RISC-V: Support FP lrint/lrintf auto vectorization
This patch would like to support the FP lrint/lrintf auto vectorization.
* long lrint (double) for rv64
* long lrintf (float) for rv32
Due to the limitation that only the same size of data type are allowed
in the vectorier, the standard name lrintmn2 only act on DF => DI for
rv64, and SF => SI for rv32.
Given we have code like:
void
test_lrint (long *out, double *in, unsigned count)
{
for (unsigned i = 0; i < count; i++)
out[i] = __builtin_lrint (in[i]);
}
Before this patch:
.L3:
...
fld fa5,0(a1)
fcvt.l.d a5,fa5,dyn
sd a5,-8(a0)
...
bne a1,a4,.L3
After this patch:
.L3:
...
vsetvli a3,zero,e64,m1,ta,ma
vfcvt.x.f.v v1,v1
vsetvli zero,a2,e64,m1,ta,ma
vse32.v v1,0(a0)
...
bne a2,zero,.L3
The rest part like SF => DI/HF => DI/DF => SI/HF => SI will be covered
by TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION.
gcc/ChangeLog:
* config/riscv/autovec.md (lrint<mode><vlconvert>2): New pattern
for lrint/lintf.
* config/riscv/riscv-protos.h (expand_vec_lrint): New func decl
for expanding lint.
* config/riscv/riscv-v.cc (emit_vec_cvt_x_f): New helper func impl
for vfcvt.x.f.v.
(expand_vec_lrint): New function impl for expanding lint.
* config/riscv/vector-iterators.md: New mode attr and iterator.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/unop/test-math.h: New define for
CVT like test case.
* gcc.target/riscv/rvv/autovec/vls/def.h: Ditto.
* gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
This commit is contained in:
Pan Li
parent
d4de593d36
commit
d1e5566685
12 changed files with 348 additions and 0 deletions
|
|
@ -2239,6 +2239,7 @@
|
|||
;; - round/roundf
|
||||
;; - trunc/truncf
|
||||
;; - roundeven/roundevenf
|
||||
;; - lrint/lrintf
|
||||
;; -------------------------------------------------------------------------
|
||||
(define_expand "ceil<mode>2"
|
||||
[(match_operand:V_VLSF 0 "register_operand")
|
||||
|
|
@ -2309,3 +2310,13 @@
|
|||
DONE;
|
||||
}
|
||||
)
|
||||
|
||||
(define_expand "lrint<mode><vlconvert>2"
|
||||
[(match_operand:<VLCONVERT> 0 "register_operand")
|
||||
(match_operand:V_VLS_FCONVERTL 1 "register_operand")]
|
||||
"TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
|
||||
{
|
||||
riscv_vector::expand_vec_lrint (operands[0], operands[1], <MODE>mode, <VLCONVERT>mode);
|
||||
DONE;
|
||||
}
|
||||
)
|
||||
|
|
|
|||
|
|
@ -474,6 +474,7 @@ void expand_vec_rint (rtx, rtx, machine_mode, machine_mode);
|
|||
void expand_vec_round (rtx, rtx, machine_mode, machine_mode);
|
||||
void expand_vec_trunc (rtx, rtx, machine_mode, machine_mode);
|
||||
void expand_vec_roundeven (rtx, rtx, machine_mode, machine_mode);
|
||||
void expand_vec_lrint (rtx, rtx, machine_mode, machine_mode);
|
||||
#endif
|
||||
bool sew64_scalar_helper (rtx *, rtx *, rtx, machine_mode,
|
||||
bool, void (*)(rtx *, rtx));
|
||||
|
|
|
|||
|
|
@ -3911,6 +3911,16 @@ emit_vec_cvt_x_f (rtx op_dest, rtx op_src, rtx mask,
|
|||
emit_vlmax_insn (icode, type, cvt_x_ops);
|
||||
}
|
||||
|
||||
static void
|
||||
emit_vec_cvt_x_f (rtx op_dest, rtx op_src, insn_type type,
|
||||
machine_mode vec_mode)
|
||||
{
|
||||
rtx ops[] = {op_dest, op_src};
|
||||
insn_code icode = code_for_pred_fcvt_x_f (UNSPEC_VFCVT, vec_mode);
|
||||
|
||||
emit_vlmax_insn (icode, type, ops);
|
||||
}
|
||||
|
||||
static void
|
||||
emit_vec_cvt_f_x (rtx op_dest, rtx op_src, rtx mask,
|
||||
insn_type type, machine_mode vec_mode)
|
||||
|
|
@ -4095,4 +4105,14 @@ expand_vec_roundeven (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
|||
emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode);
|
||||
}
|
||||
|
||||
void
|
||||
expand_vec_lrint (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_long_mode)
|
||||
{
|
||||
gcc_assert (known_eq (GET_MODE_SIZE (vec_fp_mode),
|
||||
GET_MODE_SIZE (vec_long_mode)));
|
||||
|
||||
emit_vec_cvt_x_f (op_0, op_1, UNARY_OP_FRM_DYN, vec_fp_mode);
|
||||
