def generate_scheme(self):
# declaring target and instantiating optimization engine
vx = self.implementation.add_input_variable("x", self.precision)
Log.set_dump_stdout(True)
Log.report(Log.Info,
"\033[33;1m generating implementation scheme \033[0m")
if self.debug_flag:
Log.report(Log.Info, "\033[31;1m debug has been enabled \033[0;m")
# local overloading of RaiseReturn operation
def ExpRaiseReturn(*args, **kwords):
kwords["arg_value"] = vx
kwords["function_name"] = self.function_name
if self.libm_compliant:
return RaiseReturn(*args, precision=self.precision, **kwords)
else:
return Return(kwords["return_value"], precision=self.precision)
test_nan_or_inf = Test(vx,
specifier=Test.IsInfOrNaN,
likely=False,
debug=debug_multi,
tag="nan_or_inf")
test_nan = Test(vx,
specifier=Test.IsNaN,
debug=debug_multi,
tag="is_nan_test")
test_positive = Comparison(vx,
0,
specifier=Comparison.GreaterOrEqual,
debug=debug_multi,
tag="inf_sign")
test_signaling_nan = Test(vx,
specifier=Test.IsSignalingNaN,
debug=debug_multi,
tag="is_signaling_nan")
return_snan = Statement(
ExpRaiseReturn(ML_FPE_Invalid,
return_value=FP_QNaN(self.precision)))
# return in case of infinity input
infty_return = Statement(
ConditionBlock(
test_positive,
Return(FP_PlusInfty(self.precision), precision=self.precision),
Return(FP_PlusZero(self.precision), precision=self.precision)))
# return in case of specific value input (NaN or inf)
specific_return = ConditionBlock(
test_nan,
ConditionBlock(
test_signaling_nan, return_snan,
Return(FP_QNaN(self.precision), precision=self.precision)),
infty_return)
# return in case of standard (non-special) input
# exclusion of early overflow and underflow cases
precision_emax = self.precision.get_emax()
precision_max_value = S2 * S2**precision_emax
exp_overflow_bound = sollya.ceil(log(precision_max_value))
early_overflow_test = Comparison(vx,
exp_overflow_bound,
likely=False,
specifier=Comparison.Greater)
early_overflow_return = Statement(
ClearException() if self.libm_compliant else Statement(),
ExpRaiseReturn(ML_FPE_Inexact,
ML_FPE_Overflow,
return_value=FP_PlusInfty(self.precision)))
precision_emin = self.precision.get_emin_subnormal()
precision_min_value = S2**precision_emin
exp_underflow_bound = floor(log(precision_min_value))
early_underflow_test = Comparison(vx,
exp_underflow_bound,
likely=False,
specifier=Comparison.Less)
early_underflow_return = Statement(
ClearException() if self.libm_compliant else Statement(),
ExpRaiseReturn(ML_FPE_Inexact,
ML_FPE_Underflow,
return_value=FP_PlusZero(self.precision)))
# constant computation
invlog2 = self.precision.round_sollya_object(1 / log(2), sollya.RN)
interval_vx = Interval(exp_underflow_bound, exp_overflow_bound)
interval_fk = interval_vx * invlog2
interval_k = Interval(floor(inf(interval_fk)),
sollya.ceil(sup(interval_fk)))
log2_hi_precision = self.precision.get_field_size() - (
sollya.ceil(log2(sup(abs(interval_k)))) + 2)
Log.report(Log.Info, "log2_hi_precision: %d" % log2_hi_precision)
invlog2_cst = Constant(invlog2, precision=self.precision)
log2_hi = round(log(2), log2_hi_precision, sollya.RN)
log2_lo = self.precision.round_sollya_object(
log(2) - log2_hi, sollya.RN)
# argument reduction
unround_k = vx * invlog2
unround_k.set_attributes(tag="unround_k", debug=debug_multi)
k = NearestInteger(unround_k,
precision=self.precision,
debug=debug_multi)
ik = NearestInteger(unround_k,
precision=self.precision.get_integer_format(),
debug=debug_multi,
tag="ik")
ik.set_tag("ik")
k.set_tag("k")
exact_pre_mul = (k * log2_hi)
exact_pre_mul.set_attributes(exact=True)
exact_hi_part = vx - exact_pre_mul
exact_hi_part.set_attributes(exact=True,
tag="exact_hi",
debug=debug_multi,
prevent_optimization=True)
exact_lo_part = -k * log2_lo
exact_lo_part.set_attributes(tag="exact_lo",
debug=debug_multi,
prevent_optimization=True)
r = exact_hi_part + exact_lo_part
r.set_tag("r")
r.set_attributes(debug=debug_multi)
approx_interval = Interval(-log(2) / 2, log(2) / 2)
approx_interval_half = approx_interval / 2
approx_interval_split = [
Interval(-log(2) / 2, inf(approx_interval_half)),
approx_interval_half,
Interval(sup(approx_interval_half),
log(2) / 2)
]
# TODO: should be computed automatically
exact_hi_interval = approx_interval
exact_lo_interval = -interval_k * log2_lo
opt_r = self.optimise_scheme(r, copy={})
tag_map = {}
self.opt_engine.register_nodes_by_tag(opt_r, tag_map)
cg_eval_error_copy_map = {
vx:
Variable("x", precision=self.precision, interval=interval_vx),
tag_map["k"]:
Variable("k", interval=interval_k, precision=self.precision)
}
#try:
if is_gappa_installed():
eval_error = self.gappa_engine.get_eval_error_v2(
self.opt_engine,
opt_r,
cg_eval_error_copy_map,
gappa_filename="red_arg.g")
else:
eval_error = 0.0
Log.report(Log.Warning,
"gappa is not installed in this environnement")
Log.report(Log.Info, "eval error: %s" % eval_error)
