RISC-V: Support FP l/ll round and rint HF mode autovec
This patch would like to support the FP below API auto vectorization
with different type size
+------------+-----------+----------+
| API | RV64 | RV32 |
+------------+-----------+----------+
| lrintf16 | HF => DI | HF => SI |
| llrintf16 | HF => DI | HF => DI |
| lroundf16 | HF => DI | HF => SI |
| llroundf16 | HF => DI | HF => DI |
+------------+-----------+----------+
Given below code:
void
test_lrintf16 (long *out, _Float16 *in, int count)
{
for (unsigned i = 0; i < count; i++)
out[i] = __builtin_lrintf16 (in[i]);
}
Before this patch:
.L3:
lhu a5,0(s0)
addi s0,s0,2
addi s1,s1,8
fmv.s.x fa0,a5
call lrintf16
sd a0,-8(s1)
bne s0,s2,.L3
After this patch:
.L3:
vsetvli a5,a2,e16,mf4,ta,ma
vle16.v v1,0(a1)
vfwcvt.f.f.v v2,v1
vsetvli zero,zero,e32,mf2,ta,ma
vfwcvt.x.f.v v1,v2
vse64.v v1,0(a0)
slli a4,a5,1
add a1,a1,a4
slli a4,a5,3
add a0,a0,a4
sub a2,a2,a5
bne a2,zero,.L3
gcc/ChangeLog:
* config/riscv/autovec.md: Add bridge mode to lrint and lround
pattern.
* config/riscv/riscv-protos.h (expand_vec_lrint): Add new arg
bridge machine mode.
(expand_vec_lround): Ditto.
* config/riscv/riscv-v.cc (emit_vec_widden_cvt_f_f): New helper
func impl to emit vfwcvt.f.f.
(emit_vec_rounding_to_integer): Handle the HF to DI rounding
with the bridge mode.
(expand_vec_lrint): Reorder the args.
(expand_vec_lround): Ditto.
(expand_vec_lceil): Ditto.
(expand_vec_lfloor): Ditto.
* config/riscv/vector-iterators.md: Add vector HFmode and bridge
mode for converting to DI.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/unop/math-llrintf16-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-llroundf16-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lrintf16-rv32-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lrintf16-rv64-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lroundf16-rv32-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-lroundf16-rv64-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-llrintf16-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-llroundf16-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lrintf16-rv32-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lrintf16-rv64-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lroundf16-rv32-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-lroundf16-rv64-0.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
This commit is contained in:
Pan Li
parent
93e92b2e5d
commit
5dfa501d2f
16 changed files with 397 additions and 24 deletions
|
|
@ -2455,14 +2455,13 @@
|
|||
}
|
||||
)
|
||||
|
||||
;; Add mode_size equal check as we opened the modes for different sizes.
|
||||
;; The check will be removed soon after related codegen implemented
|
||||
(define_expand "lrint<mode><v_f2si_convert>2"
|
||||
[(match_operand:<V_F2SI_CONVERT> 0 "register_operand")
|
||||
(match_operand:V_VLS_F_CONVERT_SI 1 "register_operand")]
|
||||
"TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
|
||||
{
|
||||
