Run util/openssl-format-source on the Curve448 code

[openssl.git] / crypto / ec / curve448 / arch_x86_64 / f_impl.c

diff --git a/crypto/ec/curve448/arch_x86_64/f_impl.c b/crypto/ec/curve448/arch_x86_64/f_impl.c
index 1e1d76d6170179bbf7b89821a0e0e3eb7e61a73b..a1c9dbd12259727680e592c831bc1e2177cd1388 100644 (file)
--- a/crypto/ec/curve448/arch_x86_64/f_impl.c
+++ b/crypto/ec/curve448/arch_x86_64/f_impl.c
@@ -1,35 +1,45 @@
-/* Copyright (c) 2014 Cryptography Research, Inc.
- * Released under the MIT License.  See LICENSE.txt for license information.
+/*
+ * Copyright 2017 The OpenSSL Project Authors. All Rights Reserved.
+ * Copyright 2014 Cryptography Research, Inc.
+ *
+ * Licensed under the OpenSSL license (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ *
+ * Originally written by Mike Hamburg

  */
 
 #include "f_field.h"
 
  */
 
 #include "f_field.h"
 

-void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
+void gf_mul(gf_s * __restrict__ cs, const gf as, const gf bs)
+{

     const uint64_t *a = as->limb, *b = bs->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0 = 0, accum1 = 0, accum2;
     const uint64_t *a = as->limb, *b = bs->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0 = 0, accum1 = 0, accum2;

-    uint64_t mask = (1ull<<56) - 1;  
+    uint64_t mask = (1ull << 56) - 1;

 
     uint64_t aa[4] VECTOR_ALIGNED, bb[4] VECTOR_ALIGNED, bbb[4] VECTOR_ALIGNED;
 
     /* For some reason clang doesn't vectorize this without prompting? */
     unsigned int i;
 
     uint64_t aa[4] VECTOR_ALIGNED, bb[4] VECTOR_ALIGNED, bbb[4] VECTOR_ALIGNED;
 
     /* For some reason clang doesn't vectorize this without prompting? */
     unsigned int i;

-    for (i=0; i<sizeof(aa)/sizeof(uint64xn_t); i++) {
-        ((uint64xn_t*)aa)[i] = ((const uint64xn_t*)a)[i] + ((const uint64xn_t*)(&a[4]))[i];
-        ((uint64xn_t*)bb)[i] = ((const uint64xn_t*)b)[i] + ((const uint64xn_t*)(&b[4]))[i]; 
-        ((uint64xn_t*)bbb)[i] = ((const uint64xn_t*)bb)[i] + ((const uint64xn_t*)(&b[4]))[i];     
+    for (i = 0; i < sizeof(aa) / sizeof(uint64xn_t); i++) {
+        ((uint64xn_t *) aa)[i] =
+            ((const uint64xn_t *)a)[i] + ((const uint64xn_t *)(&a[4]))[i];
+        ((uint64xn_t *) bb)[i] =
+            ((const uint64xn_t *)b)[i] + ((const uint64xn_t *)(&b[4]))[i];
+        ((uint64xn_t *) bbb)[i] =
+            ((const uint64xn_t *)bb)[i] + ((const uint64xn_t *)(&b[4]))[i];

     }
     /*
     }
     /*

-    for (int i=0; i<4; i++) {
-    aa[i] = a[i] + a[i+4];
-    bb[i] = b[i] + b[i+4];
-    }
-    */
+     * for (int i=0; i<4; i++) { aa[i] = a[i] + a[i+4]; bb[i] = b[i] + b[i+4];
+     * }
+     */

 
 

-    accum2  = widemul(&a[0],&b[3]);
-    accum0  = widemul(&aa[0],&bb[3]);
-    accum1  = widemul(&a[4],&b[7]);
+    accum2 = widemul(&a[0], &b[3]);
+    accum0 = widemul(&aa[0], &bb[3]);
+    accum1 = widemul(&a[4], &b[7]);

 
     mac(&accum2, &a[1], &b[2]);
     mac(&accum0, &aa[1], &bb[2]);
 
     mac(&accum2, &a[1], &b[2]);
     mac(&accum0, &aa[1], &bb[2]);


