Chris Lattner
ac225ca051
Add a new way to match vector constants, which make it easier to bang bits of
...
different types.
Codegen spltw(0x7FFFFFFF) and spltw(0x80000000) without a constant pool load,
implementing PowerPC/vec_constants.ll:test1. This compiles:
typedef float vf __attribute__ ((vector_size (16)));
typedef int vi __attribute__ ((vector_size (16)));
void test(vi *P1, vi *P2, vf *P3) {
*P1 &= (vi){0x80000000,0x80000000,0x80000000,0x80000000};
*P2 &= (vi){0x7FFFFFFF,0x7FFFFFFF,0x7FFFFFFF,0x7FFFFFFF};
*P3 = vec_abs((vector float)*P3);
}
to:
_test:
mfspr r2, 256
oris r6, r2, 49152
mtspr 256, r6
vspltisw v0, -1
vslw v0, v0, v0
lvx v1, 0, r3
vand v1, v1, v0
stvx v1, 0, r3
lvx v1, 0, r4
vandc v1, v1, v0
stvx v1, 0, r4
lvx v1, 0, r5
vandc v0, v1, v0
stvx v0, 0, r5
mtspr 256, r2
blr
instead of (with two constant pool entries):
_test:
mfspr r2, 256
oris r6, r2, 49152
mtspr 256, r6
li r6, lo16(LCPI1_0)
lis r7, ha16(LCPI1_0)
li r8, lo16(LCPI1_1)
lis r9, ha16(LCPI1_1)
lvx v0, r7, r6
lvx v1, 0, r3
vand v0, v1, v0
stvx v0, 0, r3
lvx v0, r9, r8
lvx v1, 0, r4
vand v1, v1, v0
stvx v1, 0, r4
lvx v1, 0, r5
vand v0, v1, v0
stvx v0, 0, r5
mtspr 256, r2
blr
GCC produces (with 2 cp entries):
_test:
mfspr r0,256
stw r0,-4(r1)
oris r0,r0,0xc00c
mtspr 256,r0
lis r2,ha16(LC0)
lis r9,ha16(LC1)
la r2,lo16(LC0)(r2)
lvx v0,0,r3
lvx v1,0,r5
la r9,lo16(LC1)(r9)
lwz r12,-4(r1)
lvx v12,0,r2
lvx v13,0,r9
vand v0,v0,v12
stvx v0,0,r3
vspltisw v0,-1
vslw v12,v0,v0
vandc v1,v1,v12
stvx v1,0,r5
lvx v0,0,r4
vand v0,v0,v13
stvx v0,0,r4
mtspr 256,r12
blr
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27624 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-12 19:07:14 +00:00
Chris Lattner
4468c22458
Implement an item from the readme, folding vcmp/vcmp. instructions with
...
identical instructions into a single instruction. For example, for:
void test(vector float *x, vector float *y, int *P) {
int v = vec_any_out(*x, *y);
*x = (vector float)vec_cmpb(*x, *y);
*P = v;
}
we now generate:
_test:
mfspr r2, 256
oris r6, r2, 49152
mtspr 256, r6
lvx v0, 0, r4
lvx v1, 0, r3
vcmpbfp. v0, v1, v0
mfcr r4, 2
stvx v0, 0, r3
rlwinm r3, r4, 27, 31, 31
xori r3, r3, 1
stw r3, 0(r5)
mtspr 256, r2
blr
instead of:
_test:
mfspr r2, 256
oris r6, r2, 57344
mtspr 256, r6
lvx v0, 0, r4
lvx v1, 0, r3
vcmpbfp. v2, v1, v0
mfcr r4, 2
*** vcmpbfp v0, v1, v0
rlwinm r4, r4, 27, 31, 31
stvx v0, 0, r3
xori r3, r4, 1
stw r3, 0(r5)
mtspr 256, r2
blr
Testcase here: CodeGen/PowerPC/vcmp-fold.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27290 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-31 06:02:07 +00:00