riscv_vector::expand_vec_lrint (operands[0], operands[1], <MODE>mode, <V_F2SI_CONVERT>mode);
|
||||
riscv_vector::expand_vec_lrint (operands[0], operands[1], <MODE>mode,
|
||||
<V_F2SI_CONVERT>mode, VOIDmode);
|
||||
DONE;
|
||||
}
|
||||
)
|
||||
|
|
@ -2472,7 +2471,9 @@
|
|||
(match_operand:V_VLS_F_CONVERT_DI 1 "register_operand")]
|
||||
"TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
|
||||
{
|
||||
riscv_vector::expand_vec_lrint (operands[0], operands[1], <MODE>mode, <V_F2DI_CONVERT>mode);
|
||||
riscv_vector::expand_vec_lrint (operands[0], operands[1], <MODE>mode,
|
||||
<V_F2DI_CONVERT>mode,
|
||||
<V_F2DI_CONVERT_BRIDGE>mode);
|
||||
DONE;
|
||||
}
|
||||
)
|
||||
|
|
@ -2482,7 +2483,8 @@
|
|||
(match_operand:V_VLS_F_CONVERT_SI 1 "register_operand")]
|
||||
"TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
|
||||
{
|
||||
riscv_vector::expand_vec_lround (operands[0], operands[1], <MODE>mode, <V_F2SI_CONVERT>mode);
|
||||
riscv_vector::expand_vec_lround (operands[0], operands[1], <MODE>mode,
|
||||
<V_F2SI_CONVERT>mode, VOIDmode);
|
||||
DONE;
|
||||
}
|
||||
)
|
||||
|
|
@ -2492,7 +2494,10 @@
|
|||
(match_operand:V_VLS_F_CONVERT_DI 1 "register_operand")]
|
||||
"TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
|
||||
{
|
||||
riscv_vector::expand_vec_lround (operands[0], operands[1], <MODE>mode, <V_F2DI_CONVERT>mode);
|
||||
riscv_vector::expand_vec_lround (operands[0], operands[1], <MODE>mode,
|
||||
<V_F2DI_CONVERT>mode,
|
||||
<V_F2DI_CONVERT_BRIDGE>mode);
|
||||
|
||||
DONE;
|
||||
}
|
||||
)
|
||||
|
|
|
|||
|
|
@ -514,8 +514,8 @@ 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);
|
||||
void expand_vec_lround (rtx, rtx, machine_mode, machine_mode);
|
||||
void expand_vec_lrint (rtx, rtx, machine_mode, machine_mode, machine_mode);
|
||||
void expand_vec_lround (rtx, rtx, machine_mode, machine_mode, machine_mode);
|
||||
void expand_vec_lceil (rtx, rtx, machine_mode, machine_mode);
|
||||
void expand_vec_lfloor (rtx, rtx, machine_mode, machine_mode);
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -4001,6 +4001,16 @@ emit_vec_widden_cvt_x_f (rtx op_dest, rtx op_src, insn_type type,
|
|||
emit_vlmax_insn (icode, type, ops);
|
||||
}
|
||||
|
||||
static void
|
||||
emit_vec_widden_cvt_f_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_extend (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)
|
||||
|
|
@ -4195,8 +4205,10 @@ expand_vec_roundeven (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
|||
|
||||
/* Handling the rounding from floating-point to int/long/long long. */
|
||||
static void
|
||||
emit_vec_rounding_to_integer (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode, insn_type type)
|
||||
emit_vec_rounding_to_integer (rtx op_0, rtx op_1, insn_type type,
|
||||
machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode,
|
||||
machine_mode vec_bridge_mode = E_VOIDmode)
|
||||
{
|
||||
poly_uint16 vec_fp_size = GET_MODE_SIZE (vec_fp_mode);
|
||||