local_ulp = sup(ulp(sollya.exp(approx_interval), self.precision))
# FIXME refactor error_goal from accuracy
Log.report(Log.Info, "accuracy: %s" % self.accuracy)
if isinstance(self.accuracy, ML_Faithful):
error_goal = local_ulp
elif isinstance(self.accuracy, ML_CorrectlyRounded):
error_goal = S2**-1 * local_ulp
elif isinstance(self.accuracy, ML_DegradedAccuracyAbsolute):
error_goal = self.accuracy.goal
elif isinstance(self.accuracy, ML_DegradedAccuracyRelative):
error_goal = self.accuracy.goal
else:
Log.report(Log.Error, "unknown accuracy: %s" % self.accuracy)
# error_goal = local_ulp #S2**-(self.precision.get_field_size()+1)
error_goal_approx = S2**-1 * error_goal
Log.report(Log.Info,
"\033[33;1m building mathematical polynomial \033[0m\n")
poly_degree = max(
sup(
guessdegree(
expm1(sollya.x) / sollya.x, approx_interval,
error_goal_approx)) - 1, 2)
init_poly_degree = poly_degree
error_function = lambda p, f, ai, mod, t: dirtyinfnorm(f - p, ai)
polynomial_scheme_builder = PolynomialSchemeEvaluator.generate_estrin_scheme
#polynomial_scheme_builder = PolynomialSchemeEvaluator.generate_horner_scheme
while 1:
Log.report(Log.Info, "attempting poly degree: %d" % poly_degree)
precision_list = [1] + [self.precision] * (poly_degree)
poly_object, poly_approx_error = Polynomial.build_from_approximation_with_error(
expm1(sollya.x),
poly_degree,
precision_list,
approx_interval,
sollya.absolute,
error_function=error_function)
Log.report(Log.Info, "polynomial: %s " % poly_object)
sub_poly = poly_object.sub_poly(start_index=2)
Log.report(Log.Info, "polynomial: %s " % sub_poly)
Log.report(Log.Info, "poly approx error: %s" % poly_approx_error)
Log.report(
Log.Info,
"\033[33;1m generating polynomial evaluation scheme \033[0m")
pre_poly = polynomial_scheme_builder(
poly_object, r, unified_precision=self.precision)
pre_poly.set_attributes(tag="pre_poly", debug=debug_multi)
pre_sub_poly = polynomial_scheme_builder(
sub_poly, r, unified_precision=self.precision)
pre_sub_poly.set_attributes(tag="pre_sub_poly", debug=debug_multi)
poly = 1 + (exact_hi_part + (exact_lo_part + pre_sub_poly))
poly.set_tag("poly")
# optimizing poly before evaluation error computation
#opt_poly = self.opt_engine.optimization_process(poly, self.precision, fuse_fma = fuse_fma)
#opt_sub_poly = self.opt_engine.optimization_process(pre_sub_poly, self.precision, fuse_fma = fuse_fma)
opt_poly = self.optimise_scheme(poly)
opt_sub_poly = self.optimise_scheme(pre_sub_poly)
# evaluating error of the polynomial approximation
r_gappa_var = Variable("r",
precision=self.precision,
interval=approx_interval)
exact_hi_gappa_var = Variable("exact_hi",
precision=self.precision,
interval=exact_hi_interval)
exact_lo_gappa_var = Variable("exact_lo",
precision=self.precision,
interval=exact_lo_interval)
vx_gappa_var = Variable("x",
precision=self.precision,
interval=interval_vx)
k_gappa_var = Variable("k",
interval=interval_k,
precision=self.precision)
#print "exact_hi interval: ", exact_hi_interval
sub_poly_error_copy_map = {
#r.get_handle().get_node(): r_gappa_var,
#vx.get_handle().get_node(): vx_gappa_var,
exact_hi_part.get_handle().get_node():
exact_hi_gappa_var,
exact_lo_part.get_handle().get_node():
exact_lo_gappa_var,
#k.get_handle().get_node(): k_gappa_var,
}
poly_error_copy_map = {
exact_hi_part.get_handle().get_node(): exact_hi_gappa_var,
exact_lo_part.get_handle().get_node(): exact_lo_gappa_var,
}
if is_gappa_installed():
sub_poly_eval_error = -1.0
sub_poly_eval_error = self.gappa_engine.get_eval_error_v2(
self.opt_engine,
opt_sub_poly,
sub_poly_error_copy_map,
gappa_filename="%s_gappa_sub_poly.g" % self.function_name)
dichotomy_map = [
{
exact_hi_part.get_handle().get_node():
approx_interval_split[0],
},
{
exact_hi_part.get_handle().get_node():
approx_interval_split[1],
},
{
exact_hi_part.get_handle().get_node():
approx_interval_split[2],
},
]
poly_eval_error_dico = self.gappa_engine.get_eval_error_v3(
self.opt_engine,
opt_poly,
poly_error_copy_map,
gappa_filename="gappa_poly.g",
dichotomy=dichotomy_map)
poly_eval_error = max(
[sup(abs(err)) for err in poly_eval_error_dico])
else:
poly_eval_error = 0.0
sub_poly_eval_error = 0.0
Log.report(Log.Warning,
"gappa is not installed in this environnement")
Log.report(Log.Info, "stopping autonomous degree research")
# incrementing polynomial degree to counteract initial decrementation effect
poly_degree += 1
break
Log.report(Log.Info, "poly evaluation error: %s" % poly_eval_error)
Log.report(Log.Info,
"sub poly evaluation error: %s" % sub_poly_eval_error)
global_poly_error = None
global_rel_poly_error = None
for case_index in range(3):
poly_error = poly_approx_error + poly_eval_error_dico[
case_index]
rel_poly_error = sup(
abs(poly_error /
sollya.exp(approx_interval_split[case_index])))
if global_rel_poly_error == None or rel_poly_error > global_rel_poly_error:
