1 /*******************************************************************************
2 * Copyright 2016-2018 Intel Corporation
3 * All Rights Reserved.
4 *
5 * If this  software was obtained  under the  Intel Simplified  Software License,
6 * the following terms apply:
7 *
8 * The source code,  information  and material  ("Material") contained  herein is
9 * owned by Intel Corporation or its  suppliers or licensors,  and  title to such
10 * Material remains with Intel  Corporation or its  suppliers or  licensors.  The
11 * Material  contains  proprietary  information  of  Intel or  its suppliers  and
12 * licensors.  The Material is protected by  worldwide copyright  laws and treaty
13 * provisions.  No part  of  the  Material   may  be  used,  copied,  reproduced,
14 * modified, published,  uploaded, posted, transmitted,  distributed or disclosed
15 * in any way without Intel's prior express written permission.  No license under
16 * any patent,  copyright or other  intellectual property rights  in the Material
17 * is granted to  or  conferred  upon  you,  either   expressly,  by implication,
18 * inducement,  estoppel  or  otherwise.  Any  license   under such  intellectual
19 * property rights must be express and approved by Intel in writing.
20 *
21 * Unless otherwise agreed by Intel in writing,  you may not remove or alter this
22 * notice or  any  other  notice   embedded  in  Materials  by  Intel  or Intel's
23 * suppliers or licensors in any way.
24 *
25 *
26 * If this  software  was obtained  under the  Apache License,  Version  2.0 (the
27 * "License"), the following terms apply:
28 *
29 * You may  not use this  file except  in compliance  with  the License.  You may
30 * obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
31 *
32 *
33 * Unless  required  by   applicable  law  or  agreed  to  in  writing,  software
34 * distributed under the License  is distributed  on an  "AS IS"  BASIS,  WITHOUT
35 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
36 *
37 * See the   License  for the   specific  language   governing   permissions  and
38 * limitations under the License.
39 *******************************************************************************/
40 
41 /*
42 //
43 //  Purpose:
44 //     Cryptography Primitive.
45 //     Internal Definitions of AVX2 Montgomery Exp
46 //
47 */
48 #include "owncp.h"
49 
50 #if (_IPP32E>=_IPP32E_L9)
51 
52 #include "pcpbnuimpl.h"
53 #include "pcpngmontexpstuff.h"
54 
55 #define RSA_AVX2_MIN_BITSIZE  (1024)
56 #define RSA_AVX2_MAX_BITSIZE  (13*1024)
57 
58 #define NORM_DIGSIZE_AVX2 (BITSIZE(Ipp32u))
59 #define NORM_BASE_AVX2    ((Ipp64u)1<<NORM_DIGSIZE_AVX2)
60 #define NORM_MASK_AVX2    (NORM_BASE_AVX2-1)
61 
62 #define EXP_DIGIT_SIZE_AVX2   (27)
63 #define EXP_DIGIT_BASE_AVX2   (1<<EXP_DIGIT_SIZE_AVX2)
64 #define EXP_DIGIT_MASK_AVX2   (EXP_DIGIT_BASE_AVX2-1)
65 
66 
67 /* number of "diSize" chunks in "bitSize" bit string */
cpDigitNum_avx2(int bitSize,int digSize)68 __INLINE int cpDigitNum_avx2(int bitSize, int digSize)
69 { return (bitSize + digSize-1)/digSize; }
70 
71 /* number of "EXP_DIGIT_SIZE_AVX2" chunks in "bitSize" bit string matched for AMM */
numofVariable_avx2(int modulusBits)72 __INLINE cpSize numofVariable_avx2(int modulusBits)
73 {
74    cpSize ammBitSize = 2 + cpDigitNum_avx2(modulusBits, BITSIZE(BNU_CHUNK_T)) * BITSIZE(BNU_CHUNK_T);
75    cpSize redNum = cpDigitNum_avx2(ammBitSize, EXP_DIGIT_SIZE_AVX2);
76    return redNum;
77 }
78 
79 /* buffer corresponding to numofVariable_avx2() */
numofVariableBuff_avx2(int numV)80 __INLINE cpSize numofVariableBuff_avx2(int numV)
