around 50%.

Co-authored-by: Madhusudhanan Duraisamy <madurais@in.ibm.com>

Co-authored-by: Nilamjyoti Goswami <nilamgoswami@in.ibm.com>

Co-authored-by: Siva Sundar Anbareeswaran <srisivasundar@in.ibm.com>

Reviewed-by: Danny Tsen <dtsen@us.ibm.com>
Tested-by: Danny Tsen <dtsen@us.ibm.com>
Signed-off-by: Danny <dtsen@us.ibm.com>

Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16637)

(cherry picked from commit f596bbe4da779b56eea34d96168b557d78e1149a)
---
 crypto/ppccpuid.pl | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'crypto/ppccpuid.pl')

diff --git a/crypto/ppccpuid.pl b/crypto/ppccpuid.pl
index c6555df5d8..706164adba 100755
--- a/crypto/ppccpuid.pl
+++ b/crypto/ppccpuid.pl
@@ -81,6 +81,17 @@ $code=<<___;
 	.long	0
 	.byte	0,12,0x14,0,0,0,0,0
 
+.globl	.OPENSSL_brd31_probe
+.align	4
+.OPENSSL_brd31_probe:
+	xor	r0,r0,r0
+	brd	r3,r0
+	blr
+	.long	0
+	.byte	0,12,0x14,0,0,0,0,0
+.size	.OPENSSL_brd31_probe,.-.OPENSSL_brd31_probe
+
+
 .globl	.OPENSSL_wipe_cpu
 .align	4
 .OPENSSL_wipe_cpu:
-- 
cgit v1.2.3