global_rel_poly_error = rel_poly_error
global_poly_error = poly_error
flag = error_goal > global_rel_poly_error
if flag:
break
else:
poly_degree += 1
late_overflow_test = Comparison(ik,
self.precision.get_emax(),
specifier=Comparison.Greater,
likely=False,
debug=debug_multi,
tag="late_overflow_test")
overflow_exp_offset = (self.precision.get_emax() -
self.precision.get_field_size() / 2)
diff_k = Subtraction(
ik,
Constant(overflow_exp_offset,
precision=self.precision.get_integer_format()),
precision=self.precision.get_integer_format(),
debug=debug_multi,
tag="diff_k",
)
late_overflow_result = (ExponentInsertion(
diff_k, precision=self.precision) * poly) * ExponentInsertion(
overflow_exp_offset, precision=self.precision)
late_overflow_result.set_attributes(silent=False,
tag="late_overflow_result",
debug=debug_multi,
precision=self.precision)
late_overflow_return = ConditionBlock(
Test(late_overflow_result, specifier=Test.IsInfty, likely=False),
ExpRaiseReturn(ML_FPE_Overflow,
return_value=FP_PlusInfty(self.precision)),
Return(late_overflow_result, precision=self.precision))
late_underflow_test = Comparison(k,
self.precision.get_emin_normal(),
specifier=Comparison.LessOrEqual,
likely=False)
underflow_exp_offset = 2 * self.precision.get_field_size()
corrected_exp = Addition(
ik,
Constant(underflow_exp_offset,
precision=self.precision.get_integer_format()),
precision=self.precision.get_integer_format(),
tag="corrected_exp")
late_underflow_result = (
ExponentInsertion(corrected_exp, precision=self.precision) *
poly) * ExponentInsertion(-underflow_exp_offset,
precision=self.precision)
late_underflow_result.set_attributes(debug=debug_multi,
tag="late_underflow_result",
silent=False)
test_subnormal = Test(late_underflow_result,
specifier=Test.IsSubnormal)
late_underflow_return = Statement(
ConditionBlock(
test_subnormal,
ExpRaiseReturn(ML_FPE_Underflow,
return_value=late_underflow_result)),
Return(late_underflow_result, precision=self.precision))
twok = ExponentInsertion(ik,
tag="exp_ik",
debug=debug_multi,
precision=self.precision)
#std_result = twok * ((1 + exact_hi_part * pre_poly) + exact_lo_part * pre_poly)
std_result = twok * poly
std_result.set_attributes(tag="std_result", debug=debug_multi)
result_scheme = ConditionBlock(
late_overflow_test, late_overflow_return,
ConditionBlock(late_underflow_test, late_underflow_return,
Return(std_result, precision=self.precision)))
std_return = ConditionBlock(
early_overflow_test, early_overflow_return,
ConditionBlock(early_underflow_test, early_underflow_return,
result_scheme))
# main scheme
Log.report(Log.Info, "\033[33;1m MDL scheme \033[0m")
scheme = ConditionBlock(
test_nan_or_inf,
Statement(ClearException() if self.libm_compliant else Statement(),
specific_return), std_return)
return scheme
def generate_scheme(self):
# declaring target and instantiating optimization engine
vx = self.implementation.add_input_variable("x", self.precision)
Log.set_dump_stdout(True)
Log.report(Log.Info, "\033[33;1m generating implementation scheme \033[0m")
if self.debug_flag:
Log.report(Log.Info, "\033[31;1m debug has been enabled \033[0;m")
# local overloading of RaiseReturn operation
def ExpRaiseReturn(*args, **kwords):
kwords["arg_value"] = vx
kwords["function_name"] = self.function_name
return RaiseReturn(*args, **kwords)
C_m1 = Constant(-1, precision = self.precision)
test_NaN_or_inf = Test(vx, specifier = Test.IsInfOrNaN, likely = False, debug = debug_multi, tag = "NaN_or_inf", precision = ML_Bool)
test_NaN = Test(vx, specifier = Test.IsNaN, likely = False, debug = debug_multi, tag = "is_NaN", precision = ML_Bool)
test_inf = Comparison(vx, 0, specifier = Comparison.Greater, debug = debug_multi, tag = "sign", precision = ML_Bool, likely = False);
# Infnty input
infty_return = Statement(ConditionBlock(test_inf, Return(FP_PlusInfty(self.precision)), Return(C_m1)))
# non-std input (inf/nan)
specific_return = ConditionBlock(test_NaN, Return(FP_QNaN(self.precision)), infty_return)
# Over/Underflow Tests
precision_emax = self.precision.get_emax()
precision_max_value = S2**(precision_emax + 1)
expm1_overflow_bound = ceil(log(precision_max_value + 1))
overflow_test = Comparison(vx, expm1_overflow_bound, likely = False, specifier = Comparison.Greater, precision = ML_Bool)
overflow_return = Statement(Return(FP_PlusInfty(self.precision)))
precision_emin = self.precision.get_emin_subnormal()
precision_min_value = S2** precision_emin
expm1_underflow_bound = floor(log(precision_min_value) + 1)
underflow_test = Comparison(vx, expm1_underflow_bound, likely = False, specifier = Comparison.Less, precision = ML_Bool)
underflow_return = Statement(Return(C_m1))
sollya_precision = {ML_Binary32: sollya.binary32, ML_Binary64: sollya.binary64}[self.precision]
int_precision = {ML_Binary32: ML_Int32, ML_Binary64: ML_Int64}[self.precision]