@@ -51,18 +61,18 @@ void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
 
     accum0 >>= 56;
     accum1 >>= 56;
 
     accum0 >>= 56;
     accum1 >>= 56;

-    
-    mac(&accum0, &aa[1],&bb[3]);
+
+    mac(&accum0, &aa[1], &bb[3]);

     mac(&accum1, &a[5], &b[7]);
     mac(&accum0, &aa[2], &bb[2]);
     mac(&accum1, &a[6], &b[6]);
     mac(&accum0, &aa[3], &bb[1]);
     accum1 += accum0;
 
     mac(&accum1, &a[5], &b[7]);
     mac(&accum0, &aa[2], &bb[2]);
     mac(&accum1, &a[6], &b[6]);
     mac(&accum0, &aa[3], &bb[1]);
     accum1 += accum0;
 

-    accum2 = widemul(&a[0],&b[0]);
+    accum2 = widemul(&a[0], &b[0]);

     accum1 -= accum2;
     accum0 += accum2;
     accum1 -= accum2;
     accum0 += accum2;

-    
+

     msb(&accum0, &a[1], &b[3]);
     msb(&accum0, &a[2], &b[2]);
     mac(&accum1, &a[7], &b[5]);
     msb(&accum0, &a[1], &b[3]);
     msb(&accum0, &a[2], &b[2]);
     mac(&accum1, &a[7], &b[5]);


@@ -76,7 +86,7 @@ void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
     accum0 >>= 56;
     accum1 >>= 56;
 
     accum0 >>= 56;
     accum1 >>= 56;
 

-    accum2  = widemul(&a[2],&b[7]);
+    accum2 = widemul(&a[2], &b[7]);

     mac(&accum0, &a[6], &bb[3]);
     mac(&accum1, &aa[2], &bbb[3]);
 
     mac(&accum0, &a[6], &bb[3]);
     mac(&accum1, &aa[2], &bbb[3]);
 


@@ -84,7 +94,7 @@ void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
     mac(&accum0, &a[7], &bb[2]);
     mac(&accum1, &aa[3], &bbb[2]);
 
     mac(&accum0, &a[7], &bb[2]);
     mac(&accum1, &aa[3], &bbb[2]);
 

-    mac(&accum2, &a[0],&b[1]);
+    mac(&accum2, &a[0], &b[1]);

     mac(&accum1, &aa[0], &bb[1]);
     mac(&accum0, &a[4], &b[5]);
 
     mac(&accum1, &aa[0], &bb[1]);
     mac(&accum0, &a[4], &b[5]);
 


@@ -101,11 +111,11 @@ void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
     accum0 >>= 56;
     accum1 >>= 56;
 
     accum0 >>= 56;
     accum1 >>= 56;
 

-    accum2  = widemul(&a[3],&b[7]);
+    accum2 = widemul(&a[3], &b[7]);

     mac(&accum0, &a[7], &bb[3]);
     mac(&accum1, &aa[3], &bbb[3]);
 
     mac(&accum0, &a[7], &bb[3]);
     mac(&accum1, &aa[3], &bbb[3]);
 

-    mac(&accum2, &a[0],&b[2]);
+    mac(&accum2, &a[0], &b[2]);

     mac(&accum1, &aa[0], &bb[2]);
     mac(&accum0, &a[4], &b[6]);
 
     mac(&accum1, &aa[0], &bb[2]);
     mac(&accum0, &a[4], &b[6]);
 


@@ -139,37 +149,46 @@ void gf_mul (gf_s *__restrict__ cs, const gf as, const gf bs) {
     c[0] += ((uint64_t)(accum1));
 }
 
     c[0] += ((uint64_t)(accum1));
 }
 

-void gf_mulw_unsigned (gf_s *__restrict__ cs, const gf as, uint32_t b) {
+void gf_mulw_unsigned(gf_s * __restrict__ cs, const gf as, uint32_t b)
+{

     const uint64_t *a = as->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0, accum4;
     const uint64_t *a = as->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0, accum4;

