diff options
Diffstat (limited to 'crypto/ec/asm/ecp_nistz256-avx2.pl')
| -rwxr-xr-x | crypto/ec/asm/ecp_nistz256-avx2.pl | 73 |
1 files changed, 30 insertions, 43 deletions
diff --git a/crypto/ec/asm/ecp_nistz256-avx2.pl b/crypto/ec/asm/ecp_nistz256-avx2.pl index 4c220aa645f1..794e56a082fc 100755 --- a/crypto/ec/asm/ecp_nistz256-avx2.pl +++ b/crypto/ec/asm/ecp_nistz256-avx2.pl @@ -1,32 +1,19 @@ -#!/usr/bin/env perl - -############################################################################## -# # -# Copyright 2014 Intel Corporation # -# # -# Licensed under the Apache License, Version 2.0 (the "License"); # -# you may not use this file except in compliance with the License. # -# You may obtain a copy of the License at # -# # -# http://www.apache.org/licenses/LICENSE-2.0 # -# # -# Unless required by applicable law or agreed to in writing, software # -# distributed under the License is distributed on an "AS IS" BASIS, # -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # -# See the License for the specific language governing permissions and # -# limitations under the License. # -# # -############################################################################## -# # -# Developers and authors: # -# Shay Gueron (1, 2), and Vlad Krasnov (1) # -# (1) Intel Corporation, Israel Development Center # -# (2) University of Haifa # -# Reference: # -# S.Gueron and V.Krasnov, "Fast Prime Field Elliptic Curve Cryptography with# -# 256 Bit Primes" # -# # -############################################################################## +#! /usr/bin/env perl +# Copyright 2014-2018 The OpenSSL Project Authors. All Rights Reserved. +# Copyright (c) 2014, Intel Corporation. All Rights Reserved. +# +# 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 Shay Gueron (1, 2), and Vlad Krasnov (1) +# (1) Intel Corporation, Israel Development Center, Haifa, Israel +# (2) University of Haifa, Israel +# +# Reference: +# S.Gueron and V.Krasnov, "Fast Prime Field Elliptic Curve Cryptography with +# 256 Bit Primes" $flavour = shift; $output = shift; @@ -60,7 +47,7 @@ if (!$addx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && $addx = ($1>=12); } -if (!$addx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9])\.([0-9]+)/) { +if (!$addx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|based on LLVM) ([3-9])\.([0-9]+)/) { my $ver = $2 + $3/100.0; # 3.1->3.01, 3.10->3.10 $avx = ($ver>=3.0) + ($ver>=3.01); $addx = ($ver>=3.03); @@ -149,8 +136,8 @@ $code.=<<___; ___ { -# This function recieves a pointer to an array of four affine points -# (X, Y, <1>) and rearanges the data for AVX2 execution, while +# This function receives a pointer to an array of four affine points +# (X, Y, <1>) and rearranges the data for AVX2 execution, while # converting it to 2^29 radix redundant form my ($X0,$X1,$X2,$X3, $Y0,$Y1,$Y2,$Y3, @@ -301,8 +288,8 @@ ___ } { ################################################################################ -# This function recieves a pointer to an array of four AVX2 formatted points -# (X, Y, Z) convert the data to normal representation, and rearanges the data +# This function receives a pointer to an array of four AVX2 formatted points +# (X, Y, Z) convert the data to normal representation, and rearranges the data my ($D0,$D1,$D2,$D3, $D4,$D5,$D6,$D7, $D8)=map("%ymm$_",(0..8)); my ($T0,$T1,$T2,$T3, $T4,$T5,$T6)=map("%ymm$_",(9..15)); @@ -1909,7 +1896,7 @@ ___ } { ################################################################################ -# void ecp_nistz256_avx2_multi_select_w7(void* RESULT, void *in, +# void ecp_nistz256_avx2_multi_gather_w7(void* RESULT, void *in, # int index0, int index1, int index2, int index3); ################################################################################ @@ -1919,10 +1906,10 @@ my ($R0a,$R0b,$R1a,$R1b,$R2a,$R2b,$R3a,$R3b)=map("%ymm$_",(4..11)); my ($M0,$T0,$T1,$TMP0)=map("%ymm$_",(12..15)); $code.=<<___; -.globl ecp_nistz256_avx2_multi_select_w7 -.type ecp_nistz256_avx2_multi_select_w7,\@function,6 +.globl ecp_nistz256_avx2_multi_gather_w7 +.type ecp_nistz256_avx2_multi_gather_w7,\@function,6 .align 32 -ecp_nistz256_avx2_multi_select_w7: +ecp_nistz256_avx2_multi_gather_w7: vzeroupper ___ $code.=<<___ if ($win64); @@ -2036,7 +2023,7 @@ $code.=<<___ if ($win64); ___ $code.=<<___; ret -.size ecp_nistz256_avx2_multi_select_w7,.-ecp_nistz256_avx2_multi_select_w7 +.size ecp_nistz256_avx2_multi_gather_w7,.-ecp_nistz256_avx2_multi_gather_w7 .extern OPENSSL_ia32cap_P .globl ecp_nistz_avx2_eligible @@ -2061,8 +2048,8 @@ $code.=<<___; .globl ecp_nistz256_avx2_to_mont .globl ecp_nistz256_avx2_from_mont .globl ecp_nistz256_avx2_set1 -.globl ecp_nistz256_avx2_multi_select_w7 -.type ecp_nistz256_avx2_multi_select_w7,\@abi-omnipotent +.globl ecp_nistz256_avx2_multi_gather_w7 +.type ecp_nistz256_avx2_multi_gather_w7,\@abi-omnipotent ecp_nistz256_avx2_transpose_convert: ecp_nistz256_avx2_convert_transpose_back: ecp_nistz256_avx2_point_add_affine_x4: @@ -2070,10 +2057,10 @@ ecp_nistz256_avx2_point_add_affines_x4: ecp_nistz256_avx2_to_mont: ecp_nistz256_avx2_from_mont: ecp_nistz256_avx2_set1: -ecp_nistz256_avx2_multi_select_w7: +ecp_nistz256_avx2_multi_gather_w7: .byte 0x0f,0x0b # ud2 ret -.size ecp_nistz256_avx2_multi_select_w7,.-ecp_nistz256_avx2_multi_select_w7 +.size ecp_nistz256_avx2_multi_gather_w7,.-ecp_nistz256_avx2_multi_gather_w7 .globl ecp_nistz_avx2_eligible .type ecp_nistz_avx2_eligible,\@abi-omnipotent |