# Constants
log_2 = round(log(2), sollya_precision, sollya.RN)
invlog2 = round(1/log(2), sollya_precision, sollya.RN)
log_2_cst = Constant(log_2, precision = self.precision)
interval_vx = Interval(expm1_underflow_bound, expm1_overflow_bound)
interval_fk = interval_vx * invlog2
interval_k = Interval(floor(inf(interval_fk)), ceil(sup(interval_fk)))
log2_hi_precision = self.precision.get_field_size() - 6
log2_hi = round(log(2), log2_hi_precision, sollya.RN)
log2_lo = round(log(2) - log2_hi, sollya_precision, sollya.RN)
# Reduction
unround_k = vx * invlog2
ik = NearestInteger(unround_k, precision = int_precision, debug = debug_multi, tag = "ik")
k = Conversion(ik, precision = self.precision, tag = "k")
red_coeff1 = Multiplication(k, log2_hi, precision = self.precision)
red_coeff2 = Multiplication(Negation(k, precision = self.precision), log2_lo, precision = self.precision)
pre_sub_mul = Subtraction(vx, red_coeff1, precision = self.precision)
s = Addition(pre_sub_mul, red_coeff2, precision = self.precision)
z = Subtraction(s, pre_sub_mul, precision = self.precision)
t = Subtraction(red_coeff2, z, precision = self.precision)
r = Addition(s, t, precision = self.precision)
r.set_attributes(tag = "r", debug = debug_multi)
r_interval = Interval(-log_2/S2, log_2/S2)
local_ulp = sup(ulp(exp(r_interval), self.precision))
print("ulp: ", local_ulp)
error_goal = S2**-1*local_ulp
print("error goal: ", error_goal)
# Polynomial Approx
error_function = lambda p, f, ai, mod, t: dirtyinfnorm(f - p, ai)
Log.report(Log.Info, "\033[33;1m Building polynomial \033[0m\n")
poly_degree = sup(guessdegree(expm1(sollya.x), r_interval, error_goal) + 1)
polynomial_scheme_builder = PolynomialSchemeEvaluator.generate_horner_scheme
poly_degree_list = range(0, poly_degree)
precision_list = [self.precision] *(len(poly_degree_list) + 1)
poly_object, poly_error = Polynomial.build_from_approximation_with_error(expm1(sollya.x), poly_degree, precision_list, r_interval, sollya.absolute, error_function = error_function)
sub_poly = poly_object.sub_poly(start_index = 2)
Log.report(Log.Info, "Poly : %s" % sub_poly)
Log.report(Log.Info, "poly error : {} / {:d}".format(poly_error, int(sollya.log2(poly_error))))
pre_sub_poly = polynomial_scheme_builder(sub_poly, r, unified_precision = self.precision)
poly = r + pre_sub_poly
poly.set_attributes(tag = "poly", debug = debug_multi)
exp_k = ExponentInsertion(ik, tag = "exp_k", debug = debug_multi, precision = self.precision)
exp_mk = ExponentInsertion(-ik, tag = "exp_mk", debug = debug_multi, precision = self.precision)
diff = 1 - exp_mk
diff.set_attributes(tag = "diff", debug = debug_multi)
# Late Tests
late_overflow_test = Comparison(ik, self.precision.get_emax(), specifier = Comparison.Greater, likely = False, debug = debug_multi, tag = "late_overflow_test")
overflow_exp_offset = (self.precision.get_emax() - self.precision.get_field_size() / 2)
diff_k = ik - overflow_exp_offset
exp_diff_k = ExponentInsertion(diff_k, precision = self.precision, tag = "exp_diff_k", debug = debug_multi)
exp_oflow_offset = ExponentInsertion(overflow_exp_offset, precision = self.precision, tag = "exp_offset", debug = debug_multi)
late_overflow_result = (exp_diff_k * (1 + poly)) * exp_oflow_offset - 1.0
late_overflow_return = ConditionBlock(
Test(late_overflow_result, specifier = Test.IsInfty, likely = False),
ExpRaiseReturn(ML_FPE_Overflow, return_value = FP_PlusInfty(self.precision)),
Return(late_overflow_result)
)
late_underflow_test = Comparison(k, self.precision.get_emin_normal(), specifier = Comparison.LessOrEqual, likely = False)
underflow_exp_offset = 2 * self.precision.get_field_size()
corrected_coeff = ik + underflow_exp_offset
exp_corrected = ExponentInsertion(corrected_coeff, precision = self.precision)
exp_uflow_offset = ExponentInsertion(-underflow_exp_offset, precision = self.precision)
late_underflow_result = ( exp_corrected * (1 + poly)) * exp_uflow_offset - 1.0
test_subnormal = Test(late_underflow_result, specifier = Test.IsSubnormal, likely = False)
late_underflow_return = Statement(
ConditionBlock(
test_subnormal,
ExpRaiseReturn(ML_FPE_Underflow, return_value = late_underflow_result)),
Return(late_underflow_result)
)
# Reconstruction
std_result = exp_k * ( poly + diff )
std_result.set_attributes(tag = "result", debug = debug_multi)
result_scheme = ConditionBlock(
late_overflow_test,
late_overflow_return,
ConditionBlock(
late_underflow_test,
late_underflow_return,
Return(std_result)
)
)
std_return = ConditionBlock(
overflow_test,
overflow_return,
ConditionBlock(
underflow_test,
underflow_return,
result_scheme)
)
scheme = ConditionBlock(
test_NaN_or_inf,
Statement(specific_return),
std_return
)
return scheme
def generate_scheme(self):
# declaring target and instantiating optimization engine
vx = self.implementation.add_input_variable("x", self.precision)
