PPC assembly pack: add POWER9 results.

Reviewed-by: Rich Salz <rsalz@openssl.org>

9 files changed, 11 insertions, 4 deletions

diff --git a/crypto/aes/asm/aesp8-ppc.pl b/crypto/aes/asm/aesp8-ppc.pl
index 7463df6c17..e1be23ab75 100755
--- a/crypto/aes/asm/aesp8-ppc.pl
+++ b/crypto/aes/asm/aesp8-ppc.pl
@@ -40,6 +40,7 @@
 #		CBC en-/decrypt	CTR	XTS
 # POWER8[le]	3.96/0.72	0.74	1.1
 # POWER8[be]	3.75/0.65	0.66	1.0
+# POWER9[le]	3.05/0.65	0.65	0.80
 
 $flavour = shift;
 
diff --git a/crypto/chacha/asm/chacha-ppc.pl b/crypto/chacha/asm/chacha-ppc.pl
index f972ee471a..af2f037c15 100755
--- a/crypto/chacha/asm/chacha-ppc.pl
+++ b/crypto/chacha/asm/chacha-ppc.pl
@@ -27,6 +27,7 @@
 # PPC970/G5		9.29/+160%	4.60
 # POWER7		8.62/+61%	4.27
 # POWER8		8.70/+51%	3.96
+# POWER9		6.61/+29%	3.67
 
 $flavour = shift;
 
diff --git a/crypto/modes/asm/ghashp8-ppc.pl b/crypto/modes/asm/ghashp8-ppc.pl
index 45c6438497..a1d5789cc8 100755
--- a/crypto/modes/asm/ghashp8-ppc.pl
+++ b/crypto/modes/asm/ghashp8-ppc.pl
@@ -30,6 +30,7 @@
 # 2x aggregated reduction improves performance by 50% (resulting
 # performance on POWER8 is 1 cycle per processed byte), and 4x
 # aggregated reduction - by 170% or 2.7x (resulting in 0.55 cpb).
+# POWER9 delivers 0.40 cpb.
 
 $flavour=shift;
 $output =shift;
diff --git a/crypto/poly1305/asm/poly1305-ppc.pl b/crypto/poly1305/asm/poly1305-ppc.pl
index ab65910282..8e105d77fb 100755
--- a/crypto/poly1305/asm/poly1305-ppc.pl
+++ b/crypto/poly1305/asm/poly1305-ppc.pl
@@ -28,6 +28,7 @@
 # PPC970		7.00/+114%	3.51/+205%
 # POWER7		3.75/+260%	1.93/+100%
 # POWER8		-		2.03/+200%
+# POWER9		-		1.56/+150%
 #
 # Do we need floating-point implementation for PPC? Results presented
 # in poly1305_ieee754.c are tricky to compare to, because they are for
diff --git a/crypto/poly1305/asm/poly1305-ppcfp.pl b/crypto/poly1305/asm/poly1305-ppcfp.pl
index 49f70a8c03..fc62baa222 100755
--- a/crypto/poly1305/asm/poly1305-ppcfp.pl
+++ b/crypto/poly1305/asm/poly1305-ppcfp.pl
@@ -26,6 +26,7 @@
 # PPC970		6.03/+80%
 # POWER7		3.50/+30%
 # POWER8		3.75/+10%
+# POWER9		2.80/+12%
 
 $flavour = shift;
 
diff --git a/crypto/poly1305/poly1305_ieee754.c b/crypto/poly1305/poly1305_ieee754.c
index 995a02e5c1..1a06e03558 100644
--- a/crypto/poly1305/poly1305_ieee754.c
+++ b/crypto/poly1305/poly1305_ieee754.c
@@ -38,6 +38,7 @@
  * POWER6               4.92
  * POWER7               4.50
  * POWER8               4.10
+ * POWER9               3.14
  *
  * z10                  11.2
  * z196+                7.30
diff --git a/crypto/sha/asm/keccak1600-ppc64.pl b/crypto/sha/asm/keccak1600-ppc64.pl
index f89f71c825..60ed2f2326 100755
--- a/crypto/sha/asm/keccak1600-ppc64.pl
+++ b/crypto/sha/asm/keccak1600-ppc64.pl
@@ -30,6 +30,7 @@
 # PPC970/G5	14.6/+120%
 # POWER7	10.3/+100%
 # POWER8	11.5/+85%
+# POWER9	7.2/+45%
 #
 # (*)	Corresponds to SHA3-256. Percentage after slash is improvement
 #	over gcc-4.x-generated KECCAK_1X_ALT code. Newer compilers do
diff --git a/crypto/sha/asm/keccak1600p8-ppc.pl b/crypto/sha/asm/keccak1600p8-ppc.pl
index feec68839f..95e6242f99 100755
--- a/crypto/sha/asm/keccak1600p8-ppc.pl
+++ b/crypto/sha/asm/keccak1600p8-ppc.pl
@@ -23,7 +23,7 @@
 # buffer for r=1088, which matches SHA3-256. This is 17% better than
 # scalar PPC64 code. It probably should be noted that if POWER8's
 # successor can achieve higher scalar instruction issue rate, then
-# this module will loose...
+# this module will loose... And it does on POWER9 with 8.8 vs. 7.2.
 
 $flavour = shift;
 
diff --git a/crypto/sha/asm/sha512p8-ppc.pl b/crypto/sha/asm/sha512p8-ppc.pl
index 93dfef20a9..e6e9467905 100755
--- a/crypto/sha/asm/sha512p8-ppc.pl
+++ b/crypto/sha/asm/sha512p8-ppc.pl
@@ -36,9 +36,9 @@
 # little-endian system]. Numbers in square brackets are for 64-bit
 # build of sha512-ppc.pl, presented for reference.
 #
-#		POWER8
-# SHA256	9.9 [15.8]
-# SHA512	6.3 [10.3]
+#		POWER8		POWER9
+# SHA256	9.9 [15.8]	9.2 [9.3]
+# SHA512	6.3 [10.3]	5.8 [5.9]
 
 $flavour=shift;
 $output =shift;