-    uint64_t mask = (1ull<<56) - 1;  
+    uint64_t mask = (1ull << 56) - 1;

 
     accum0 = widemul_rm(b, &a[0]);
     accum4 = widemul_rm(b, &a[4]);
 
 
     accum0 = widemul_rm(b, &a[0]);
     accum4 = widemul_rm(b, &a[4]);
 

-    c[0] = accum0 & mask; accum0 >>= 56;
-    c[4] = accum4 & mask; accum4 >>= 56;
+    c[0] = accum0 & mask;
+    accum0 >>= 56;
+    c[4] = accum4 & mask;
+    accum4 >>= 56;

 
     mac_rm(&accum0, b, &a[1]);
     mac_rm(&accum4, b, &a[5]);
 
 
     mac_rm(&accum0, b, &a[1]);
     mac_rm(&accum4, b, &a[5]);
 

-    c[1] = accum0 & mask; accum0 >>= 56;
-    c[5] = accum4 & mask; accum4 >>= 56;
+    c[1] = accum0 & mask;
+    accum0 >>= 56;
+    c[5] = accum4 & mask;
+    accum4 >>= 56;

 
     mac_rm(&accum0, b, &a[2]);
     mac_rm(&accum4, b, &a[6]);
 
 
     mac_rm(&accum0, b, &a[2]);
     mac_rm(&accum4, b, &a[6]);
 

-    c[2] = accum0 & mask; accum0 >>= 56;
-    c[6] = accum4 & mask; accum4 >>= 56;
+    c[2] = accum0 & mask;
+    accum0 >>= 56;
+    c[6] = accum4 & mask;
+    accum4 >>= 56;

 
     mac_rm(&accum0, b, &a[3]);
     mac_rm(&accum4, b, &a[7]);
 
 
     mac_rm(&accum0, b, &a[3]);
     mac_rm(&accum4, b, &a[7]);
 

-    c[3] = accum0 & mask; accum0 >>= 56;
-    c[7] = accum4 & mask; accum4 >>= 56;
-    
+    c[3] = accum0 & mask;
+    accum0 >>= 56;
+    c[7] = accum4 & mask;
+    accum4 >>= 56;
+

     accum0 += accum4 + c[4];
     c[4] = accum0 & mask;
     c[5] += accum0 >> 56;
     accum0 += accum4 + c[4];
     c[4] = accum0 & mask;
     c[5] += accum0 >> 56;


@@ -179,24 +198,26 @@ void gf_mulw_unsigned (gf_s *__restrict__ cs, const gf as, uint32_t b) {
     c[1] += accum4 >> 56;
 }
 
     c[1] += accum4 >> 56;
 }
 

-void gf_sqr (gf_s *__restrict__ cs, const gf as) {
+void gf_sqr(gf_s * __restrict__ cs, const gf as)
+{

     const uint64_t *a = as->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0 = 0, accum1 = 0, accum2;
     const uint64_t *a = as->limb;
     uint64_t *c = cs->limb;
 
     __uint128_t accum0 = 0, accum1 = 0, accum2;

-    uint64_t mask = (1ull<<56) - 1;  
+    uint64_t mask = (1ull << 56) - 1;

 
     uint64_t aa[4] VECTOR_ALIGNED;
 
     /* For some reason clang doesn't vectorize this without prompting? */
     unsigned int i;
 
     uint64_t aa[4] VECTOR_ALIGNED;
 
     /* For some reason clang doesn't vectorize this without prompting? */
     unsigned int i;

-    for (i=0; i<sizeof(aa)/sizeof(uint64xn_t); i++) {
-      ((uint64xn_t*)aa)[i] = ((const uint64xn_t*)a)[i] + ((const uint64xn_t*)(&a[4]))[i];
+    for (i = 0; i < sizeof(aa) / sizeof(uint64xn_t); i++) {
+        ((uint64xn_t *) aa)[i] =
+            ((const uint64xn_t *)a)[i] + ((const uint64xn_t *)(&a[4]))[i];

