perf(math): route ordinary products through MKL and preserve arithmetic

This commit is contained in:
KOKO\Mimi
2026-10-14 15:09:53 +09:00
parent b4fc1bb54b
commit 59c8e93b07
18 changed files with 793 additions and 169 deletions
@@ -3,7 +3,13 @@
#include <gtest/gtest.h>
#include <cmath>
#include <cstdint>
#include <cstring>
#include <limits>
#include <random>
#include <vector>
#include "high_low_arithmetic_original.h"
namespace {
using namespace fesa::math_internal;
@@ -125,4 +131,92 @@ TEST(HighLowArithmetic, RejectsChangedRoundingAndFlushToZeroEnvironment) {
EXPECT_FALSE(ArithmeticEnvironmentSupported());
#endif
}
std::uint64_t Bits(const double value) {
std::uint64_t result = 0;
std::memcpy(&result, &value, sizeof(result));
return result;
}
double FromBits(const std::uint64_t bits) {
double result = 0;
std::memcpy(&result, &bits, sizeof(result));
return result;
}
void ExpectSamePair(const HighLow actual,
const fesa::high_low_original::HighLow expected) {
EXPECT_EQ(Bits(actual.high), Bits(expected.high));
EXPECT_EQ(Bits(actual.low), Bits(expected.low));
}
TEST(HighLowArithmetic, BitExponentMatchesFrozenOracleAcrossEveryExponent) {
ASSERT_TRUE(ArithmeticEnvironmentSupported());
// Every normal exponent, every possible trailing significand-bit count,
// both signs; then every subnormal single-bit and mixed-bit boundary.
for (std::uint64_t exponent = 1; exponent < 2047; ++exponent) {
for (unsigned trailing = 0; trailing <= 52U; ++trailing) {
const auto fraction = trailing == 52U ? 0ULL : 1ULL << trailing;
for (const auto sign : {0ULL, 1ULL << 63U}) {
const double value = FromBits(sign | (exponent << 52U) | fraction);
ASSERT_EQ(LowestBitExponent(value),
fesa::high_low_original::LowestBitExponent(value));
}
}
}
for (unsigned bit = 0; bit < 52U; ++bit) {
for (const auto significand : {1ULL << bit, (1ULL << 52U) - (1ULL << bit)}) {
const double value = FromBits(significand);
EXPECT_EQ(LowestBitExponent(value),
fesa::high_low_original::LowestBitExponent(value));
}
}
}
TEST(HighLowArithmetic, OptimizedArithmeticMatchesFrozenOriginalBits) {
ASSERT_TRUE(ArithmeticEnvironmentSupported());
std::vector<double> values{0.0, -0.0,
std::numeric_limits<double>::denorm_min(),
-std::numeric_limits<double>::denorm_min(),
std::numeric_limits<double>::min(),
std::nextafter(std::numeric_limits<double>::min(), 0.0),
std::numeric_limits<double>::max(),
-std::numeric_limits<double>::max(), 1.0, -1.0,
std::nextafter(1.0, 2.0), std::ldexp(1.0, -53),
std::ldexp(1.0, -54), std::numeric_limits<double>::infinity(),
-std::numeric_limits<double>::infinity(),
std::numeric_limits<double>::quiet_NaN()};
std::mt19937_64 random{0x58a0fU};
for (int sample = 0; sample < 4000; ++sample) {
values.push_back(FromBits(random()));
}
for (std::size_t index = 0; index < values.size(); ++index) {
const double high = values[index];
const double low = values[(index * 13U + 7U) % values.size()];
const fesa::high_low_original::HighLow original{high, low};
EXPECT_EQ(IsNormalized({high, low}),
fesa::high_low_original::IsNormalized(original));
// Normalize a raw pair with the frozen operation, never the new predicate.
const auto a = fesa::high_low_original::TwoSum(high, low);
const auto b = fesa::high_low_original::TwoSum(
values[(index + 1U) % values.size()],
values[(index * 3U + 2U) % values.size()]);
ExpectSamePair(Add({a.high, a.low}, {b.high, b.low}),
fesa::high_low_original::Add(a, b));
ExpectSamePair(Multiply({a.high, a.low}, {b.high, b.low}),
fesa::high_low_original::Multiply(a, b));
ExpectSamePair(Divide({a.high, a.low}, {b.high, b.low}),
fesa::high_low_original::Divide(a, b));
ExpectSamePair(TwoProduct(high, low),
fesa::high_low_original::TwoProduct(high, low));
}
for (double high : {1.0, std::nextafter(1.0, 2.0), -1.0,
std::numeric_limits<double>::max()}) {
for (double low : {0.0, -0.0, std::ldexp(1.0, -53),
-std::ldexp(1.0, -53)}) {
EXPECT_EQ(IsNormalized({high, low}),
fesa::high_low_original::IsNormalized({high, low}));
}
}
}
} // namespace