Log.set_dump_stdout(True)
Log.report(Log.Info,
"\033[33;1m generating implementation scheme \033[0m")
if self.debug_flag:
Log.report(Log.Info, "\033[31;1m debug has been enabled \033[0;m")
# local overloading of RaiseReturn operation
def ExpRaiseReturn(*args, **kwords):
kwords["arg_value"] = vx
kwords["function_name"] = self.function_name
return RaiseReturn(*args, **kwords)
r_interval = Interval(-0.5, 0.5)
local_ulp = sup(ulp(2**r_interval, self.precision))
Log.report(Log.Info, "ulp: ", local_ulp)
error_goal = S2**-1 * local_ulp
Log.report(Log.Info, "error goal: ", error_goal)
sollya_precision = {
ML_Binary32: sollya.binary32,
ML_Binary64: sollya.binary64
}[self.precision]
int_precision = {
ML_Binary32: ML_Int32,
ML_Binary64: ML_Int64
}[self.precision]
#Argument Reduction
vx_int = NearestInteger(vx,
precision=int_precision,
tag='vx_int',
debug=debug_multi)
vx_intf = Conversion(vx_int, precision=self.precision)
vx_r = vx - vx_intf
vx_r.set_attributes(tag="vx_r", debug=debug_multi)
degree = sup(guessdegree(2**(sollya.x), r_interval, error_goal)) + 2
precision_list = [1] + [self.precision] * degree
exp_X = ExponentInsertion(vx_int,
tag="exp_X",
debug=debug_multi,
precision=self.precision)
#Polynomial Approx
polynomial_scheme_builder = PolynomialSchemeEvaluator.generate_horner_scheme
poly_object, poly_error = Polynomial.build_from_approximation_with_error(
2**(sollya.x) - 1, degree, precision_list, r_interval,
sollya.absolute)
Log.report(Log.Info, "Poly : %s" % poly_object)
Log.report(Log.Info, "poly_error : ", poly_error)
poly = polynomial_scheme_builder(poly_object.sub_poly(start_index=1),
vx_r,
unified_precision=self.precision)
poly.set_attributes(tag="poly", debug=debug_multi)
#Handling special cases
oflow_bound = Constant(self.precision.get_emax() + 1,
precision=self.precision)
subnormal_bound = self.precision.get_emin_subnormal()
uflow_bound = self.precision.get_emin_normal()
Log.report(Log.Info, "oflow : ", oflow_bound)
#print "uflow : ", uflow_bound
#print "sub : ", subnormal_bound
test_overflow = Comparison(vx,
oflow_bound,
specifier=Comparison.GreaterOrEqual)
test_overflow.set_attributes(tag="oflow_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
test_underflow = Comparison(vx, uflow_bound, specifier=Comparison.Less)
test_underflow.set_attributes(tag="uflow_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
test_subnormal = Comparison(vx,
subnormal_bound,
specifier=Comparison.Greater)
test_subnormal.set_attributes(tag="sub_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
subnormal_offset = -(uflow_bound - vx_int)
subnormal_offset.set_attributes(tag="offset", debug=debug_multi)
exp_offset = ExponentInsertion(subnormal_offset,
precision=self.precision,
debug=debug_multi,
tag="exp_offset")
exp_min = ExponentInsertion(uflow_bound,
precision=self.precision,
debug=debug_multi,
tag="exp_min")
subnormal_result = exp_offset * exp_min * poly + exp_offset * exp_min
test_std = LogicalOr(test_overflow,
test_underflow,
precision=ML_Bool,
tag="std_test",
likely=False)
#Reconstruction
result = exp_X * poly + exp_X
result.set_attributes(tag="result", debug=debug_multi)
C0 = Constant(0, precision=self.precision)
return_inf = Return(FP_PlusInfty(self.precision))
return_C0 = Return(C0)
return_sub = Return(subnormal_result)
return_std = Return(result)
non_std_statement = Statement(
ConditionBlock(
test_overflow, return_inf,
ConditionBlock(test_subnormal, return_sub, return_C0)))
scheme = Statement(
ConditionBlock(test_std, non_std_statement, return_std))
return scheme
def generate_scalar_scheme(self, vx, inline_select=False):
Log.set_dump_stdout(True)
Log.report(Log.Info,
"\033[33;1m generating implementation scheme \033[0m")
if self.debug_flag:
Log.report(Log.Info, "\033[31;1m debug has been enabled \033[0;m")
# local overloading of RaiseReturn operation
def ExpRaiseReturn(*args, **kwords):
kwords["arg_value"] = vx
kwords["function_name"] = self.function_name
return RaiseReturn(*args, **kwords)
# r_interval = Interval(0, 1.0)
index_size = 3
r_interval = Interval(-2**(-index_size), 2**-index_size)
local_ulp = sup(ulp(2**r_interval, self.precision))
Log.report(Log.Info, "ulp: ", local_ulp)
error_goal = S2**-1 * local_ulp
Log.report(Log.Info, "error goal: ", error_goal)
sollya_precision = {
ML_Binary32: sollya.binary32,
ML_Binary64: sollya.binary64
}[self.precision]
int_precision = {
ML_Binary32: ML_Int32,
ML_Binary64: ML_Int64
}[self.precision]
# Argument Reduction
# r = x - floor(x), r >= 0
vx_floor = Floor(vx,
precision=self.precision,
tag='vx_floor',
debug=debug_multi)
vx_int = Conversion(vx_floor,
precision=int_precision,
tag="vx_int",
debug=debug_multi)
vx_intf = vx_floor # Conversion(vx_int, precision = self.precision)
vx_r = vx - vx_intf
r_hi = NearestInteger(vx_r * 2**index_size,
