forked from OSchip/llvm-project
72 lines
2.2 KiB
ArmAsm
72 lines
2.2 KiB
ArmAsm
//===----------------------Hexagon builtin routine ------------------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is dual licensed under the MIT and the University of Illinois Open
|
|
// Source Licenses. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
.macro FUNCTION_BEGIN name
|
|
.text
|
|
.p2align 5
|
|
.globl \name
|
|
.type \name, @function
|
|
\name:
|
|
.endm
|
|
|
|
.macro FUNCTION_END name
|
|
.size \name, . - \name
|
|
.endm
|
|
|
|
|
|
FUNCTION_BEGIN __hexagon_udivdi3
|
|
{
|
|
r6 = cl0(r1:0) // count leading 0's of dividend (numerator)
|
|
r7 = cl0(r3:2) // count leading 0's of divisor (denominator)
|
|
r5:4 = r3:2 // divisor moved into working registers
|
|
r3:2 = r1:0 // dividend is the initial remainder, r3:2 contains remainder
|
|
}
|
|
{
|
|
r10 = sub(r7,r6) // left shift count for bit & divisor
|
|
r1:0 = #0 // initialize quotient to 0
|
|
r15:14 = #1 // initialize bit to 1
|
|
}
|
|
{
|
|
r11 = add(r10,#1) // loop count is 1 more than shift count
|
|
r13:12 = lsl(r5:4,r10) // shift divisor msb into same bit position as dividend msb
|
|
r15:14 = lsl(r15:14,r10) // shift the bit left by same amount as divisor
|
|
}
|
|
{
|
|
p0 = cmp.gtu(r5:4,r3:2) // check if divisor > dividend
|
|
loop0(1f,r11) // register loop
|
|
}
|
|
{
|
|
if (p0) jumpr r31 // if divisor > dividend, we're done, so return
|
|
}
|
|
.falign
|
|
1:
|
|
{
|
|
p0 = cmp.gtu(r13:12,r3:2) // set predicate reg if shifted divisor > current remainder
|
|
}
|
|
{
|
|
r7:6 = sub(r3:2, r13:12) // subtract shifted divisor from current remainder
|
|
r9:8 = add(r1:0, r15:14) // save current quotient to temp (r9:8)
|
|
}
|
|
{
|
|
r1:0 = vmux(p0, r1:0, r9:8) // choose either current quotient or new quotient (r9:8)
|
|
r3:2 = vmux(p0, r3:2, r7:6) // choose either current remainder or new remainder (r7:6)
|
|
}
|
|
{
|
|
r15:14 = lsr(r15:14, #1) // shift bit right by 1 for next iteration
|
|
r13:12 = lsr(r13:12, #1) // shift "shifted divisor" right by 1 for next iteration
|
|
}:endloop0
|
|
{
|
|
jumpr r31 // return
|
|
}
|
|
FUNCTION_END __hexagon_udivdi3
|
|
|
|
.globl __qdsp_udivdi3
|
|
.set __qdsp_udivdi3, __hexagon_udivdi3
|