get_native_u2 & friends

[Edward Nevill]

Hi all,

I think the best thing to do with get_native_u2 and friends is to let the compiler decide
how to access unaligned data. Most modern compilers have some facility for doing this.
In gcc you can use __attribute__((packed)) as follows.

typedef union unaligned {
	unsigned	u;
	unsigned short	us;
	unsigned long long ul;
} __attribute__((packed)) unaligned;

unsigned short get_native_u2(unaligned *p)
{
	return p->us;
}

unsigned get_native_u4(unaligned *p)
{
	return p->u;
}

unsigned long long get_native_u8(unaligned *p)
{
	return p->ul;
}

Below is the code generated for ARM and X86. Note that in the X86 case it just does the access
since X86 allows unaligned accesses whereas for ARM it goes ahead and doesbyte loads.

If on some architechture it is better to test the alignment and then do word/halfword loads if
the pointer is aligned and byte loads otherwise then hopefully the compiler will know the
best code to generate rarther than us trying to second guess what is best on individual
architectures.

Also, in many case these functions are called when it is known that the data is aligned as in
this example from _tableswitch...

      CASE(_tableswitch): {
          jint* lpc  = (jint*)VMalignWordUp(pc+1);
          int32_t  key  = STACK_INT(-1);
          int32_t  low  = Bytes::get_Java_u4((address)&lpc[1]);
          int32_t  high = Bytes::get_Java_u4((address)&lpc[2]);

Maybe it is worth having get_Java_u4() and get_Java_u4_unaligned()?

Regards,
Ed.


--- x86.s --------------------------------------------------------
	.file	"test.c"
	.text
	.p2align 4,,15
.globl get_native_u2
	.type	get_native_u2, @function
get_native_u2:
	pushl	%ebp
	movl	%esp, %ebp
	movl	8(%ebp), %eax
	popl	%ebp
	movzwl	(%eax), %eax
	ret
	.size	get_native_u2, .-get_native_u2
	.p2align 4,,15
.globl get_native_u4
	.type	get_native_u4, @function
get_native_u4:
	pushl	%ebp
	movl	%esp, %ebp
	movl	8(%ebp), %eax
	popl	%ebp
	movl	(%eax), %eax
	ret
	.size	get_native_u4, .-get_native_u4
	.p2align 4,,15
.globl get_native_u8
	.type	get_native_u8, @function
get_native_u8:
	pushl	%ebp
	movl	%esp, %ebp
	movl	8(%ebp), %eax
	popl	%ebp
	movl	4(%eax), %edx
	movl	(%eax), %eax
	ret
	.size	get_native_u8, .-get_native_u8
	.ident	"GCC: (GNU) 4.2.4 (Ubuntu 4.2.4-1ubuntu3)"
	.section	.note.GNU-stack,"", at progbits
--- arm.s -------------------------------------------------------------
	.arch armv5t
	.fpu softvfp
	.eabi_attribute 20, 1
	.eabi_attribute 21, 1
	.eabi_attribute 23, 3
	.eabi_attribute 24, 1
	.eabi_attribute 25, 1
	.eabi_attribute 26, 2
	.eabi_attribute 30, 2
	.eabi_attribute 18, 4
	.file	"test.c"
	.text
	.align	2
	.global	get_native_u2
	.type	get_native_u2, %function
get_native_u2:
	@ args = 0, pretend = 0, frame = 0
	@ frame_needed = 0, uses_anonymous_args = 0
	@ link register save eliminated.
	ldrb	r3, [r0, #1]	@ zero_extendqisi2
	ldrb	r0, [r0, #0]	@ zero_extendqisi2
	orr	r0, r0, r3, asl #8
	bx	lr
	.size	get_native_u2, .-get_native_u2
	.align	2
	.global	get_native_u4
	.type	get_native_u4, %function
get_native_u4:
	@ args = 0, pretend = 0, frame = 0
	@ frame_needed = 0, uses_anonymous_args = 0
	@ link register save eliminated.
	ldrb	r1, [r0, #1]	@ zero_extendqisi2
	ldrb	r3, [r0, #0]	@ zero_extendqisi2
	ldrb	r2, [r0, #2]	@ zero_extendqisi2
	ldrb	r0, [r0, #3]	@ zero_extendqisi2
	orr	r3, r3, r1, asl #8
	orr	r3, r3, r2, asl #16
	orr	r0, r3, r0, asl #24
	bx	lr
	.size	get_native_u4, .-get_native_u4
	.align	2
	.global	get_native_u8
	.type	get_native_u8, %function
get_native_u8:
	@ args = 0, pretend = 0, frame = 0
	@ frame_needed = 0, uses_anonymous_args = 0
	@ link register save eliminated.
	stmfd	sp!, {r4, r5, r6}
	ldrb	r5, [r0, #1]	@ zero_extendqisi2
	ldrb	r6, [r0, #5]	@ zero_extendqisi2
	ldrb	r3, [r0, #0]	@ zero_extendqisi2
	ldrb	ip, [r0, #2]	@ zero_extendqisi2
	ldrb	r1, [r0, #4]	@ zero_extendqisi2
	ldrb	r2, [r0, #6]	@ zero_extendqisi2
	ldrb	r4, [r0, #7]	@ zero_extendqisi2
	ldrb	r0, [r0, #3]	@ zero_extendqisi2
	orr	r3, r3, r5, asl #8
	orr	r1, r1, r6, asl #8
	orr	r3, r3, ip, asl #16
	orr	r1, r1, r2, asl #16
	orr	r0, r3, r0, asl #24
	orr	r1, r1, r4, asl #24
	ldmfd	sp!, {r4, r5, r6}
	bx	lr
	.size	get_native_u8, .-get_native_u8
	.ident	"GCC: (Ubuntu 4.3.3-1ubuntu1) 4.3.3"
	.section	.note.GNU-stack,"",%progbits