}
|
||||
|
||||
} // namespace riscv_vector
|
||||
|
|
|
|||
|
|
@ -3281,6 +3281,75 @@
|
|||
(V512DI "v512hf")
|
||||
])
|
||||
|
||||
;; L indicates convert to long
|
||||
(define_mode_attr VLCONVERT [
|
||||
(RVVM8SF "RVVM8SI") (RVVM4SF "RVVM4SI") (RVVM2SF "RVVM2SI")
|
||||
(RVVM1SF "RVVM1SI") (RVVMF2SF "RVVMF2SI")
|
||||
|
||||
(RVVM8DF "RVVM8DI") (RVVM4DF "RVVM4DI") (RVVM2DF "RVVM2DI")
|
||||
(RVVM1DF "RVVM1DI")
|
||||
|
||||
(V1SF "V1SI") (V2SF "V2SI") (V4SF "V4SI") (V8SF "V8SI") (V16SF "V16SI")
|
||||
(V32SF "V32SI") (V64SF "V64SI") (V128SF "V128SI") (V256SF "V256SI")
|
||||
(V512SF "V512SI") (V1024SF "V1024SI")
|
||||
|
||||
(V1DF "V1DI") (V2DF "V2DI") (V4DF "V4DI") (V8DF "V8DI") (V16DF "V16DI")
|
||||
(V32DF "V32DI") (V64DF "V64DI") (V128DF "V128DI") (V256DF "V256DI")
|
||||
(V512DF "V512DI")
|
||||
])
|
||||
|
||||
(define_mode_attr vlconvert [
|
||||
(RVVM8SF "rvvm8si") (RVVM4SF "rvvm4si") (RVVM2SF "rvvm2si")
|
||||
(RVVM1SF "rvvm1si") (RVVMF2SF "rvvmf2si")
|
||||
|
||||
(RVVM8DF "rvvm8di") (RVVM4DF "rvvm4di") (RVVM2DF "rvvm2di")
|
||||
(RVVM1DF "rvvm1di")
|
||||
|
||||
(V1SF "v1si") (V2SF "v2si") (V4SF "v4si") (V8SF "v8si") (V16SF "v16si")
|
||||
(V32SF "v32si") (V64SF "v64si") (V128SF "v128si") (V256SF "v256si")
|
||||
(V512SF "v512si") (V1024SF "v1024si")
|
||||
|
||||
(V1DF "v1di") (V2DF "v2di") (V4DF "v4di") (V8DF "v8di") (V16DF "v16di")
|
||||
(V32DF "v32di") (V64DF "v64di") (V128DF "v128di") (V256DF "v256di")
|
||||
(V512DF "v512di")
|
||||
])
|
||||
|
||||
(define_mode_iterator V_VLS_FCONVERTL [
|
||||
(RVVM8SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(RVVM4SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(RVVM2SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(RVVM1SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(RVVMF2SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN > 32")
|
||||
|
||||
(RVVM8DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(RVVM4DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(RVVM2DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(RVVM1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
|
||||
(V1SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(V2SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(V4SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(V8SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT")
|
||||
(V16SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 64")
|
||||
(V32SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 128")
|
||||
(V64SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 256")
|
||||
(V128SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 512")
|
||||
(V256SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 1024")
|
||||
(V512SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 2048")
|
||||
(V1024SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 4096")
|
||||
|
||||
(V1DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(V2DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(V4DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT")
|
||||
(V8DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 64")
|
||||
(V16DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 128")
|
||||
(V32DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 256")
|
||||
(V64DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 512")
|
||||
(V128DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 1024")
|
||||
(V256DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 2048")
|
||||
(V512DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 4096")
|
||||
])
|
||||
|
||||
(define_mode_attr VDEMOTE [
|
||||
(RVVM8DI "RVVM8SI") (RVVM4DI "RVVM4SI") (RVVM2DI "RVVM2SI") (RVVM1DI "RVVM1SI")
|
||||
(V1DI "V1SI")
|
||||
|
|
|
|||
|
|
@ -0,0 +1,14 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
|
||||
/* { dg-final { check-function-bodies "**" "" } } */
|
||||
|
||||
#include "test-math.h"