precision=self.precision,
tag="r_hi",
debug=debug_multi)
# clamping r_hi_int within table-size to make sure
# it does not exceeds hi_part_table when used to index it
r_hi_int = Max(
Min(
Conversion(r_hi,
precision=int_precision,
tag="r_hi_int",
debug=debug_multi), 2**index_size + 1), 0)
r_lo = vx_r - r_hi * 2**-index_size
r_lo.set_attributes(tag="r_lo", debug=debug_multi)
vx_r.set_attributes(tag="vx_r", debug=debug_multi)
degree = sup(guessdegree(2**(sollya.x), r_interval, error_goal)) + 2
precision_list = [1] + [self.precision] * degree
exp_X = ExponentInsertion(vx_int,
tag="exp_X",
debug=debug_multi,
precision=self.precision)
#Polynomial Approx
polynomial_scheme_builder = PolynomialSchemeEvaluator.generate_horner_scheme
poly_object, poly_error = Polynomial.build_from_approximation_with_error(
2**(sollya.x) - 1, degree, precision_list, r_interval,
sollya.absolute)
Log.report(Log.Info, "Poly : %s" % poly_object)
Log.report(Log.Info, "poly_error : ", poly_error)
poly = polynomial_scheme_builder(poly_object.sub_poly(start_index=1),
r_lo,
unified_precision=self.precision)
poly.set_attributes(tag="poly", debug=debug_multi)
hi_part_table = ML_NewTable(dimensions=[2**index_size + 1],
storage_precision=self.precision,
tag=self.uniquify_name("exp2_table"),
const=True)
for i in range(2**index_size + 1):
input_value = i * 2**-index_size
tab_value = self.precision.round_sollya_object(
sollya.SollyaObject(2)**(input_value))
hi_part_table[i] = tab_value
hi_part_value = TableLoad(hi_part_table,
r_hi_int,
precision=self.precision,
tag="hi_part_value",
debug=debug_multi)
#Handling special cases
oflow_bound = Constant(self.precision.get_emax() + 1,
precision=self.precision)
subnormal_bound = self.precision.get_emin_subnormal()
uflow_bound = self.precision.get_emin_normal()
Log.report(Log.Info, "oflow : ", oflow_bound)
#print "uflow : ", uflow_bound
#print "sub : ", subnormal_bound
test_overflow = Comparison(vx,
oflow_bound,
specifier=Comparison.GreaterOrEqual)
test_overflow.set_attributes(tag="oflow_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
test_underflow = Comparison(vx, uflow_bound, specifier=Comparison.Less)
test_underflow.set_attributes(tag="uflow_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
test_subnormal = Comparison(vx,
subnormal_bound,
specifier=Comparison.Greater)
test_subnormal.set_attributes(tag="sub_test",
debug=debug_multi,
likely=False,
precision=ML_Bool)
subnormal_offset = -(uflow_bound - vx_int)
subnormal_offset.set_attributes(tag="offset", debug=debug_multi)
exp_offset = ExponentInsertion(subnormal_offset,
precision=self.precision,
debug=debug_multi,
tag="exp_offset")
exp_min = ExponentInsertion(uflow_bound,
precision=self.precision,
debug=debug_multi,
tag="exp_min")
subnormal_result = hi_part_value * exp_offset * exp_min * poly + hi_part_value * exp_offset * exp_min
test_std = LogicalOr(test_overflow,
test_underflow,
precision=ML_Bool,
tag="std_test",
likely=False,
debug=debug_multi)
#Reconstruction
result = hi_part_value * exp_X * poly + hi_part_value * exp_X
result.set_attributes(tag="result", debug=debug_multi)
C0 = Constant(0, precision=self.precision)
if inline_select:
scheme = Select(
test_std,
Select(test_overflow, FP_PlusInfty(self.precision),
Select(
test_subnormal,
subnormal_result,
C0,
)),
result,
)
return scheme
else:
return_inf = Return(FP_PlusInfty(self.precision))
return_C0 = Return(C0)
return_sub = Return(subnormal_result)
return_std = Return(result)
non_std_statement = Statement(
ConditionBlock(
test_overflow, return_inf,
ConditionBlock(test_subnormal, return_sub, return_C0)))
scheme = Statement(
ConditionBlock(test_std, non_std_statement, return_std))
return scheme
def __init__(self,
precision = ML_Binary32,
abs_accuracy = S2**-24,
libm_compliant = True,
debug_flag = False,
fuse_fma = True,
fast_path_extract = True,
target = GenericProcessor(),
output_file = "expf.c",
function_name = "expf"):
# declaring target and instantiating optimization engine
processor = target
self.precision = precision
opt_eng = OptimizationEngine(processor)
gappacg = GappaCodeGenerator(processor, declare_cst = True, disable_debug = True)
# declaring CodeFunction and retrieving input variable
self.function_name = function_name
exp_implementation = CodeFunction(self.function_name, output_format = self.precision)
vx = exp_implementation.add_input_variable("x", self.precision)
Log.report(Log.Info, "\033[33;1m generating implementation scheme \033[0m")
# local overloading of RaiseReturn operation
def ExpRaiseReturn(*args, **kwords):
kwords["arg_value"] = vx
kwords["function_name"] = self.function_name
return RaiseReturn(*args, **kwords)
test_nan_or_inf = Test(vx, specifier = Test.IsInfOrNaN, likely = False, debug = True, tag = "nan_or_inf")
test_nan = Test(vx, specifier = Test.IsNaN, debug = True, tag = "is_nan_test")
