| 1 |
/* { dg-do compile } */ |
| 2 |
/* { dg-additional-options "-march=rv64gcv_zvfh_zvl128b -mabi=lp64d -mrvv-vector-bits=zvl -mrvv-max-lmul=m2 -fno-vect-cost-model -ffast-math" } */ |
| 3 |
#include <stdint-gcc.h> |
| 4 |
|
| 5 |
#define TEST_TYPE(TYPE1, TYPE2, N) \ |
| 6 |
__attribute__ ((noipa)) \ |
| 7 |
TYPE1 reduc_##TYPE1##_##TYPE2 (TYPE2 *restrict a, TYPE2 *restrict pred) \ |
| 8 |
{ \ |
| 9 |
TYPE1 sum = 0; \ |
| 10 |
for (int i = 0; i < N; i += 1) \ |
| 11 |
if (pred[i]) \ |
| 12 |
sum += a[i]; \ |
| 13 |
return sum; \ |
| 14 |
} |
| 15 |
|
| 16 |
#define TEST_ALL(TEST) \ |
| 17 |
TEST (int16_t, int8_t, 16) \ |
| 18 |
TEST (int32_t, int8_t, 8) \ |
| 19 |
TEST (int32_t, int16_t, 8) \ |
| 20 |
TEST (int64_t, int8_t, 4) \ |
| 21 |
TEST (int64_t, int16_t, 4) \ |
| 22 |
TEST (int64_t, int32_t, 4) \ |
| 23 |
TEST (uint16_t, uint8_t, 16) \ |
| 24 |
TEST (uint32_t, uint8_t, 8) \ |
| 25 |
TEST (uint32_t, uint16_t, 8) \ |
| 26 |
TEST (uint64_t, uint8_t, 4) \ |
| 27 |
TEST (uint64_t, uint16_t, 4) \ |
| 28 |
TEST (uint64_t, uint32_t, 4) \ |
| 29 |
TEST (float, _Float16, 8) \ |
| 30 |
TEST (double, _Float16, 4) \ |
| 31 |
TEST (double, float, 4) |
| 32 |
|
| 33 |
TEST_ALL (TEST_TYPE) |
| 34 |
|
| 35 |
/* { dg-final { scan-assembler-times {\tvfwredusum\.vs\tv[0-9]+,v[0-9]+,v[0-9]+,v0\.t} 3 } } */ |
| 36 |
/* { dg-final { scan-assembler-times {\tvwredsum\.vs\tv[0-9]+,v[0-9]+,v[0-9]+,v0\.t} 3 } } */ |
| 37 |
/* { dg-final { scan-assembler-times {\tvwredsumu\.vs\tv[0-9]+,v[0-9]+,v[0-9]+,v0\.t} 3 } } */ |
| 38 |
/* { dg-final { scan-assembler-times {\tvsext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */ |
| 39 |
/* { dg-final { scan-assembler-times {\tvsext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */ |
| 40 |
/* { dg-final { scan-assembler-times {\tvzext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */ |
| 41 |
/* { dg-final { scan-assembler-times {\tvzext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */ |