Home
last modified time | relevance | path

Searched refs:multiply (Results 1 – 14 of 14) sorted by relevance

/arch/m68k/ifpsp060/
A Dilsp.doc34 module can be used to emulate 64-bit divide and multiply,
78 For example, to use a 64-bit multiply instruction,
81 for unsigned multiply could look like:
90 bsr.l _060LISP_TOP+0x18 # branch to multiply routine
A Disp.doc42 64-bit multiply
/arch/nios2/kernel/
A Dinsnemu.S212 bne r7, zero, multiply
406 multiply: label
/arch/powerpc/lib/
A Ddiv64.S41 mulhwu r9,r11,r4 # multiply the estimate by the divisor,
/arch/m68k/fpsp040/
A Ddecbin.S472 | same sign. If the exp was pos then multiply fp1*fp0;
483 beqs mul |if clear, go to multiply
488 fmulx %fp1,%fp0 |exp is positive, so multiply by exp
A Dsetox.S567 fmulx SCALE(%a6),%fp0 | ...multiply 2^(M)
/arch/openrisc/
A DKconfig117 bool "Have instruction l.mul for hardware multiply"
120 Select this if your implementation has a hardware multiply instruction
/arch/powerpc/boot/
A Ddiv64.S41 mulhwu r9,r11,r4 # multiply the estimate by the divisor,
/arch/m68k/ifpsp060/src/
A Dilsp.S452 # multiply hi,lo words of each factor to get 4 intermediate products
485 # 64-bit multiply instruction. #
499 # Perform the multiply in pieces using 16x16->32 unsigned #
A Dfpsp.S962 # multiply operation is the smallest possible normalized number
9627 # for the multiply to work. Therefore, we're going to actually do a
11547 # For norms/denorms, scale the exponents such that a multiply #
11628 fmul.x FP_SCR0(%a6),%fp0 # execute multiply
11651 # - the result of the multiply operation is an overflow.
11668 fmul.x FP_SCR0(%a6),%fp0 # execute multiply
11762 # - the result of the multiply operation is an underflow.
13999 fsglmul.x FP_SCR0(%a6),%fp0 # execute sgl multiply
14026 fsglmul.x FP_SCR0(%a6),%fp0 # execute sgl multiply
14075 fsglmul.x FP_SCR0(%a6),%fp0 # execute sgl multiply
[all …]
A Dfplsp.S7203 fmul.x SCALE(%a6),%fp0 # multiply 2^(M)
9267 # the multiply factor that we're trying to create should be a denorm
9269 # multiply with a denorm which will cause an unimplemented data type
9293 # create an fp multiply that will create the result.
9308 fmul.x (%sp)+,%fp0 # do the multiply
A Dpfpsp.S961 # multiply operation is the smallest possible normalized number
/arch/arm/boot/dts/ti/omap/
A Dam3874-iceboard.dts105 * of the backplane. Since there are multiply assigned addresses, the
/arch/x86/math-emu/
A DREADME59 (1) Add, subtract, and multiply. Nothing remarkable in these.

Completed in 69 milliseconds