forked from OSchip/llvm-project
104 lines
2.5 KiB
ArmAsm
104 lines
2.5 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.
|
||
|
|
//
|
||
|
|
//===----------------------------------------------------------------------===//
|
||
|
|
|
||
|
|
/* Functions that implement common sequences in function prologues and epilogues
|
||
|
|
used to save code size */
|
||
|
|
|
||
|
|
.macro FUNCTION_BEGIN name
|
||
|
|
.text
|
||
|
|
.globl \name
|
||
|
|
.type \name, @function
|
||
|
|
.falign
|
||
|
|
\name:
|
||
|
|
.endm
|
||
|
|
|
||
|
|
.macro FUNCTION_END name
|
||
|
|
.size \name, . - \name
|
||
|
|
.endm
|
||
|
|
|
||
|
|
.macro FALLTHROUGH_TAIL_CALL name0 name1
|
||
|
|
.size \name0, . - \name0
|
||
|
|
.globl \name1
|
||
|
|
.type \name1, @function
|
||
|
|
.falign
|
||
|
|
\name1:
|
||
|
|
.endm
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
/* Save r25:24 at fp+#-8 and r27:26 at fp+#-16. */
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
/* The compiler knows that the __save_* functions clobber LR. No other
|
||
|
|
registers should be used without informing the compiler. */
|
||
|
|
|
||
|
|
/* Since we can only issue one store per packet, we don't hurt performance by
|
||
|
|
simply jumping to the right point in this sequence of stores. */
|
||
|
|
|
||
|
|
FUNCTION_BEGIN __save_r24_through_r27
|
||
|
|
memd(fp+#-16) = r27:26
|
||
|
|
FALLTHROUGH_TAIL_CALL __save_r24_through_r27 __save_r24_through_r25
|
||
|
|
{
|
||
|
|
memd(fp+#-8) = r25:24
|
||
|
|
jumpr lr
|
||
|
|
}
|
||
|
|
FUNCTION_END __save_r24_through_r25
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
/* For each of the *_before_tailcall functions, jumpr lr is executed in parallel
|
||
|
|
with deallocframe. That way, the return gets the old value of lr, which is
|
||
|
|
where these functions need to return, and at the same time, lr gets the value
|
||
|
|
it needs going into the tail call. */
|
||
|
|
|
||
|
|
FUNCTION_BEGIN __restore_r24_through_r27_and_deallocframe_before_tailcall
|
||
|
|
r27:26 = memd(fp+#-16)
|
||
|
|
FALLTHROUGH_TAIL_CALL __restore_r24_through_r27_and_deallocframe_before_tailcall __restore_r24_through_r25_and_deallocframe_before_tailcall
|
||
|
|
{
|
||
|
|
r25:24 = memd(fp+#-8)
|
||
|
|
deallocframe
|
||
|
|
jumpr lr
|
||
|
|
}
|
||
|
|
FUNCTION_END __restore_r24_through_r25_and_deallocframe_before_tailcall
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
/* Here we use the extra load bandwidth to restore LR early, allowing the return
|
||
|
|
to occur in parallel with the deallocframe. */
|
||
|
|
|
||
|
|
FUNCTION_BEGIN __restore_r24_through_r27_and_deallocframe
|
||
|
|
{
|
||
|
|
lr = memw(fp+#4)
|
||
|
|
r27:26 = memd(fp+#-16)
|
||
|
|
}
|
||
|
|
{
|
||
|
|
r25:24 = memd(fp+#-8)
|
||
|
|
deallocframe
|
||
|
|
jumpr lr
|
||
|
|
}
|
||
|
|
FUNCTION_END __restore_r24_through_r27_and_deallocframe
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
/* Here the load bandwidth is maximized. */
|
||
|
|
|
||
|
|
FUNCTION_BEGIN __restore_r24_through_r25_and_deallocframe
|
||
|
|
{
|
||
|
|
r25:24 = memd(fp+#-8)
|
||
|
|
deallocframe
|
||
|
|
}
|
||
|
|
jumpr lr
|
||
|
|
FUNCTION_END __restore_r24_through_r25_and_deallocframe
|