MSP430: Add 64-bit hardware multiply support

Hardware multipliers that support widening 32-bit multiplication can
be used to perform a 64-bit * 64-bit multiplication more efficiently
than a software implementation.

The following equation is used to perform 64-bit multiplication for
devices with "32bit" or "f5series" hardware multiply versions:

  64bit_result = (low32_op0 * lop32_op1)
    + ((low32_op0 * high32_op1) << 32)
       + ((high32_op0 * low32_op1) << 32)

libgcc/ChangeLog:

	* config/msp430/lib2hw_mul.S (mult64_hw): New.
	(if MUL_32): Use mult64_hw for __muldi3.
	(if MUL_F5): Use mult64_hw for __muldi3.
	* config/msp430/lib2mul.c (__muldi3): New.
	* config/msp430/t-msp430 (LIB2FUNCS_EXCLUDE): Define.

libgcc/config/msp430/lib2hw_mul.S

@@ -207,6 +207,73 @@
 	MOV.W   &\RES3, R15		; Ready high 16-bits for return
 .endm
 
+.macro mult64_hw  MPY32_LO MPY32_HI OP2_LO OP2_HI RES0 RES1 RES2 RES3
+;* * 64-bit hardware multiply with a 64-bit result
+;*	int64 = int64 * int64
+;*
+;*   - Operand 1 is in R8, R9, R10, R11
+;*   - Operand 2 is in R12, R13, R14, R15
+;*   - Result    is in R12, R13, R14, R15
+;*
+;* 64-bit multiplication is achieved using the 32-bit hardware multiplier with
+;* the following equation:
+;*    R12:R15 = (R8:R9 * R12:R13) + ((R8:R9 * R14:R15) << 32) + ((R10:R11 * R12:R13) << 32)
+;*
+;* The left shift by 32 is handled with minimal cost by saving the two low
+;* words and discarding the two high words.
+;*
+;* To ensure that the multiply is performed atomically, interrupts are
+;* disabled upon routine entry.  Interrupt state is restored upon exit.
+;*
+;*   Registers used:  R6, R7, R8, R9, R10, R11, R12, R13, R14, R15
+;*
+;* Macro arguments are the memory locations of the hardware registers.
+;*
+#if defined(__MSP430X_LARGE__)
+	PUSHM.A	#5, R10
+#elif defined(__MSP430X__)
+	PUSHM.W	#5, R10
+#else
+	PUSH R10 { PUSH R9 { PUSH R8 { PUSH R7 { PUSH R6
+#endif
+	; Multiply the low 32-bits of op0 and the high 32-bits of op1.
+	MOV.W	R8, &\MPY32_LO
+	MOV.W	R9, &\MPY32_HI
+	MOV.W	R14, &\OP2_LO
+	MOV.W	R15, &\OP2_HI
+	; Save the low 32-bits of the result.
+	MOV.W	&\RES0, R6
+	MOV.W	&\RES1, R7
+	; Multiply the high 32-bits of op0 and the low 32-bits of op1.
+	MOV.W	R10, &\MPY32_LO
+	MOV.W	R11, &\MPY32_HI
+	MOV.W	R12, &\OP2_LO
+	MOV.W	R13, &\OP2_HI
+	; Add the low 32-bits of the result to the previously saved result.
+	ADD.W	&\RES0, R6
+	ADDC.W	&\RES1, R7
+	; Multiply the low 32-bits of op0 and op1.
+	MOV.W	R8, &\MPY32_LO
+	MOV.W	R9, &\MPY32_HI
+	MOV.W	R12, &\OP2_LO
+	MOV.W	R13, &\OP2_HI
+	; Write the return values
+	MOV.W	&\RES0, R12
+	MOV.W   &\RES1, R13
+	MOV.W	&\RES2, R14
+	MOV.W   &\RES3, R15
+	; Add the saved low 32-bit results from earlier to the high 32-bits of
+	; this result, effectively shifting those two results left by 32 bits.
+	ADD.W	R6, R14
+	ADDC.W  R7, R15
+#if defined(__MSP430X_LARGE__)
+	POPM.A	#5, R10
+#elif defined(__MSP430X__)
+	POPM.W	#5, R10
+#else
+	POP R6 { POP R7 { POP R8 { POP R9 { POP R10
+#endif
+.endm
 
 ;; EABI mandated names:
 ;; 
@@ -365,8 +432,9 @@
 	mult3264_hw MPY32L, MPY32H, OP2L, OP2H, RES0, RES1, RES2, RES3
 	end_func   __umulsidi2
 
-	;; FIXME: Add a hardware version of this function.
-	fake_func __muldi3    __mspabi_mpyll  __mspabi_mpyll_hw32
+	start_func __muldi3   __mspabi_mpyll __mspabi_mpyll_hw32
+	mult64_hw MPY32L, MPY32H, OP2L, OP2H, RES0, RES1, RES2, RES3
+	end_func __muldi3
 