81 {
82    return numV +4;
83 }
84 
85 /* basic operations */
86 #define cpMontMul1024_avx2 OWNAPI(cpMontMul1024_avx2)
87 void    cpMontMul1024_avx2(Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pB, const Ipp64u* pModulus, int mLen, Ipp64u m0);
88 #define cpMontMul4n_avx2 OWNAPI(cpMontMul4n_avx2)
89 void    cpMontMul4n_avx2  (Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pB, const Ipp64u* pModulus, int mLen, Ipp64u m0, Ipp64u* pScratchBuffer);
90 #define cpMontMul4n1_avx2 OWNAPI(cpMontMul4n1_avx2)
91 void    cpMontMul4n1_avx2 (Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pB, const Ipp64u* pModulus, int mLen, Ipp64u m0, Ipp64u* pScratchBuffer);
92 #define cpMontMul4n2_avx2 OWNAPI(cpMontMul4n2_avx2)
93 void    cpMontMul4n2_avx2 (Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pB, const Ipp64u* pModulus, int mLen, Ipp64u m0, Ipp64u* pScratchBuffer);
94 #define cpMontMul4n3_avx2 OWNAPI(cpMontMul4n3_avx2)
95 void    cpMontMul4n3_avx2 (Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pB, const Ipp64u* pModulus, int mLen, Ipp64u m0, Ipp64u* pScratchBuffer);
96 
97 #define cpMontSqr1024_avx2 OWNAPI(cpMontSqr1024_avx2)
98 void    cpMontSqr1024_avx2(Ipp64u* pR, const Ipp64u* pA, const Ipp64u* pModulus, int mLen, Ipp64u k0, Ipp64u* pBuffer);
99 #define cpSqr1024_avx2 OWNAPI(cpSqr1024_avx2)
100 void    cpSqr1024_avx2 (Ipp64u* pR, const Ipp64u* pA, int aLen, Ipp64u* pBuffer);
101 #define cpSqr_avx2 OWNAPI(cpSqr_avx2)
102 void    cpSqr_avx2 (Ipp64u* pR, const Ipp64u* pA, int aLen, Ipp64u* pBuffer);
103 
104 #define cpMontRed_avx2 OWNAPI(cpMontRed_avx2)
105 void    cpMontRed_avx2(Ipp64u* pR, Ipp64u* pProduct, const Ipp64u* pModulus, int mLen, Ipp64u k0);
106 
107 /* exponentiation buffer size */
108 #define gsMontExpBinBuffer_avx2 OWNAPI(gsMontExpBinBuffer_avx2)
109 #define gsMontExpWinBuffer_avx2 OWNAPI(gsMontExpWinBuffer_avx2)
110 cpSize  gsMontExpBinBuffer_avx2(int modulusBits);
111 cpSize  gsMontExpWinBuffer_avx2(int modulusBits);
112 
113 /* AVX2 exponentiations */
114 #define gsMontExpBin_BNU_avx2 OWNAPI(gsMontExpBin_BNU_avx2)
115 cpSize  gsMontExpBin_BNU_avx2(BNU_CHUNK_T* dataY,
116                         const BNU_CHUNK_T* dataX, cpSize nsX,
117                         const BNU_CHUNK_T* dataE, cpSize nsE,
118                               gsModEngine* pMont,
119                               BNU_CHUNK_T* pBuffer);
120 
121 #define gsMontExpBin_BNU_sscm_avx2 OWNAPI(gsMontExpBin_BNU_sscm_avx2)
122 cpSize  gsMontExpBin_BNU_sscm_avx2(BNU_CHUNK_T* dataY,
123                              const BNU_CHUNK_T* dataX, cpSize nsX,
124                              const BNU_CHUNK_T* dataE, cpSize nsE,
125                                    gsModEngine* pMont,
126                                    BNU_CHUNK_T* pBuffer);
127 
128 #define gsMontExpWin_BNU_avx2 OWNAPI(gsMontExpWin_BNU_avx2)
129 cpSize  gsMontExpWin_BNU_avx2(BNU_CHUNK_T* dataY,
130                         const BNU_CHUNK_T* dataX, cpSize nsX,
131                         const BNU_CHUNK_T* dataE, cpSize nsE,
132                               gsModEngine* pMont,
133                               BNU_CHUNK_T* pBuffer);
134 
135 #define gsMontExpWin_BNU_sscm_avx2 OWNAPI(gsMontExpWin_BNU_sscm_avx2)
136 cpSize  gsMontExpWin_BNU_sscm_avx2(BNU_CHUNK_T* dataY,
137                              const BNU_CHUNK_T* dataX, cpSize nsX,
138                              const BNU_CHUNK_T* dataE, cpSize nsE,
139                                    gsModEngine* pMont,
140                                    BNU_CHUNK_T* pBuffer);
141 
142 #endif /* _IPP32E_L9 */
143