Viewing file:  vcond_4_costly.c (2.77 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
/* { dg-do compile } */
/* { dg-options "-O2 -ftree-vectorize -fno-vect-cost-model" } */
#include <stdint.h>
#define eq(A, B) ((A) == (B))
#define ne(A, B) ((A) != (B))
#define olt(A, B) ((A) < (B))
#define ole(A, B) ((A) <= (B))
#define oge(A, B) ((A) >= (B))
#define ogt(A, B) ((A) > (B))
#define ordered(A, B) (!__builtin_isunordered (A, B))
#define unordered(A, B) (__builtin_isunordered (A, B))
#define ueq(A, B) (!__builtin_islessgreater (A, B))
#define ult(A, B) (__builtin_isless (A, B))
#define ule(A, B) (__builtin_islessequal (A, B))
#define uge(A, B) (__builtin_isgreaterequal (A, B))
#define ugt(A, B) (__builtin_isgreater (A, B))
#define nueq(A, B) (__builtin_islessgreater (A, B))
#define nult(A, B) (!__builtin_isless (A, B))
#define nule(A, B) (!__builtin_islessequal (A, B))
#define nuge(A, B) (!__builtin_isgreaterequal (A, B))
#define nugt(A, B) (!__builtin_isgreater (A, B))
#define TEST_LOOP(TYPE1, TYPE2, CMP) \
void __attribute__ ((noinline, noclone)) \
test_##TYPE1##_##TYPE2##_##CMP##_var (TYPE1 *restrict dest, \
TYPE1 *restrict src, \
TYPE1 fallback, \
TYPE2 *restrict a, \
TYPE2 *restrict b, \
int count) \
{ \
for (int i = 0; i < count; ++i) \
dest[i] = CMP (a[i], b[i]) ? src[i] : fallback; \
}
#define TEST_CMP(CMP) \
TEST_LOOP (int64_t, float, CMP) \
TEST_LOOP (uint64_t, float, CMP) \
TEST_LOOP (int32_t, double, CMP) \
TEST_LOOP (uint32_t, double, CMP)
TEST_CMP (eq)
TEST_CMP (ne)
TEST_CMP (olt)
TEST_CMP (ole)
TEST_CMP (oge)
TEST_CMP (ogt)
TEST_CMP (ordered)
TEST_CMP (unordered)
TEST_CMP (ueq)
TEST_CMP (ult)
TEST_CMP (ule)
TEST_CMP (uge)
TEST_CMP (ugt)
TEST_CMP (nueq)
TEST_CMP (nult)
TEST_CMP (nule)
TEST_CMP (nuge)
TEST_CMP (nugt)
/* 2 each for: eq, ne, ueq, nueq. */
/* { dg-final { scan-assembler-times {\tfcm(?:eq|ne)\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 8 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcm(?:eq|ne)\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 16 { xfail *-*-* } } } */
/* 2 each for: olt, ult, nult, ogt, ugt, nugt. */
/* { dg-final { scan-assembler-times {\tfcm[lg]t\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 12 } } */
/* { dg-final { scan-assembler-times {\tfcm[lg]t\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 24 } } */
/* 2 each for: ole, ule, nule, oge, uge, nuge. */
/* { dg-final { scan-assembler-times {\tfcm[lg]e\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 12 } } */
/* { dg-final { scan-assembler-times {\tfcm[lg]e\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 24 } } */
/* 2 invocations for all 12 unordered comparisons. */
/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 24 } } */
/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 48 } } */
|
