;   Copyright (C) 2014-2015 Free Software Foundation, Inc.
;   Contributed by Red Hat.
; 
; This file is free software; you can redistribute it and/or modify it
; under the terms of the GNU General Public License as published by the
; Free Software Foundation; either version 3, or (at your option) any
; later version.
; 
; This file 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
; General Public License for more details.
; 
; Under Section 7 of GPL version 3, you are granted additional
; permissions described in the GCC Runtime Library Exception, version
; 3.1, as published by the Free Software Foundation.
;
; You should have received a copy of the GNU General Public License and
; a copy of the GCC Runtime Library Exception along with this program;
; see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
; <http://www.gnu.org/licenses/>.

.macro start_func name
	.pushsection .text.\name,"ax",@progbits
	.align 2
	.global \name
	.type \name , @function
\name:
	PUSH.W	sr			; Save current interrupt state
	DINT				; Disable interrupts
	NOP				; Account for latency
.endm

.macro end_func name
#ifdef __MSP430X_LARGE__
	POP.W  sr
        RETA
#else
	RETI
#endif
	.size \name , . - \name
	.popsection
.endm

.macro mult16 OP1, OP2, RESULT
;* * 16-bit hardware multiply:  int16 = int16 * int16
;*  
;*   - Operand 1 is in R12
;*   - Operand 2 is in R13
;*   - Result is in R12
;*
;* To ensure that the multiply is performed atomically, interrupts are
;* disabled upon routine entry.  Interrupt state is restored upon exit.
;*
;*   Registers used:  R12, R13
;*
;* Macro arguments are the memory locations of the hardware registers.
	
	MOV.W	r12, &\OP1		; Load operand 1 into multiplier
	MOV.W	r13, &\OP2		; Load operand 2 which triggers MPY
	MOV.W	&\RESULT, r12		; Move result into return register
.endm

.macro mult1632 OP1, OP2, RESULT_LO, RESULT_HI
;* * 16-bit hardware multiply with a 32-bit result:
;*	int32 = int16 * int16
;* 	uint32 = uint16 * uint16
;*  
;*   - Operand 1 is in R12
;*   - Operand 2 is in R13
;*   - Result is in R12, R13
;*
;* To ensure that the multiply is performed atomically, interrupts are
;* disabled upon routine entry.  Interrupt state is restored upon exit.
;*
;*   Registers used:  R12, R13
;*
;* Macro arguments are the memory locations of the hardware registers.
	
	MOV.W	r12, &\OP1		; Load operand 1 into multiplier
	MOV.W	r13, &\OP2		; Load operand 2 which triggers MPY
	MOV.W	&\RESULT_LO, r12	; Move low result into return register
	MOV.W	&\RESULT_HI, r13	; Move high result into return register
.endm

.macro mult32 OP1, OP2, MAC_OP1, MAC_OP2, RESULT_LO, RESULT_HI
;* * 32-bit hardware multiply with a 32-bit result using 16 multiply and accumulate:
;*	int32 = int32 * int32
;*  
;*   - Operand 1 is in R12, R13
;*   - Operand 2 is in R14, R15
;*   - Result    is in R12, R13
;*
;* To ensure that the multiply is performed atomically, interrupts are
;* disabled upon routine entry.  Interrupt state is restored upon exit.
;*
;*   Registers used:  R12, R13, R14, R15
;*
;* Macro arguments are the memory locations of the hardware registers.
	
	MOV.W	r12, &\OP1		; Load operand 1 Low into multiplier
	MOV.W	r14, &\OP2		; Load operand 2 Low which triggers MPY
	MOV.W	r12, &\MAC_OP1		; Load operand 1 Low into mac
	MOV.W   &\RESULT_LO, r12	; Low 16-bits of result ready for return
	MOV.W   &\RESULT_HI, &\RESULT_LO; MOV intermediate mpy high into low
	MOV.W	r15, &\MAC_OP2		; Load operand 2 High, trigger MAC
	MOV.W	r13, &\MAC_OP1		; Load operand 1 High
	MOV.W	r14, &\MAC_OP2		; Load operand 2 Lo, trigger MAC
	MOV.W	&\RESULT_LO, r13        ; Upper 16-bits result ready for return
.endm


.macro mult32_hw  OP1_LO  OP1_HI  OP2_LO  OP2_HI  RESULT_LO  RESULT_HI
;* * 32-bit hardware multiply with a 32-bit result
;*	int32 = int32 * int32
;*  
;*   - Operand 1 is in R12, R13
;*   - Operand 2 is in R14, R15
;*   - Result    is in R12, R13
;*
;* To ensure that the multiply is performed atomically, interrupts are
;* disabled upon routine entry.  Interrupt state is restored upon exit.
;*
;*   Registers used:  R12, R13, R14, R15
;*
;* Macro arguments are the memory locations of the hardware registers.
	