test_positive = Comparison(vx, 0, specifier = Comparison.GreaterOrEqual, debug = True, tag = "inf_sign")
test_signaling_nan = Test(vx, specifier = Test.IsSignalingNaN, debug = True, tag = "is_signaling_nan")
return_snan = Statement(ExpRaiseReturn(ML_FPE_Invalid, return_value = FP_QNaN(self.precision)))
# return in case of infinity input
infty_return = Statement(ConditionBlock(test_positive, Return(FP_PlusInfty(self.precision)), Return(FP_PlusZero(self.precision))))
# return in case of specific value input (NaN or inf)
specific_return = ConditionBlock(test_nan, ConditionBlock(test_signaling_nan, return_snan, Return(FP_QNaN(self.precision))), infty_return)
# return in case of standard (non-special) input
# exclusion of early overflow and underflow cases
precision_emax = self.precision.get_emax()
precision_max_value = S2 * S2**precision_emax
exp_overflow_bound = ceil(log(precision_max_value))
early_overflow_test = Comparison(vx, exp_overflow_bound, likely = False, specifier = Comparison.Greater)
early_overflow_return = Statement(ClearException(), ExpRaiseReturn(ML_FPE_Inexact, ML_FPE_Overflow, return_value = FP_PlusInfty(self.precision)))
precision_emin = self.precision.get_emin_subnormal()
precision_min_value = S2 ** precision_emin
exp_underflow_bound = floor(log(precision_min_value))
early_underflow_test = Comparison(vx, exp_underflow_bound, likely = False, specifier = Comparison.Less)
early_underflow_return = Statement(ClearException(), ExpRaiseReturn(ML_FPE_Inexact, ML_FPE_Underflow, return_value = FP_PlusZero(self.precision)))
sollya_prec_map = {ML_Binary32: sollya.binary32, ML_Binary64: sollya.binary64}
# constant computation
invlog2 = round(1/log(2), sollya_prec_map[self.precision], RN)
interval_vx = Interval(exp_underflow_bound, exp_overflow_bound)
interval_fk = interval_vx * invlog2
interval_k = Interval(floor(inf(interval_fk)), ceil(sup(interval_fk)))
log2_hi_precision = self.precision.get_field_size() - (ceil(log2(sup(abs(interval_k)))) + 2)
Log.report(Log.Info, "log2_hi_precision: "), log2_hi_precision
invlog2_cst = Constant(invlog2, precision = self.precision)
log2_hi = round(log(2), log2_hi_precision, sollya.RN)
log2_lo = round(log(2) - log2_hi, sollya_prec_map[self.precision], sollya.RN)
# argument reduction
unround_k = vx * invlog2
unround_k.set_attributes(tag = "unround_k", debug = ML_Debug(display_format = "%f"))
k = NearestInteger(unround_k, precision = self.precision, debug = ML_Debug(display_format = "%f"))
ik = NearestInteger(unround_k, precision = ML_Int32, debug = ML_Debug(display_format = "%d"), tag = "ik")
ik.set_tag("ik")
k.set_tag("k")
exact_pre_mul = (k * log2_hi)
exact_pre_mul.set_attributes(exact= True)
exact_hi_part = vx - exact_pre_mul
exact_hi_part.set_attributes(exact = True)
r = exact_hi_part - k * log2_lo
r.set_tag("r")
r.set_attributes(debug = ML_Debug(display_format = "%f"))
opt_r = opt_eng.optimization_process(r, self.precision, copy = True, fuse_fma = fuse_fma)
tag_map = {}
opt_eng.register_nodes_by_tag(opt_r, tag_map)
cg_eval_error_copy_map = {
vx: Variable("x", precision = self.precision, interval = interval_vx),
tag_map["k"]: Variable("k", interval = interval_k, precision = self.precision)
}
#try:
if 1:
#eval_error = gappacg.get_eval_error(opt_r, cg_eval_error_copy_map, gappa_filename = "red_arg.g")
eval_error = gappacg.get_eval_error_v2(opt_eng, opt_r, cg_eval_error_copy_map, gappa_filename = "red_arg.g")
Log.report(Log.Info, "eval error: %s" % eval_error)
#except:
# Log.report(Log.Info, "gappa error evaluation failed")
print r.get_str(depth = None, display_precision = True, display_attribute = True)
print opt_r.get_str(depth = None, display_precision = True, display_attribute = True)
approx_interval = Interval(-log(2)/2, log(2)/2)
local_ulp = sup(ulp(exp(approx_interval), self.precision))
print "ulp: ", local_ulp
error_goal = local_ulp #S2**-(self.precision.get_field_size()+1)
error_goal_approx = S2**-1 * error_goal
Log.report(Log.Info, "\033[33;1m building mathematical polynomial \033[0m\n")
poly_degree = sup(guessdegree(exp(x), approx_interval, error_goal_approx)) #- 1
init_poly_degree = poly_degree
return
while 1:
Log.report(Log.Info, "attempting poly degree: %d" % poly_degree)
poly_object, poly_approx_error = Polynomial.build_from_approximation_with_error(exp(x), poly_degree, [self.precision]*(poly_degree+1), approx_interval, absolute)
Log.report(Log.Info, "poly approx error: %s" % poly_approx_error)
Log.report(Log.Info, "\033[33;1m generating polynomial evaluation scheme \033[0m")
poly = PolynomialSchemeEvaluator.generate_horner_scheme(poly_object, r, unified_precision = self.precision)
poly.set_tag("poly")
# optimizing poly before evaluation error computation
opt_poly = opt_eng.optimization_process(poly, self.precision)
#print "poly: ", poly.get_str(depth = None, display_precision = True)