poly_uint16 vec_int_size = GET_MODE_SIZE (vec_int_mode);
|
||||
|
|
@ -4205,42 +4217,53 @@ emit_vec_rounding_to_integer (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
|||
emit_vec_cvt_x_f (op_0, op_1, type, vec_fp_mode);
|
||||
else if (maybe_eq (vec_fp_size, vec_int_size * 2)) /* DF => SI. */
|
||||
emit_vec_narrow_cvt_x_f (op_0, op_1, type, vec_fp_mode);
|
||||
else if (maybe_eq (vec_fp_size * 2, vec_int_size)) /* SF => DI. */
|
||||
else if (maybe_eq (vec_fp_size * 2, vec_int_size)) /* SF => DI, HF => SI. */
|
||||
emit_vec_widden_cvt_x_f (op_0, op_1, type, vec_int_mode);
|
||||
else /* HF requires additional middle-end support. */
|
||||
else if (maybe_eq (vec_fp_size * 4, vec_int_size)) /* HF => DI. */
|
||||
{
|
||||
gcc_assert (vec_bridge_mode != E_VOIDmode);
|
||||
|
||||
rtx op_sf = gen_reg_rtx (vec_bridge_mode);
|
||||
|
||||
/* Step-1: HF => SF, no rounding here. */
|
||||
emit_vec_widden_cvt_f_f (op_sf, op_1, UNARY_OP, vec_bridge_mode);
|
||||
/* Step-2: SF => DI. */
|
||||
emit_vec_widden_cvt_x_f (op_0, op_sf, type, vec_int_mode);
|
||||
}
|
||||
else
|
||||
gcc_unreachable ();
|
||||
}
|
||||
|
||||
void
|
||||
expand_vec_lrint (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode)
|
||||
machine_mode vec_int_mode, machine_mode vec_bridge_mode)
|
||||
{
|
||||
emit_vec_rounding_to_integer (op_0, op_1, vec_fp_mode, vec_int_mode,
|
||||
UNARY_OP_FRM_DYN);
|
||||
emit_vec_rounding_to_integer (op_0, op_1, UNARY_OP_FRM_DYN, vec_fp_mode,
|
||||
vec_int_mode, vec_bridge_mode);
|
||||
}
|
||||
|
||||
void
|
||||
expand_vec_lround (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode)
|
||||
machine_mode vec_int_mode, machine_mode vec_bridge_mode)
|
||||
{
|
||||
emit_vec_rounding_to_integer (op_0, op_1, vec_fp_mode, vec_int_mode,
|
||||
UNARY_OP_FRM_RMM);
|
||||
emit_vec_rounding_to_integer (op_0, op_1, UNARY_OP_FRM_RMM, vec_fp_mode,
|
||||
vec_int_mode, vec_bridge_mode);
|
||||
}
|
||||
|
||||
void
|
||||
expand_vec_lceil (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode)
|
||||
{
|
||||
emit_vec_rounding_to_integer (op_0, op_1, vec_fp_mode, vec_int_mode,
|
||||
UNARY_OP_FRM_RUP);
|
||||
emit_vec_rounding_to_integer (op_0, op_1, UNARY_OP_FRM_RUP, vec_fp_mode,
|
||||
vec_int_mode);
|
||||
}
|
||||
|
||||
void
|
||||
expand_vec_lfloor (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
|
||||
machine_mode vec_int_mode)
|
||||
{
|
||||
emit_vec_rounding_to_integer (op_0, op_1, vec_fp_mode, vec_int_mode,
|
||||
UNARY_OP_FRM_RDN);
|
||||
emit_vec_rounding_to_integer (op_0, op_1, UNARY_OP_FRM_RDN, vec_fp_mode,
|
||||
vec_int_mode);
|
||||
}
|
||||
|
||||
/* Vectorize popcount by the Wilkes-Wheeler-Gill algorithm that libgcc uses as
|
||||
|
|
|
|||
|
|
@ -3221,15 +3221,20 @@
|
|||
;; V_F2SI_CONVERT: (HF, SF, DF) => SI
|
||||
;; V_F2DI_CONVERT: (HF, SF, DF) => DI
|
||||
;;
|
||||
;; HF requires additional support from internal function, aka
|
||||
;; gcc/internal-fn.def, remove HF shortly until the middle-end is ready.
