crypto: serpent - add AVX2/x86_64 assembler implementation of serpent cipher

Patch adds AVX2/x86-64 implementation of Serpent cipher, requiring 16 parallel
blocks for input (256 bytes). Implementation is based on the AVX implementation
and extends to use the 256-bit wide YMM registers. Since serpent does not use
table look-ups, this implementation should be close to two times faster than
the AVX implementation.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 15 insertions, 0 deletions

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index fea7841dd6f3..f5e13dea8cc9 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1645,6 +1645,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__cbc-serpent-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__cbc-serpent-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__cbc-serpent-sse2",
                 .test = alg_test_null,
         }, {
@@ -1673,6 +1676,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-cbc-serpent-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-cbc-serpent-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-cbc-serpent-sse2",
                 .test = alg_test_null,
         }, {
@@ -1701,6 +1707,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-ecb-serpent-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-ecb-serpent-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-ecb-serpent-sse2",
                 .test = alg_test_null,
         }, {
@@ -1969,6 +1978,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "cryptd(__driver-cbc-camellia-aesni)",
                 .test = alg_test_null,
         }, {
+                .alg = "cryptd(__driver-cbc-serpent-avx2)",
+                .test = alg_test_null,
+        }, {
                 .alg = "cryptd(__driver-ecb-aes-aesni)",
                 .test = alg_test_null,
                 .fips_allowed = 1,
@@ -1988,6 +2000,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "cryptd(__driver-ecb-serpent-avx)",
                 .test = alg_test_null,
         }, {
+                .alg = "cryptd(__driver-ecb-serpent-avx2)",
+                .test = alg_test_null,
+        }, {
                 .alg = "cryptd(__driver-ecb-serpent-sse2)",
                 .test = alg_test_null,
         }, {