|
||||
|
||||
/*
|
||||
** test_double_long___builtin_lrint:
|
||||
** ...
|
||||
** vsetvli\s+[atx][0-9]+,\s*zero,\s*e64,\s*m1,\s*ta,\s*ma
|
||||
** vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (double, long, __builtin_lrint)
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv -mabi=ilp32f -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
|
||||
/* { dg-final { check-function-bodies "**" "" } } */
|
||||
|
||||
#include "test-math.h"
|
||||
|
||||
/*
|
||||
** test_float_long___builtin_lrintf:
|
||||
** ...
|
||||
** vsetvli\s+[atx][0-9]+,\s*zero,\s*e32,\s*m1,\s*ta,\s*ma
|
||||
** vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (float, long, __builtin_lrintf)
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
/* { dg-do run { target { riscv_v && rv64 } } } */
|
||||
/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */
|
||||
|
||||
#include "test-math.h"
|
||||
|
||||
#define ARRAY_SIZE 128
|
||||
|
||||
double in[ARRAY_SIZE];
|
||||
long out[ARRAY_SIZE];
|
||||
long ref[ARRAY_SIZE];
|
||||
|
||||
TEST_UNARY_CALL_CVT (double, long, __builtin_lrint)
|
||||
TEST_ASSERT (long)
|
||||
|
||||
TEST_INIT_CVT (double, 1.2, long, __builtin_lrint (1.2), 1)
|
||||
TEST_INIT_CVT (double, -1.2, long, __builtin_lrint (-1.2), 2)
|
||||
TEST_INIT_CVT (double, 0.5, long, __builtin_lrint (0.5), 3)
|
||||
TEST_INIT_CVT (double, -0.5, long, __builtin_lrint (-0.5), 4)
|
||||
TEST_INIT_CVT (double, 0.1, long, __builtin_lrint (0.1), 5)
|
||||
TEST_INIT_CVT (double, -0.1, long, __builtin_lrint (-0.1), 6)
|
||||
TEST_INIT_CVT (double, 3.0, long, __builtin_lrint (3.0), 7)
|
||||
TEST_INIT_CVT (double, -3.0, long, __builtin_lrint (-3.0), 8)
|
||||
TEST_INIT_CVT (double, 4503599627370495.5, long, __builtin_lrint (4503599627370495.5), 9)
|
||||
TEST_INIT_CVT (double, 4503599627370497.0, long, __builtin_lrint (4503599627370497.0), 10)
|
||||
TEST_INIT_CVT (double, -4503599627370495.5, long, __builtin_lrint (-4503599627370495.5), 11)
|
||||
TEST_INIT_CVT (double, -4503599627370496.0, long, __builtin_lrint (-4503599627370496.0), 12)
|
||||
TEST_INIT_CVT (double, 0.0, long, __builtin_lrint (-0.0), 13)
|
||||
TEST_INIT_CVT (double, -0.0, long, __builtin_lrint (-0.0), 14)
|
||||
TEST_INIT_CVT (double, 9223372036854774784.0, long, __builtin_lrint (9223372036854774784.0), 15)
|
||||
TEST_INIT_CVT (double, 9223372036854775808.0, long, __builtin_lrint (9223372036854775808.0), 16)
|
||||
TEST_INIT_CVT (double, -9223372036854775808.0, long, __builtin_lrint (-9223372036854775808.0), 17)
|
||||
TEST_INIT_CVT (double, -9223372036854777856.0, long, __builtin_lrint (-9223372036854777856.0), 18)
|
||||
TEST_INIT_CVT (double, __builtin_inf (), long, __builtin_lrint (__builtin_inf ()), 19)
|
||||
TEST_INIT_CVT (double, -__builtin_inf (), long, __builtin_lrint (-__builtin_inf ()), 20)
|
||||
TEST_INIT_CVT (double, __builtin_nan (""), long, 0x7fffffffffffffff, 21)
|
||||
|
||||
int
|
||||
main ()
|
||||
{
|
||||
RUN_TEST_CVT (double, long, 1, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 2, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 3, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 4, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 5, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 6, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 7, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 8, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 9, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 10, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 11, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 12, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 13, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 14, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 15, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 16, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 17, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 18, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 19, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 20, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (double, long, 21, __builtin_lrint, in, out, ref, ARRAY_SIZE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
