Re: [PATCH V3] RISC-V: Fix bug of pre-calculated const vector mask for VNx1BI, VNx2BI and VNx4BI

[Jeff Law <jeffreyalaw@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 1213 bytes --]



On 6/28/23 03:47, Juzhe-Zhong wrote:
> This bug blocks the following patches.
> 
> GCC doesn't know RVV is using compact mask model.
> Consider this following case:
> 
> #define N 16
> 
> int
> main ()
> {
>    int8_t mask[N] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
>    int8_t out[N] = {0};
>    for (int8_t i = 0; i < N; ++i)
>      if (mask[i])
>        out[i] = i;
>    for (int8_t i = 0; i < N; ++i)
>      {
>        if (mask[i])
> 	assert (out[i] == i);
>        else
> 	assert (out[i] == 0);
>      }
> }
> 
> Before this patch, the pre-calculated mask in constant memory pool:
> .LC1:
>          .byte   68 ====> 0b01000100
> 
> This is incorrect, such case failed in execution.
> 
> After this patch:
> .LC1:
> 	.byte	10 ====> 0b1010
So I don't get anything like this in my testing.  What are the precise 
arguments you're using to build the testcase?

I'm compiling the test use a trunk compiler with

  -O3 --param riscv-autovec-preference=fixed-vlmax -march=rv64gcv

I get the attached code both before and after your patch.  Clearly I'm 
doing something different/wrong.    So my request is for the precise 
command line you're using and the before/after resulting assembly code.

Jeff

[-- Attachment #2: j.s --]
[-- Type: text/plain, Size: 2415 bytes --]

	.file	"j.c"
	.option nopic
	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_v1p0_zicsr2p0_zifencei2p0_zve32f1p0_zve32x1p0_zve64d1p0_zve64f1p0_zve64x1p0_zvl128b1p0_zvl32b1p0_zvl64b1p0"
	.attribute unaligned_access, 0
	.attribute stack_align, 16
	.text
	.section	.rodata.str1.8,"aMS",@progbits,1
	.align	3
.LC1:
	.string	"j.c"
	.align	3
.LC2:
	.string	"out[i] == i"
	.align	3
.LC3:
	.string	"out[i] == 0"
	.section	.text.startup,"ax",@progbits
	.align	1
	.globl	main
	.type	main, @function
main:
.LFB0:
	.cfi_startproc
	lui	a5,%hi(.LANCHOR0)
	addi	a5,a5,%lo(.LANCHOR0)
	ld	a4,0(a5)
	ld	a5,8(a5)
	addi	sp,sp,-48
	.cfi_def_cfa_offset 48
	vsetivli	zero,16,e8,m1,ta,ma
	sd	zero,16(sp)
	sd	a4,0(sp)
	sd	a5,8(sp)
	sd	ra,40(sp)
	.cfi_offset 1, -8
	addi	a5,sp,16
	sd	zero,24(sp)
	vid.v	v1
	vl1re8.v	v0,0(sp)
	vmsne.vi	v0,v0,0
	vsetvli	a4,zero,e8,m1,ta,ma
	vse8.v	v1,0(a5),v0.t
	lbu	a5,16(sp)
	bne	a5,zero,.L2
	lbu	a4,17(sp)
	li	a5,1
	bne	a4,a5,.L3
	lbu	a5,18(sp)
	bne	a5,zero,.L2
	lbu	a4,19(sp)
	li	a5,3
	bne	a4,a5,.L3
	lbu	a5,20(sp)
	bne	a5,zero,.L2
	lbu	a4,21(sp)
	li	a5,5
	bne	a4,a5,.L3
	lbu	a5,22(sp)
	bne	a5,zero,.L2
	lbu	a4,23(sp)
	li	a5,7
	bne	a4,a5,.L3
	lbu	a5,24(sp)
	bne	a5,zero,.L2
	lbu	a4,25(sp)
	li	a5,9
	bne	a4,a5,.L3
	lbu	a5,26(sp)
	bne	a5,zero,.L2
	lbu	a4,27(sp)
	li	a5,11
	bne	a4,a5,.L3
	lbu	a5,28(sp)
	bne	a5,zero,.L2
	lbu	a4,29(sp)
	li	a5,13
	bne	a4,a5,.L3
	lbu	a5,30(sp)
	bne	a5,zero,.L2
	lbu	a4,31(sp)
	li	a5,15
	bne	a4,a5,.L3
	ld	ra,40(sp)
	.cfi_remember_state
	.cfi_restore 1
	li	a0,0
	addi	sp,sp,48
	.cfi_def_cfa_offset 0
	jr	ra
.L2:
	.cfi_restore_state
	lui	a3,%hi(__PRETTY_FUNCTION__.0)
	lui	a1,%hi(.LC1)
	lui	a0,%hi(.LC3)
	addi	a3,a3,%lo(__PRETTY_FUNCTION__.0)
	li	a2,18
	addi	a1,a1,%lo(.LC1)
	addi	a0,a0,%lo(.LC3)
	call	__assert_fail
.L3:
	lui	a3,%hi(__PRETTY_FUNCTION__.0)
	lui	a1,%hi(.LC1)
	lui	a0,%hi(.LC2)
	addi	a3,a3,%lo(__PRETTY_FUNCTION__.0)
	li	a2,16
	addi	a1,a1,%lo(.LC1)
	addi	a0,a0,%lo(.LC2)
	call	__assert_fail
	.cfi_endproc
.LFE0:
	.size	main, .-main
	.section	.rodata
	.align	3
	.set	.LANCHOR0,. + 0
.LC0:
	.string	""
	.string	"\001"
	.string	"\001"
	.string	"\001"
	.string	"\001"
	.string	"\001"
	.string	"\001"
	.string	"\001"
	.ascii	"\001"
	.section	.srodata,"a"
	.align	3
	.type	__PRETTY_FUNCTION__.0, @object
	.size	__PRETTY_FUNCTION__.0, 5
__PRETTY_FUNCTION__.0:
	.string	"main"
	.ident	"GCC: (GNU) 14.0.0 20230628 (experimental)"
	.section	.note.GNU-stack,"",@progbits