|
||||
(define_mode_attr V_F2SI_CONVERT [
|
||||
(RVVM4HF "RVVM8SI") (RVVM2HF "RVVM4SI") (RVVM1HF "RVVM2SI")
|
||||
(RVVMF2HF "RVVM1SI") (RVVMF4HF "RVVMF2SI")
|
||||
|
||||
(RVVM8SF "RVVM8SI") (RVVM4SF "RVVM4SI") (RVVM2SF "RVVM2SI")
|
||||
(RVVM1SF "RVVM1SI") (RVVMF2SF "RVVMF2SI")
|
||||
|
||||
(RVVM8DF "RVVM4SI") (RVVM4DF "RVVM2SI") (RVVM2DF "RVVM1SI")
|
||||
(RVVM1DF "RVVMF2SI")
|
||||
|
||||
(V1HF "V1SI") (V2HF "V2SI") (V4HF "V4SI") (V8HF "V8SI") (V16HF "V16SI")
|
||||
(V32HF "V32SI") (V64HF "V64SI") (V128HF "V128SI") (V256HF "V256SI")
|
||||
(V512HF "V512SI") (V1024HF "V1024SI")
|
||||
|
||||
(V1SF "V1SI") (V2SF "V2SI") (V4SF "V4SI") (V8SF "V8SI") (V16SF "V16SI")
|
||||
(V32SF "V32SI") (V64SF "V64SI") (V128SF "V128SI") (V256SF "V256SI")
|
||||
(V512SF "V512SI") (V1024SF "V1024SI")
|
||||
|
|
@ -3240,12 +3245,19 @@
|
|||
])
|
||||
|
||||
(define_mode_attr v_f2si_convert [
|
||||
(RVVM4HF "rvvm8si") (RVVM2HF "rvvm4si") (RVVM1HF "rvvm2si")
|
||||
(RVVMF2HF "rvvm1si") (RVVMF4HF "rvvmf2si")
|
||||
|
||||
(RVVM8SF "rvvm8si") (RVVM4SF "rvvm4si") (RVVM2SF "rvvm2si")
|
||||
(RVVM1SF "rvvm1si") (RVVMF2SF "rvvmf2si")
|
||||
|
||||
(RVVM8DF "rvvm4si") (RVVM4DF "rvvm2si") (RVVM2DF "rvvm1si")
|
||||
(RVVM1DF "rvvmf2si")
|
||||
|
||||
(V1HF "v1si") (V2HF "v2si") (V4HF "v4si") (V8HF "v8si") (V16HF "v16si")
|
||||
(V32HF "v32si") (V64HF "v64si") (V128HF "v128si") (V256HF "v256si")
|
||||
(V512HF "v512si") (V1024HF "v1024si")
|
||||
|
||||
(V1SF "v1si") (V2SF "v2si") (V4SF "v4si") (V8SF "v8si") (V16SF "v16si")
|
||||
(V32SF "v32si") (V64SF "v64si") (V128SF "v128si") (V256SF "v256si")
|
||||
(V512SF "v512si") (V1024SF "v1024si")
|
||||
|
|
@ -3256,6 +3268,9 @@
|
|||
])
|
||||
|
||||
(define_mode_iterator V_VLS_F_CONVERT_SI [
|
||||
(RVVM4HF "TARGET_ZVFH") (RVVM2HF "TARGET_ZVFH") (RVVM1HF "TARGET_ZVFH")
|
||||
(RVVMF2HF "TARGET_ZVFH") (RVVMF4HF "TARGET_ZVFH && TARGET_MIN_VLEN > 32")
|
||||
|
||||
(RVVM8SF "TARGET_VECTOR_ELEN_FP_32") (RVVM4SF "TARGET_VECTOR_ELEN_FP_32")
|
||||
(RVVM2SF "TARGET_VECTOR_ELEN_FP_32") (RVVM1SF "TARGET_VECTOR_ELEN_FP_32")
|
||||
(RVVMF2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32")
|
||||
|
|
@ -3265,6 +3280,18 @@
|
|||
(RVVM2DF "TARGET_VECTOR_ELEN_FP_64")
|
||||
(RVVM1DF "TARGET_VECTOR_ELEN_FP_64")
|
||||
|
||||
(V1HF "riscv_vector::vls_mode_valid_p (V1HFmode) && TARGET_ZVFH")
|
||||
(V2HF "riscv_vector::vls_mode_valid_p (V2HFmode) && TARGET_ZVFH")
|
||||
(V4HF "riscv_vector::vls_mode_valid_p (V4HFmode) && TARGET_ZVFH")
|
||||
(V8HF "riscv_vector::vls_mode_valid_p (V8HFmode) && TARGET_ZVFH")
|
||||
(V16HF "riscv_vector::vls_mode_valid_p (V16HFmode) && TARGET_ZVFH")
|
||||
(V32HF "riscv_vector::vls_mode_valid_p (V32HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 64")
|
||||
(V64HF "riscv_vector::vls_mode_valid_p (V64HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 128")
