CRUX PPC

The following is the code of vectorized sin computation which uses
a lookup table.

#define NUM_SAMPLES_IN_CIRCLE2 150*1024
extern const int sign_;
extern const int notsign_;
extern __vector float ONE_DIV_PI2_;
extern __vector float numSamples;
extern __vector float sign;
extern __vector float notsign;
extern __vector float vecZeros;
extern float lookup_samples2[NUM_SAMPLES_IN_CIRCLE2];

void vec_fastsin(
__vector float x,
__vector float& result
)
{
__vector long int indexes;
__vector long int temp;
__vector float mask;

mask = vec_and(x,sign);
x = vec_and(x,notsign);
x = vec_madd(x, ONE_DIV_PI2_, vecZeros);
x = vec_sub(x, vec_ctf(vec_cts(x,0),0));
x = vec_madd(x, numSamples, vecZeros);

indexes = vec_cts(x,0);

int *p=((int *) &indexes);
((float *)&result)[0] = lookup_samples2[p[0]];
((float *)&result)[1] = lookup_samples2[p[1]];
((float *)&result)[2] = lookup_samples2[p[2]];
((float *)&result)[3] = lookup_samples2[p[3]];

result=vec_xor(result, mask);
}


I'm using gcc version 2.96 for PowerPC which is included in Tornado 2.2.1 suite:
it works fine when compiling with debug information but using -O2 option it doesn't work.
The problem is that compiler performs an incorrect optimization moving the last vec_xor
before the assignments to result. Doing that it doesn't work only for negative numbers.
It follows the disassembly of the compiled code:

test1.o: file format elf32-powerpc

Disassembly of section .text:

00000000 <vec_fastsin__FEfREf>:
0: 54 2b 07 38 rlwinm r11,r1,0,28,28
4: 21 6b ff e0 subfic r11,r11,-32
8: 7c 21 59 6e stwux r1,r1,r11
c: 3d 60 00 00 lis r11,0
10: 3d 40 00 00 lis r10,0
14: 7c 20 18 ce lvx v1,r0,r3
18: 39 6b 00 00 addi r11,r11,0
1c: 3d 20 00 00 lis r9,0
20: 7d a0 58 ce lvx v13,r0,r11
24: 39 4a 00 00 addi r10,r10,0
28: 39 29 00 00 addi r9,r9,0
2c: 7d 60 48 ce lvx v11,r0,r9
30: 3d 60 00 00 lis r11,0
34: 39 01 00 10 addi r8,r1,16
38: 7d 80 50 ce lvx v12,r0,r10
3c: 3d 20 00 00 lis r9,0
40: 39 6b 00 00 addi r11,r11,0
44: 39 29 00 00 addi r9,r9,0
48: 7d 40 58 ce lvx v10,r0,r11
4c: 3d 40 00 00 lis r10,0
50: 11 a2 6c 04 vand v13,v2,v13
54: 7c 00 48 ce lvx v0,r0,r9
58: 39 4a 00 00 addi r10,r10,0
5c: 11 ad 5b 2e vmaddfp v13,v13,v12,v11
60: 10 42 04 04 vand v2,v2,v0
64: 10 21 14 c4 vxor v1,v1,v2 <----------VXOR is here!!
68: 7c 20 19 ce stvx v1,r0,r3
6c: 10 00 6b ca vctsxs v0,v13,0
70: 10 00 03 4a vcfsx v0,v0,0
74: 11 ad 00 4a vsubfp v13,v13,v0
78: 11 ad 5a ae vmaddfp v13,v13,v10,v11
7c: 11 a0 6b ca vctsxs v13,v13,0
80: 7d a0 41 ce stvx v13,r0,r8
84: 80 01 00 10 lwz r0,16(r1)
88: 81 28 00 04 lwz r9,4(r8)
8c: 54 00 10 3a rlwinm r0,r0,2,0,29
90: 81 68 00 08 lwz r11,8(r8)
94: 7c 0a 04 2e lfsx f0,r10,r0
98: 55 29 10 3a rlwinm r9,r9,2,0,29
9c: d0 03 00 00 stfs f0,0(r3)
a0: 55 6b 10 3a rlwinm r11,r11,2,0,29
a4: 7c 0a 4c 2e lfsx f0,r10,r9
a8: d0 03 00 04 stfs f0,4(r3)
ac: 80 08 00 0c lwz r0,12(r8)
b0: 7c 0a 5c 2e lfsx f0,r10,r11
b4: d0 03 00 08 stfs f0,8(r3)
b8: 54 00 10 3a rlwinm r0,r0,2,0,29
bc: 7c 0a 04 2e lfsx f0,r10,r0
c0: d0 03 00 0c stfs f0,12(r3)
c4: 81 61 00 00 lwz r11,0(r1)
c8: 7d 61 5b 78 mr r1,r11
cc: 4e 80 00 20 blr



as you can note vec_xor is BEFORE the store of result. Do you think this is
a compiler error?

how is this problem related to cruxppc?