	MOV.W	r12, &\OP1_LO		; Load operand 1 Low into multiplier
	MOV.W	r13, &\OP1_HI		; Load operand 1 High into multiplier
	MOV.W	r14, &\OP2_LO		; Load operand 2 Low into multiplier
	MOV.W	r15, &\OP2_HI		; Load operand 2 High, trigger MPY
	MOV.W	&\RESULT_LO, r12	; Ready low 16-bits for return
	MOV.W   &\RESULT_HI, r13	; Ready high 16-bits for return
.endm

.macro mult3264_hw  OP1_LO  OP1_HI  OP2_LO  OP2_HI  RES0 RES1 RES2 RES3
;* * 32-bit hardware multiply with a 64-bit result
;*	int64 = int32 * int32
;*	uint64 = uint32 * uint32
;*  
;*   - Operand 1 is in R12, R13
;*   - Operand 2 is in R14, R15
;*   - Result    is in R12, R13, R14, R15
;*
;* To ensure that the multiply is performed atomically, interrupts are
;* disabled upon routine entry.  Interrupt state is restored upon exit.
;*
;*   Registers used:  R12, R13, R14, R15
;*
;* Macro arguments are the memory locations of the hardware registers.
	
	MOV.W	r12, &\OP1_LO		; Load operand 1 Low into multiplier
	MOV.W	r13, &\OP1_HI		; Load operand 1 High into multiplier
	MOV.W	r14, &\OP2_LO		; Load operand 2 Low into multiplier
	MOV.W	r15, &\OP2_HI		; Load operand 2 High, trigger MPY
	MOV.W	&\RES0, R12		; Ready low 16-bits for return
	MOV.W   &\RES1, R13		; 
	MOV.W	&\RES2, R14		; 
	MOV.W   &\RES3, R15		; Ready high 16-bits for return
.endm


;;  First generation MSP430 hardware multiplies ....

.set MPY_OP1,   0x0130
.set MPY_OP1_S, 0x0132
.set MAC_OP1, 	0x0134
.set MPY_OP2, 	0x0138
.set MAC_OP2, 	0x0138
.set RESULT_LO, 0x013A
.set RESULT_HI, 0x013C
	
	start_func __mulhi2
	mult16 MPY_OP1, MPY_OP2, RESULT_LO
	end_func __mulhi2

	start_func __mulsihi2
	mult1632 MPY_OP1_S, MPY_OP2, RESULT_LO, RESULT_HI
	end_func __mulsihi2

	start_func __umulsihi2
	mult1632 MPY_OP1, MPY_OP2, RESULT_LO, RESULT_HI
	end_func __umulsihi2

	start_func __mulsi2
	mult32 MPY_OP1, MPY_OP2, MAC_OP1, MAC_OP2, RESULT_LO, RESULT_HI
	end_func __mulsi2

	start_func __mulsi2_hw32
	mult32_hw 0x0140, 0x0142, 0x0150, 0x0152, 0x0154, 0x0156
	end_func __mulsi2_hw32

	start_func __muldisi2_hw32
	mult3264_hw 0x0144, 0x146, 0x0150, 0x0152, 0x0154, 0x0156, 0x0158, 0x015A
	end_func __muldisi2_hw32

	start_func __umuldisi2_hw32
	mult3264_hw 0x0140, 0x142, 0x0150, 0x0152, 0x0154, 0x0156, 0x0158, 0x015A
	end_func __umuldisi2_hw32
	
/* The F5xxx series of MCUs support the same 16-bit hardware
   multiply, but it is accessed from different memory registers.  */
	
	start_func __mulhi2_f5
	mult16 0x04C0, 0x04C8, 0x04CA
	end_func __mulhi2_f5

	start_func __mulsihi2_f5
	mult1632 0x04C2, 0x04C8, 0x04CA, 0x04CC
	end_func __mulsihi2_f5
	
	start_func __umulsihi2_f5
	mult1632 0x04C0, 0x04C8, 0x04CA, 0x04CC
	end_func __umulsihi2_f5

	start_func __mulsi2_f5
	mult32_hw 0x04D0, 0x04D2, 0x04E0, 0x04E2, 0x04E4, 0x04E6
	end_func __mulsi2_f5
	
	start_func __muldisi2_f5
	mult3264_hw 0x04D4, 0x04D6, 0x04E0, 0x04E2, 0x04E4, 0x04E6, 0x04E8, 0x04EA
	end_func __muldisi2_f5
	
	start_func __umuldisi2_f5
	mult3264_hw 0x04D0, 0x04D2, 0x04E0, 0x04E2, 0x04E4, 0x04E6, 0x04E8, 0x04EA
	end_func __umuldisi2_f5