|
||||
(V128HF "riscv_vector::vls_mode_valid_p (V128HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 256")
|
||||
(V256HF "riscv_vector::vls_mode_valid_p (V256HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 512")
|
||||
(V512HF "riscv_vector::vls_mode_valid_p (V512HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 1024")
|
||||
(V1024HF "riscv_vector::vls_mode_valid_p (V1024HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 2048")
|
||||
|
||||
(V1SF "riscv_vector::vls_mode_valid_p (V1SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
(V2SF "riscv_vector::vls_mode_valid_p (V2SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
(V4SF "riscv_vector::vls_mode_valid_p (V4SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
|
|
@ -3290,12 +3317,19 @@
|
|||
])
|
||||
|
||||
(define_mode_attr V_F2DI_CONVERT [
|
||||
(RVVM2HF "RVVM8DI") (RVVM1HF "RVVM4DI") (RVVMF2HF "RVVM2DI")
|
||||
(RVVMF4HF "RVVM1DI")
|
||||
|
||||
(RVVM4SF "RVVM8DI") (RVVM2SF "RVVM4DI") (RVVM1SF "RVVM2DI")
|
||||
(RVVMF2SF "RVVM1DI")
|
||||
|
||||
(RVVM8DF "RVVM8DI") (RVVM4DF "RVVM4DI") (RVVM2DF "RVVM2DI")
|
||||
(RVVM1DF "RVVM1DI")
|
||||
|
||||
(V1HF "V1DI") (V2HF "V2DI") (V4HF "V4DI") (V8HF "V8DI") (V16HF "V16DI")
|
||||
(V32HF "V32DI") (V64HF "V64DI") (V128HF "V128DI") (V256HF "V256DI")
|
||||
(V512HF "V512DI")
|
||||
|
||||
(V1SF "V1DI") (V2SF "V2DI") (V4SF "V4DI") (V8SF "V8DI") (V16SF "V16DI")
|
||||
(V32SF "V32DI") (V64SF "V64DI") (V128SF "V128DI") (V256SF "V256DI")
|
||||
(V512SF "V512DI")
|
||||
|
|
@ -3306,12 +3340,19 @@
|
|||
])
|
||||
|
||||
(define_mode_attr v_f2di_convert [
|
||||
(RVVM2HF "rvvm8di") (RVVM1HF "rvvm4di") (RVVMF2HF "rvvm2di")
|
||||
(RVVMF4HF "rvvm1di")
|
||||
|
||||
(RVVM4SF "rvvm8di") (RVVM2SF "rvvm4di") (RVVM1SF "rvvm2di")
|
||||
(RVVMF2SF "rvvm1di")
|
||||
|
||||
(RVVM8DF "rvvm8di") (RVVM4DF "rvvm4di") (RVVM2DF "rvvm2di")
|
||||
(RVVM1DF "rvvm1di")
|
||||
|
||||
(V1HF "v1di") (V2HF "v2di") (V4HF "v4di") (V8HF "v8di") (V16HF "v16di")
|
||||
(V32HF "v32di") (V64HF "v64di") (V128HF "v128di") (V256HF "v256di")
|
||||
(V512HF "v512di")
|
||||
|
||||
(V1SF "v1di") (V2SF "v2di") (V4SF "v4di") (V8SF "v8di") (V16SF "v16di")
|
||||
(V32SF "v32di") (V64SF "v64di") (V128SF "v128di") (V256SF "v256di")
|
||||
(V512SF "v512di")
|
||||
|
|
@ -3321,7 +3362,33 @@
|
|||
(V512DF "v512di")
|
||||
])
|
||||
|
||||
(define_mode_attr V_F2DI_CONVERT_BRIDGE [
|
||||
(RVVM2HF "RVVM4SF") (RVVM1HF "RVVM2SI") (RVVMF2HF "RVVM1SF")
|
||||
(RVVMF4HF "RVVMF2SF")
|
||||
|
||||
(RVVM4SF "VOID") (RVVM2SF "VOID") (RVVM1SF "VOID")
|
||||
(RVVMF2SF "VOID")
|
||||
|
||||
(RVVM8DF "VOID") (RVVM4DF "VOID") (RVVM2DF "VOID")
|
||||
(RVVM1DF "VOID")
|
||||
|
||||
(V1HF "V1SF") (V2HF "V2SF") (V4HF "V4SF") (V8HF "V8SF") (V16HF "V16SF")
|
||||
(V32HF "V32SF") (V64HF "V64SF") (V128HF "V128SF") (V256HF "V256SF")
|
||||
(V512HF "V512SF")