     }
 
     }
 

-    accum2  = widemul(&a[0],&a[3]);
-    accum0  = widemul(&aa[0],&aa[3]);
-    accum1  = widemul(&a[4],&a[7]);
+    accum2 = widemul(&a[0], &a[3]);
+    accum0 = widemul(&aa[0], &aa[3]);
+    accum1 = widemul(&a[4], &a[7]);

 
     mac(&accum2, &a[1], &a[2]);
     mac(&accum0, &aa[1], &aa[2]);
 
     mac(&accum2, &a[1], &a[2]);
     mac(&accum0, &aa[1], &aa[2]);


@@ -205,21 +226,21 @@ void gf_sqr (gf_s *__restrict__ cs, const gf as) {
     accum0 -= accum2;
     accum1 += accum2;
 
     accum0 -= accum2;
     accum1 += accum2;
 

-    c[3] = ((uint64_t)(accum1))<<1 & mask;
-    c[7] = ((uint64_t)(accum0))<<1 & mask;
+    c[3] = ((uint64_t)(accum1)) << 1 & mask;
+    c[7] = ((uint64_t)(accum0)) << 1 & mask;

 
     accum0 >>= 55;
     accum1 >>= 55;
 
 
     accum0 >>= 55;
     accum1 >>= 55;
 

-    mac2(&accum0, &aa[1],&aa[3]);
+    mac2(&accum0, &aa[1], &aa[3]);

     mac2(&accum1, &a[5], &a[7]);
     mac(&accum0, &aa[2], &aa[2]);
     accum1 += accum0;
 
     msb2(&accum0, &a[1], &a[3]);
     mac(&accum1, &a[6], &a[6]);
     mac2(&accum1, &a[5], &a[7]);
     mac(&accum0, &aa[2], &aa[2]);
     accum1 += accum0;
 
     msb2(&accum0, &a[1], &a[3]);
     mac(&accum1, &a[6], &a[6]);

-    
-    accum2 = widemul(&a[0],&a[0]);
+
+    accum2 = widemul(&a[0], &a[0]);

     accum1 -= accum2;
     accum0 += accum2;
 
     accum1 -= accum2;
     accum0 += accum2;
 


@@ -233,14 +254,14 @@ void gf_sqr (gf_s *__restrict__ cs, const gf as) {
     accum0 >>= 56;
     accum1 >>= 56;
 
     accum0 >>= 56;
     accum1 >>= 56;
 

-    accum2  = widemul2(&aa[2],&aa[3]);
+    accum2 = widemul2(&aa[2], &aa[3]);

     msb2(&accum0, &a[2], &a[3]);
     mac2(&accum1, &a[6], &a[7]);
 
     accum1 += accum2;
     accum0 += accum2;
 
     msb2(&accum0, &a[2], &a[3]);
     mac2(&accum1, &a[6], &a[7]);
 
     accum1 += accum2;
     accum0 += accum2;
 

-    accum2  = widemul2(&a[0],&a[1]);
+    accum2 = widemul2(&a[0], &a[1]);

     mac2(&accum1, &aa[0], &aa[1]);
     mac2(&accum0, &a[4], &a[5]);
 
     mac2(&accum1, &aa[0], &aa[1]);
     mac2(&accum0, &a[4], &a[5]);
 


@@ -253,14 +274,14 @@ void gf_sqr (gf_s *__restrict__ cs, const gf as) {
     accum0 >>= 56;
     accum1 >>= 56;
 
     accum0 >>= 56;
     accum1 >>= 56;
 

-    accum2  = widemul(&aa[3],&aa[3]);
+    accum2 = widemul(&aa[3], &aa[3]);

     msb(&accum0, &a[3], &a[3]);
     mac(&accum1, &a[7], &a[7]);
 
     accum1 += accum2;
     accum0 += accum2;
 
     msb(&accum0, &a[3], &a[3]);
     mac(&accum1, &a[7], &a[7]);
 
     accum1 += accum2;
     accum0 += accum2;
 

-    accum2  = widemul2(&a[0],&a[2]);
+    accum2 = widemul2(&a[0], &a[2]);

     mac2(&accum1, &aa[0], &aa[2]);
     mac2(&accum0, &a[4], &a[6]);
 
     mac2(&accum1, &aa[0], &aa[2]);
     mac2(&accum0, &a[4], &a[6]);