/* { dg-do run { target { riscv_v && rv32 } } } */
|
||||
/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */
|
||||
|
||||
#include "test-math.h"
|
||||
|
||||
#define ARRAY_SIZE 128
|
||||
|
||||
float in[ARRAY_SIZE];
|
||||
long out[ARRAY_SIZE];
|
||||
long ref[ARRAY_SIZE];
|
||||
|
||||
TEST_UNARY_CALL_CVT (float, long, __builtin_lrintf)
|
||||
TEST_ASSERT (long)
|
||||
|
||||
TEST_INIT_CVT (float, 1.2, long, __builtin_lrintf (1.2), 1)
|
||||
TEST_INIT_CVT (float, -1.2, long, __builtin_lrintf (-1.2), 2)
|
||||
TEST_INIT_CVT (float, 0.5, long, __builtin_lrintf (0.5), 3)
|
||||
TEST_INIT_CVT (float, -0.5, long, __builtin_lrintf (-0.5), 4)
|
||||
TEST_INIT_CVT (float, 0.1, long, __builtin_lrintf (0.1), 5)
|
||||
TEST_INIT_CVT (float, -0.1, long, __builtin_lrintf (-0.1), 6)
|
||||
TEST_INIT_CVT (float, 3.0, long, __builtin_lrintf (3.0), 7)
|
||||
TEST_INIT_CVT (float, -3.0, long, __builtin_lrintf (-3.0), 8)
|
||||
TEST_INIT_CVT (float, 8388607.5, long, __builtin_lrintf (8388607.5), 9)
|
||||
TEST_INIT_CVT (float, 8388609.0, long, __builtin_lrintf (8388609.0), 10)
|
||||
TEST_INIT_CVT (float, -8388607.5, long, __builtin_lrintf (-8388607.5), 11)
|
||||
TEST_INIT_CVT (float, -8388609.0, long, __builtin_lrintf (-8388609.0), 12)
|
||||
TEST_INIT_CVT (float, 0.0, long, __builtin_lrintf (-0.0), 13)
|
||||
TEST_INIT_CVT (float, -0.0, long, __builtin_lrintf (-0.0), 14)
|
||||
TEST_INIT_CVT (float, 2147483520.0, long, __builtin_lrintf (2147483520.0), 15)
|
||||
TEST_INIT_CVT (float, 2147483648.0, long, __builtin_lrintf (2147483648.0), 16)
|
||||
TEST_INIT_CVT (float, -2147483648.0, long, __builtin_lrintf (-2147483648.0), 17)
|
||||
TEST_INIT_CVT (float, -2147483904.0, long, __builtin_lrintf (-2147483904.0), 18)
|
||||
TEST_INIT_CVT (float, __builtin_inf (), long, __builtin_lrintf (__builtin_inff ()), 19)
|
||||
TEST_INIT_CVT (float, -__builtin_inf (), long, __builtin_lrintf (-__builtin_inff ()), 20)
|
||||
TEST_INIT_CVT (float, __builtin_nanf (""), long, 0x7fffffff, 21)
|
||||
|
||||
int
|
||||
main ()
|
||||
{
|
||||
RUN_TEST_CVT (float, long, 1, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 2, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 3, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 4, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 5, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 6, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 7, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 8, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 9, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 10, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 11, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 12, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 13, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 14, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 15, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 16, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 17, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 18, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 19, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 20, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
RUN_TEST_CVT (float, long, 21, __builtin_lrintf, in, out, ref, ARRAY_SIZE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -5,6 +5,14 @@
|
|||
out[i] = CALL (in[i]); \
|
||||
}
|
||||
|
||||
#define TEST_UNARY_CALL_CVT(TYPE_IN, TYPE_OUT, CALL) \
|
||||
void test_##TYPE_IN##_##TYPE_OUT##_##CALL ( \
|
||||
TYPE_OUT *out, TYPE_IN *in, unsigned count) \
|
||||
{ \
|
||||
for (unsigned i = 0; i < count; i++) \