|
||||
|
||||
(V1SF "VOID") (V2SF "VOID") (V4SF "VOID") (V8SF "VOID") (V16SF "VOID")
|
||||
(V32SF "VOID") (V64SF "VOID") (V128SF "VOID") (V256SF "VOID")
|
||||
(V512SF "VOID")
|
||||
|
||||
(V1DF "VOID") (V2DF "VOID") (V4DF "VOID") (V8DF "VOID") (V16DF "VOID")
|
||||
(V32DF "VOID") (V64DF "VOID") (V128DF "VOID") (V256DF "VOID")
|
||||
(V512DF "VOID")
|
||||
])
|
||||
|
||||
(define_mode_iterator V_VLS_F_CONVERT_DI [
|
||||
(RVVM2HF "TARGET_ZVFH") (RVVM1HF "TARGET_ZVFH") (RVVMF2HF "TARGET_ZVFH")
|
||||
(RVVMF4HF "TARGET_ZVFH && TARGET_MIN_VLEN > 32")
|
||||
|
||||
(RVVM4SF "TARGET_VECTOR_ELEN_FP_32") (RVVM2SF "TARGET_VECTOR_ELEN_FP_32")
|
||||
(RVVM1SF "TARGET_VECTOR_ELEN_FP_32")
|
||||
(RVVMF2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32")
|
||||
|
|
@ -3329,6 +3396,17 @@
|
|||
(RVVM8DF "TARGET_VECTOR_ELEN_FP_64") (RVVM4DF "TARGET_VECTOR_ELEN_FP_64")
|
||||
(RVVM2DF "TARGET_VECTOR_ELEN_FP_64") (RVVM1DF "TARGET_VECTOR_ELEN_FP_64")
|
||||
|
||||
(V1HF "riscv_vector::vls_mode_valid_p (V1HFmode) && TARGET_ZVFH")
|
||||
(V2HF "riscv_vector::vls_mode_valid_p (V2HFmode) && TARGET_ZVFH")
|
||||
(V4HF "riscv_vector::vls_mode_valid_p (V4HFmode) && TARGET_ZVFH")
|
||||
(V8HF "riscv_vector::vls_mode_valid_p (V8HFmode) && TARGET_ZVFH")
|
||||
(V16HF "riscv_vector::vls_mode_valid_p (V16HFmode) && TARGET_ZVFH")
|
||||
(V32HF "riscv_vector::vls_mode_valid_p (V32HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 64")
|
||||
(V64HF "riscv_vector::vls_mode_valid_p (V64HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 128")
|
||||
(V128HF "riscv_vector::vls_mode_valid_p (V128HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 256")
|
||||
(V256HF "riscv_vector::vls_mode_valid_p (V256HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 512")
|
||||
(V512HF "riscv_vector::vls_mode_valid_p (V512HFmode) && TARGET_ZVFH && TARGET_MIN_VLEN >= 1024")
|
||||
|
||||
(V1SF "riscv_vector::vls_mode_valid_p (V1SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
(V2SF "riscv_vector::vls_mode_valid_p (V2SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
(V4SF "riscv_vector::vls_mode_valid_p (V4SFmode) && TARGET_VECTOR_ELEN_FP_32")
|
||||
|
|
|
|||
|
|
@ -0,0 +1,14 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv_zvfh_zfh -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
|
||||
/* { dg-final { check-function-bodies "**" "" } } */
|
||||
|
||||
#include <stdint-gcc.h>
|
||||
#include "test-math.h"
|
||||
|
||||
/*
|
||||
** test__Float16_int64_t___builtin_llrintf16:
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, int64_t, __builtin_llrintf16)
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv_zvfh_zfh -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
|
||||
/* { dg-final { check-function-bodies "**" "" } } */
|
||||
|
||||
#include <stdint-gcc.h>
|
||||
#include "test-math.h"