 #elif defined MUL_F5
 /* The F5xxx series of MCUs support the same 16-bit and 32-bit multiply
@@ -397,8 +465,9 @@
 	mult3264_hw MPY32L_F5, MPY32H_F5, OP2L_F5, OP2H_F5, RES0_F5, RES1_F5, RES2_F5, RES3_F5
 	end_func   __umulsidi2
 
-	;; FIXME: Add a hardware version of this function.
-	fake_func __muldi3   __mspabi_mpyll __mspabi_mpyll_f5hw
+	start_func __muldi3   __mspabi_mpyll __mspabi_mpyll_f5hw
+	mult64_hw MPY32L_F5, MPY32H_F5, OP2L_F5, OP2H_F5, RES0_F5, RES1_F5, RES2_F5, RES3_F5
+	end_func __muldi3
 
 #else
 #error MUL type not defined

libgcc/config/msp430/lib2mul.c

@@ -30,6 +30,58 @@ typedef unsigned int  uint08_type   __attribute__ ((mode (QI)));
 #define C3B(a,b,c) a##b##c
 #define C3(a,b,c) C3B(a,b,c)
 
+#if defined (MUL_NONE) || defined (MUL_16)
+/* __muldi3 must be excluded from libgcc.a to prevent multiple-definition
+   errors for the hwmult configurations that have their own definition.
+   However, for MUL_NONE and MUL_16, the software version is still required, so
+   the necessary preprocessed output from libgcc2.c to compile that
+   software version of __muldi3 is below.  */
+typedef unsigned int USItype __attribute__ ((mode (SI)));
+typedef int DItype __attribute__ ((mode (DI)));
+typedef int SItype __attribute__ ((mode (SI)));
+struct DWstruct {SItype low, high;};
+
+typedef union
+{
+  struct DWstruct s;
+  DItype ll;
+} DWunion;
+
+DItype __muldi3 (DItype u, DItype v);
+
+DItype
+__muldi3 (DItype u, DItype v)
+{
+  const DWunion uu = {.ll = u};
+  const DWunion vv = {.ll = v};
+  /* The next block of code is expanded from the following line:
+     DWunion w = {.ll = __umulsidi3 (uu.s.low, vv.s.low)};  */
+  DWunion w;
+  USItype __x0, __x1, __x2, __x3;
+  USItype __ul, __vl, __uh, __vh;
+  __ul = ((USItype) (uu.s.low) & (((USItype) 1 << ((4 * 8) / 2)) - 1));
+  __uh = ((USItype) (uu.s.low) >> ((4 * 8) / 2));
+  __vl = ((USItype) (vv.s.low) & (((USItype) 1 << ((4 * 8) / 2)) - 1));
+  __vh = ((USItype) (vv.s.low) >> ((4 * 8) / 2));
+  __x0 = (USItype) __ul * __vl;
+  __x1 = (USItype) __ul * __vh;
+  __x2 = (USItype) __uh * __vl;
+  __x3 = (USItype) __uh * __vh;
+  __x1 += ((USItype) (__x0) >> ((4 * 8) / 2));
+  __x1 += __x2;
+  if (__x1 < __x2)
+    __x3 += ((USItype) 1 << ((4 * 8) / 2));
+  (w.s.high) = __x3 + ((USItype) (__x1) >> ((4 * 8) / 2));
+  (w.s.low) = ((USItype) (__x1) & (((USItype) 1 << ((4 * 8) / 2)) - 1))
+    * ((USItype) 1 << ((4 * 8) / 2))
+    + ((USItype) (__x0) & (((USItype) 1 << ((4 * 8) / 2)) - 1));
+
+  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
+	       + (USItype) uu.s.high * (USItype) vv.s.low);
+  return w.ll;
+}
+#endif
+
 #if defined MUL_NONE
 
 /* The software multiply library needs __mspabi_mpyll.  */

libgcc/config/msp430/t-msp430

@@ -40,6 +40,11 @@ LIB2ADD = \
 	$(srcdir)/config/msp430/floathisf.c \
 	$(srcdir)/config/msp430/cmpd.c
 
+# 32-bit and F5series hardware multiply have their own version of this function.
+# To handle the case when there is no hardware multiply or only 16-bit hardware
+# multiply, the libgcc version has been copied to lib2mul.c.
+LIB2FUNCS_EXCLUDE += _muldi3
+
 HOST_LIBGCC2_CFLAGS += -Os -ffunction-sections -fdata-sections -mhwmult=none
 
 crtbegin_no_eh.o: $(srcdir)/crtstuff.c