/*
 * Copyright 2014 Martin Peres <martin.peres@free.fr>
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the folloing conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 * Authors: Martin Peres
 */

/******************************************************************************
 * arith data segment
 *****************************************************************************/
#ifdef INCLUDE_PROC
#endif

#ifdef INCLUDE_DATA
#endif

/******************************************************************************
 * arith code segment
 *****************************************************************************/
#ifdef INCLUDE_CODE

// does a 32x32 -> 64 multiplication
//
// A * B = A_lo * B_lo
//        + ( A_hi * B_lo ) << 16
//        + ( A_lo * B_hi ) << 16
//        + ( A_hi * B_hi ) << 32
//
// $r15 - current
// $r14 - A
// $r13 - B
// $r12 - mul_lo (return)
// $r11 - mul_hi (return)
// $r0  - zero
mulu32_32_64:
	push $r1 // A_hi
	push $r2 // B_hi
	push $r3 // tmp0
	push $r4 // tmp1

	shr b32 $r1 $r14 16
	shr b32 $r2 $r13 16

	clear b32 $r12
	clear b32 $r11

	// A_lo * B_lo
	mulu $r12 $r14 $r13

	// ( A_hi * B_lo ) << 16
	mulu $r3 $r1 $r13 // tmp0 = A_hi * B_lo
	mov b32 $r4 $r3
	and $r3 0xffff // tmp0 = tmp0_lo
	shl b32 $r3 16
	shr b32 $r4 16 // tmp1 = tmp0_hi
	add b32 $r12 $r3
	adc b32 $r11 $r4

	// ( A_lo * B_hi ) << 16
	mulu $r3 $r14 $r2 // tmp0 = A_lo * B_hi
	mov b32 $r4 $r3
	and $r3 0xffff // tmp0 = tmp0_lo
	shl b32 $r3 16
	shr b32 $r4 16 // tmp1 = tmp0_hi
	add b32 $r12 $r3
	adc b32 $r11 $r4

	// ( A_hi * B_hi ) << 32
	mulu $r3 $r1 $r2 // tmp0 = A_hi * B_hi
	add b32 $r11 $r3

	pop $r4
	pop $r3
	pop $r2
	pop $r1
	ret
#endif