|
||||
|
||||
/*
|
||||
** test__Float16_int64_t___builtin_llroundf16:
|
||||
** frrm\s+[atx][0-9]+
|
||||
** ...
|
||||
** fsrmi\s+4
|
||||
** ...
|
||||
** vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** fsrm\s+[atx][0-9]+
|
||||
** ret
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, int64_t, __builtin_llroundf16)
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv_zvfh_zfh -mabi=ilp32d -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__Float16_long___builtin_lrintf16:
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, long, __builtin_lrintf16)
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv_zvfh_zfh -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__Float16_long___builtin_lrintf16:
|
||||
** ...
|
||||
** vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, long, __builtin_lrintf16)
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv_zvfh_zfh -mabi=ilp32d -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__Float16_long___builtin_lroundf16:
|
||||
** frrm\s+[atx][0-9]+
|
||||
** ...
|
||||
** fsrmi\s+4
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** fsrm\s+[atx][0-9]+
|
||||
** ret
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, long, __builtin_lroundf16)
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv64gcv_zvfh_zfh -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__Float16_long___builtin_lroundf16:
|
||||
** frrm\s+[atx][0-9]+
|
||||
** ...
|
||||
** fsrmi\s+4
|
||||
** ...
|
||||
** vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
|
||||
** ...
|
||||
** fsrm\s+[atx][0-9]+
|
||||
** ret
|
||||
*/
|
||||
TEST_UNARY_CALL_CVT (_Float16, long, __builtin_lroundf16)
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
/* { 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 (llrintf16, 1, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 2, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 4, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 8, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 16, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 32, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 64, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 128, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 256, _Float16, int64_t, __builtin_llrintf16)
|
||||
DEF_OP_V_CVT (llrintf16, 512, _Float16, int64_t, __builtin_llrintf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
/* { 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 (llroundf16, 1, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 2, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 4, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 8, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 16, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 32, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 64, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 128, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 256, _Float16, int64_t, __builtin_llroundf16)
|
||||
DEF_OP_V_CVT (llroundf16, 512, _Float16, int64_t, __builtin_llroundf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv_zvfh_zvl4096b -mabi=ilp32d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
|
||||
|
||||
#include "def.h"
|
||||
|
||||
DEF_OP_V_CVT (lrintf16, 1, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 2, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 4, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 8, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 16, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 32, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 64, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 128, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 256, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 512, _Float16, long, __builtin_lrintf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
/* { 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 (lrintf16, 1, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 2, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 4, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 8, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 16, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 32, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 64, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 128, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 256, _Float16, long, __builtin_lrintf16)
|
||||
DEF_OP_V_CVT (lrintf16, 512, _Float16, long, __builtin_lrintf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-march=rv32gcv_zvfh_zvl4096b -mabi=ilp32d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
|
||||
|
||||
#include "def.h"
|
||||
|
||||
DEF_OP_V_CVT (lroundf16, 1, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 2, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 4, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 8, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 16, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 32, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 64, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 128, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 256, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 512, _Float16, long, __builtin_lroundf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
/* { 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 (lroundf16, 1, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 2, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 4, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 8, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 16, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 32, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 64, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 128, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 256, _Float16, long, __builtin_lroundf16)
|
||||
DEF_OP_V_CVT (lroundf16, 512, _Float16, long, __builtin_lroundf16)
|
||||
|
||||
/* { 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-assembler-times {vfwcvt\.f\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */
|
||||
Loading…
Add table
Reference in a new issue