diff --git a/mpi/amd64/mpih-lshift.S b/mpi/amd64/mpih-lshift.S index c11e808c..3fa6e4fd 100644 --- a/mpi/amd64/mpih-lshift.S +++ b/mpi/amd64/mpih-lshift.S @@ -1,79 +1,79 @@ /* AMD64 (x86_64) lshift -- Left shift a limb vector and store * result in a second limb vector. * * Copyright (C) 1992, 1994, 1995, 1998, * 2001, 2002, 2006 Free Software Foundation, Inc. * * This file is part of Libgcrypt. * * Libgcrypt is free software; you can redistribute it and/or modify * it under the terms of the GNU Lesser General Public License as * published by the Free Software Foundation; either version 2.1 of * the License, or (at your option) any later version. * * Libgcrypt is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. */ #include "sysdep.h" #include "asm-syntax.h" /******************* * mpi_limb_t * _gcry_mpih_lshift( mpi_ptr_t wp, rdi * mpi_ptr_t up, rsi * mpi_size_t usize, rdx * unsigned cnt) rcx */ TEXT ALIGN(4) .globl C_SYMBOL_NAME(_gcry_mpih_lshift) C_SYMBOL_NAME(_gcry_mpih_lshift:) FUNC_ENTRY() /* Note: %xmm6 and %xmm7 not used for WIN64 ABI compatibility. */ movq -8(%rsi,%rdx,8), %xmm4 movd %ecx, %xmm1 movl $64, %eax subl %ecx, %eax movd %eax, %xmm0 movdqa %xmm4, %xmm3 psrlq %xmm0, %xmm4 - movd %xmm4, %rax + movq %xmm4, %rax subq $2, %rdx jl .Lendo ALIGN(4) /* minimal alignment for claimed speed */ .Loop: movq (%rsi,%rdx,8), %xmm5 movdqa %xmm5, %xmm2 psrlq %xmm0, %xmm5 psllq %xmm1, %xmm3 por %xmm5, %xmm3 movq %xmm3, 8(%rdi,%rdx,8) je .Lende movq -8(%rsi,%rdx,8), %xmm4 movdqa %xmm4, %xmm3 psrlq %xmm0, %xmm4 psllq %xmm1, %xmm2 por %xmm4, %xmm2 movq %xmm2, (%rdi,%rdx,8) subq $2, %rdx jge .Loop .Lendo: movdqa %xmm3, %xmm2 .Lende: psllq %xmm1, %xmm2 movq %xmm2, (%rdi) FUNC_EXIT() diff --git a/mpi/amd64/mpih-rshift.S b/mpi/amd64/mpih-rshift.S index 430ba4b0..4bc5db22 100644 --- a/mpi/amd64/mpih-rshift.S +++ b/mpi/amd64/mpih-rshift.S @@ -1,82 +1,82 @@ /* AMD64 (x86_64) rshift -- Right shift a limb vector and store * result in a second limb vector. * * Copyright (C) 1992, 1994, 1995, 1998, * 2001, 2002, 2006 Free Software Foundation, Inc. * * This file is part of Libgcrypt. * * Libgcrypt is free software; you can redistribute it and/or modify * it under the terms of the GNU Lesser General Public License as * published by the Free Software Foundation; either version 2.1 of * the License, or (at your option) any later version. * * Libgcrypt is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. */ #include "sysdep.h" #include "asm-syntax.h" /******************* * mpi_limb_t * _gcry_mpih_rshift( mpi_ptr_t wp, rdi * mpi_ptr_t up, rsi * mpi_size_t usize, rdx * unsigned cnt) rcx */ TEXT ALIGN(4) .globl C_SYMBOL_NAME(_gcry_mpih_rshift) C_SYMBOL_NAME(_gcry_mpih_rshift:) FUNC_ENTRY() /* Note: %xmm6 and %xmm7 not used for WIN64 ABI compatibility. */ movq (%rsi), %xmm4 movd %ecx, %xmm1 movl $64, %eax subl %ecx, %eax movd %eax, %xmm0 movdqa %xmm4, %xmm3 psllq %xmm0, %xmm4 - movd %xmm4, %rax + movq %xmm4, %rax leaq (%rsi,%rdx,8), %rsi leaq (%rdi,%rdx,8), %rdi negq %rdx addq $2, %rdx jg .Lendo ALIGN(4) /* minimal alignment for claimed speed */ .Loop: movq -8(%rsi,%rdx,8), %xmm5 movdqa %xmm5, %xmm2 psllq %xmm0, %xmm5 psrlq %xmm1, %xmm3 por %xmm5, %xmm3 movq %xmm3, -16(%rdi,%rdx,8) je .Lende movq (%rsi,%rdx,8), %xmm4 movdqa %xmm4, %xmm3 psllq %xmm0, %xmm4 psrlq %xmm1, %xmm2 por %xmm4, %xmm2 movq %xmm2, -8(%rdi,%rdx,8) addq $2, %rdx jle .Loop .Lendo: movdqa %xmm3, %xmm2 .Lende: psrlq %xmm1, %xmm2 movq %xmm2, -8(%rdi) FUNC_EXIT()