|
||||
out[i] = CALL (in[i]); \
|
||||
}
|
||||
|
||||
#define TEST_COND_UNARY_CALL(TYPE, CALL) \
|
||||
void test_##TYPE##_##CALL (TYPE *out, int *cond, TYPE *in, unsigned count) \
|
||||
{ \
|
||||
|
|
@ -22,6 +30,17 @@
|
|||
} \
|
||||
}
|
||||
|
||||
#define TEST_INIT_CVT(TYPE_IN, VAL_IN, TYPE_REF, VAL_REF, NUM) \
|
||||
void test_##TYPE_IN##_##TYPE_REF##_init_##NUM ( \
|
||||
TYPE_IN *in, TYPE_REF *ref, unsigned size) \
|
||||
{ \
|
||||
for (unsigned i = 0; i < size; i++) \
|
||||
{ \
|
||||
in[i] = VAL_IN; \
|
||||
ref[i] = VAL_REF; \
|
||||
} \
|
||||
}
|
||||
|
||||
#define TEST_ASSERT(TYPE) \
|
||||
void test_##TYPE##_assert (TYPE *out, TYPE *ref, unsigned size) \
|
||||
{ \
|
||||
|
|
@ -37,6 +56,11 @@
|
|||
test_##TYPE##_##CALL (OUT, IN, SIZE); \
|
||||
test_##TYPE##_assert (OUT, REF, SIZE);
|
||||
|
||||
#define RUN_TEST_CVT(TYPE_IN, TYPE_OUT, NUM, CALL, IN, OUT, REF, SIZE) \
|
||||
test_##TYPE_IN##_##TYPE_OUT##_init_##NUM (IN, REF, SIZE); \
|
||||
test_##TYPE_IN##_##TYPE_OUT##_##CALL (OUT, IN, SIZE); \
|
||||
test_##TYPE_OUT##_assert (OUT, REF, SIZE);
|
||||
|
||||
#define FRM_RNE 0
|
||||
#define FRM_RTZ 1
|
||||
#define FRM_RDN 2
|
||||
|
|
|
|||
|
|
@ -213,6 +213,15 @@ typedef double v512df __attribute__ ((vector_size (4096)));
|
|||
a[i] = OP (b[i]); \
|
||||
}
|
||||
|
||||
#define DEF_OP_V_CVT(PREFIX, NUM, TYPE_IN, TYPE_OUT, OP) \
|
||||
void __attribute__ ((noinline, noclone)) \
|
||||
PREFIX##_##TYPE_IN##_##TYPE_OUT##_##NUM (TYPE_OUT *restrict a, \
|
||||
TYPE_IN *restrict b) \
|
||||
{ \
|
||||
for (int i = 0; i < NUM; ++i) \
|
||||
a[i] = OP (b[i]); \
|
||||
}
|
||||
|
||||
#define DEF_CALL_VV(PREFIX, NUM, TYPE, CALL) \
|
||||
void __attribute__ ((noinline, noclone)) \
|
||||
PREFIX##_##TYPE##NUM (TYPE *restrict a, TYPE *restrict b, TYPE *restrict c) \
|
||||
|
|
|
|||
|
|
@ -0,0 +1,30 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv_zvfh_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
|
||||
|
||||
#include "def.h"
|
||||
|
||||
DEF_OP_V_CVT (lrint, 1, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 2, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 4, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 8, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 16, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 32, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 64, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 128, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 256, double, long, __builtin_lrint)
|
||||
DEF_OP_V_CVT (lrint, 512, double, long, __builtin_lrint)
|
||||
|
||||
/* { dg-final { scan-assembler-not {csrr} } } */
|
||||
/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "1024,1024" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */
|
||||
/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv_zvfh_zvl4096b -mabi=ilp32f -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
|
||||
|
||||
#include "def.h"
|
||||
|
||||
DEF_OP_V_CVT (lrintf, 1, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 2, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 4, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 8, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 16, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 32, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 64, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 128, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 256, float, long, __builtin_lrintf)
|
||||
DEF_OP_V_CVT (lrintf, 512, float, long, __builtin_lrintf)
|
||||
|
||||
/* { dg-final { scan-assembler-not {csrr} } } */
|
||||
/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "1024,1024" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */
|
||||
/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */
|
||||
/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
Loading…
Add table
Reference in a new issue