#print "opt_poly: ", opt_poly.get_str(depth = None, display_precision = True)
# evaluating error of the polynomial approximation
r_gappa_var = Variable("r", precision = self.precision, interval = approx_interval)
poly_error_copy_map = {
r.get_handle().get_node(): r_gappa_var
}
gappacg = GappaCodeGenerator(target, declare_cst = False, disable_debug = True)
poly_eval_error = gappacg.get_eval_error_v2(opt_eng, poly.get_handle().get_node(), poly_error_copy_map, gappa_filename = "gappa_poly.g")
Log.report(Log.Info, "poly evaluation error: %s" % poly_eval_error)
global_poly_error = poly_eval_error + poly_approx_error
global_rel_poly_error = global_poly_error / exp(approx_interval)
print "global_poly_error: ", global_poly_error, global_rel_poly_error
flag = local_ulp > sup(abs(global_rel_poly_error))
print "test: ", flag
if flag: break
else:
if poly_degree > init_poly_degree + 5:
Log.report(Log.Error, "poly degree search did not converge")
poly_degree += 1
late_overflow_test = Comparison(ik, self.precision.get_emax(), specifier = Comparison.Greater, likely = False, debug = True, tag = "late_overflow_test")
overflow_exp_offset = (self.precision.get_emax() - self.precision.get_field_size() / 2)
diff_k = ik - overflow_exp_offset
diff_k.set_attributes(debug = ML_Debug(display_format = "%d"), tag = "diff_k")
late_overflow_result = (ExponentInsertion(diff_k) * poly) * ExponentInsertion(overflow_exp_offset)
late_overflow_result.set_attributes(silent = False, tag = "late_overflow_result", debug = debugf)
late_overflow_return = ConditionBlock(Test(late_overflow_result, specifier = Test.IsInfty, likely = False), ExpRaiseReturn(ML_FPE_Overflow, return_value = FP_PlusInfty(self.precision)), Return(late_overflow_result))
late_underflow_test = Comparison(k, self.precision.get_emin_normal(), specifier = Comparison.LessOrEqual, likely = False)
underflow_exp_offset = 2 * self.precision.get_field_size()
late_underflow_result = (ExponentInsertion(ik + underflow_exp_offset) * poly) * ExponentInsertion(-underflow_exp_offset)
late_underflow_result.set_attributes(debug = ML_Debug(display_format = "%e"), tag = "late_underflow_result", silent = False)
test_subnormal = Test(late_underflow_result, specifier = Test.IsSubnormal)
late_underflow_return = Statement(ConditionBlock(test_subnormal, ExpRaiseReturn(ML_FPE_Underflow, return_value = late_underflow_result)), Return(late_underflow_result))
std_result = poly * ExponentInsertion(ik, tag = "exp_ik", debug = debug_lftolx)
std_result.set_attributes(tag = "std_result", debug = debug_lftolx)
result_scheme = ConditionBlock(late_overflow_test, late_overflow_return, ConditionBlock(late_underflow_test, late_underflow_return, Return(std_result)))
std_return = ConditionBlock(early_overflow_test, early_overflow_return, ConditionBlock(early_underflow_test, early_underflow_return, result_scheme))
# main scheme
Log.report(Log.Info, "\033[33;1m MDL scheme \033[0m")
scheme = ConditionBlock(test_nan_or_inf, Statement(ClearException(), specific_return), std_return)
#print scheme.get_str(depth = None, display_precision = True)
# fusing FMA
if fuse_fma:
Log.report(Log.Info, "\033[33;1m MDL fusing FMA \033[0m")
scheme = opt_eng.fuse_multiply_add(scheme, silence = True)
Log.report(Log.Info, "\033[33;1m MDL abstract scheme \033[0m")
opt_eng.instantiate_abstract_precision(scheme, None)
Log.report(Log.Info, "\033[33;1m MDL instantiated scheme \033[0m")
opt_eng.instantiate_precision(scheme, default_precision = self.precision)
Log.report(Log.Info, "\033[33;1m subexpression sharing \033[0m")
opt_eng.subexpression_sharing(scheme)
Log.report(Log.Info, "\033[33;1m silencing operation \033[0m")
opt_eng.silence_fp_operations(scheme)
# registering scheme as function implementation
exp_implementation.set_scheme(scheme)
# check processor support
Log.report(Log.Info, "\033[33;1m checking processor support \033[0m")
opt_eng.check_processor_support(scheme)
# factorizing fast path
if fast_path_extract:
Log.report(Log.Info, "\033[33;1m factorizing fast path\033[0m")
opt_eng.factorize_fast_path(scheme)
Log.report(Log.Info, "\033[33;1m generating source code \033[0m")
cg = CCodeGenerator(processor, declare_cst = False, disable_debug = not debug_flag, libm_compliant = libm_compliant)
self.result = exp_implementation.get_definition(cg, C_Code, static_cst = True)
#self.result.add_header("support_lib/ml_types.h")
self.result.add_header("support_lib/ml_special_values.h")
self.result.add_header_comment("polynomial degree for exp(x): %d" % poly_degree)
self.result.add_header_comment("sollya polynomial for exp(x): %s" % poly_object.get_sollya_object())
if debug_flag:
self.result.add_header("stdio.h")
self.result.add_header("inttypes.h")
output_stream = open(output_file, "w")#"%s.c" % exp_implementation.get_name(), "w")
output_stream.write(self.result.get(cg))
output_stream.close()
