5dbd5118ec
Re-order exceptional branches and slightly adjust the evaluation. Performance tested with the CORE-MATH project on AMD EPYC 7B12 (clocks/op) Reciprocal throughputs: ``` --- BEFORE --- $ CORE_MATH_PERF_MODE=rdtsc ./perf.sh tanhf [####################] 100 % (with -mavx2 -mfma) Ntrial = 20 ; Min = 7.794 + 0.102 clc/call; Median-Min = 0.066 clc/call; Max = 8.267 clc/call; [####################] 100 %. (with -msse4.2) Ntrial = 20 ; Min = 10.783 + 0.172 clc/call; Median-Min = 0.144 clc/call; Max = 11.446 clc/call; [####################] 100 %. (SSE2) Ntrial = 20 ; Min = 18.926 + 0.381 clc/call; Median-Min = 0.342 clc/call; Max = 19.623 clc/call; --- AFTER --- $ CORE_MATH_PERF_MODE=rdtsc ./perf.sh tanhf [####################] 100 % (with -mavx2 -mfma) Ntrial = 20 ; Min = 6.598 + 0.085 clc/call; Median-Min = 0.052 clc/call; Max = 6.868 clc/call; [####################] 100 % (with -msse4.2) Ntrial = 20 ; Min = 9.245 + 0.304 clc/call; Median-Min = 0.248 clc/call; Max = 10.675 clc/call; [####################] 100 %. (SSE2) Ntrial = 20 ; Min = 11.724 + 0.440 clc/call; Median-Min = 0.444 clc/call; Max = 12.262 clc/call; ``` Latency: ``` --- BEFORE --- $ PERF_ARGS="--latency" CORE_MATH_PERF_MODE=rdtsc ./perf.sh tanhf [####################] 100 % (with -mavx2 -mfma) Ntrial = 20 ; Min = 38.821 + 0.157 clc/call; Median-Min = 0.122 clc/call; Max = 39.539 clc/call; [####################] 100 %. (with -msse4.2) Ntrial = 20 ; Min = 44.767 + 0.766 clc/call; Median-Min = 0.681 clc/call; Max = 45.951 clc/call; [####################] 100 %. (SSE2) Ntrial = 20 ; Min = 55.055 + 1.512 clc/call; Median-Min = 1.571 clc/call; Max = 57.039 clc/call; --- AFTER --- $ PERF_ARGS="--latency" CORE_MATH_PERF_MODE=rdtsc ./perf.sh tanhf [####################] 100 % (with -mavx2 -mfma) Ntrial = 20 ; Min = 36.147 + 0.194 clc/call; Median-Min = 0.181 clc/call; Max = 36.536 clc/call; [####################] 100 % (with -msse4.2) Ntrial = 20 ; Min = 40.904 + 0.728 clc/call; Median-Min = 0.557 clc/call; Max = 42.231 clc/call; [####################] 100 %. (SSE2) Ntrial = 20 ; Min = 55.776 + 0.557 clc/call; Median-Min = 0.542 clc/call; Max = 56.551 clc/call; ``` Reviewed By: michaelrj Differential Revision: https://reviews.llvm.org/D153026
74 lines
2.1 KiB
C++
74 lines
2.1 KiB
C++
//===-- Unittests for tanhf -----------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "src/__support/FPUtil/FPBits.h"
|
|
#include "src/errno/libc_errno.h"
|
|
#include "src/math/tanhf.h"
|
|
#include "test/UnitTest/FPMatcher.h"
|
|
#include "test/UnitTest/Test.h"
|
|
#include "utils/MPFRWrapper/MPFRUtils.h"
|
|
#include <math.h>
|
|
|
|
#include <errno.h>
|
|
#include <stdint.h>
|
|
|
|
using FPBits = __llvm_libc::fputil::FPBits<float>;
|
|
|
|
namespace mpfr = __llvm_libc::testing::mpfr;
|
|
|
|
DECLARE_SPECIAL_CONSTANTS(float)
|
|
|
|
TEST(LlvmLibcTanhfTest, SpecialNumbers) {
|
|
libc_errno = 0;
|
|
|
|
EXPECT_FP_EQ(aNaN, __llvm_libc::tanhf(aNaN));
|
|
EXPECT_MATH_ERRNO(0);
|
|
|
|
EXPECT_FP_EQ(0.0f, __llvm_libc::tanhf(0.0f));
|
|
EXPECT_MATH_ERRNO(0);
|
|
|
|
EXPECT_FP_EQ(-0.0f, __llvm_libc::tanhf(-0.0f));
|
|
EXPECT_MATH_ERRNO(0);
|
|
|
|
EXPECT_FP_EQ(1.0f, __llvm_libc::tanhf(inf));
|
|
EXPECT_MATH_ERRNO(0);
|
|
|
|
EXPECT_FP_EQ(-1.0f, __llvm_libc::tanhf(neg_inf));
|
|
EXPECT_MATH_ERRNO(0);
|
|
}
|
|
|
|
TEST(LlvmLibcTanhfTest, InFloatRange) {
|
|
constexpr uint32_t COUNT = 100'001;
|
|
constexpr uint32_t STEP = UINT32_MAX / COUNT;
|
|
for (uint32_t i = 0, v = 0; i <= COUNT; ++i, v += STEP) {
|
|
float x = float(FPBits(v));
|
|
if (isnan(x) || isinf(x))
|
|
continue;
|
|
ASSERT_MPFR_MATCH_ALL_ROUNDING(mpfr::Operation::Tanh, x,
|
|
__llvm_libc::tanhf(x), 0.5);
|
|
}
|
|
}
|
|
|
|
TEST(LlvmLibcTanhfTest, ExceptionalValues) {
|
|
constexpr int N = 4;
|
|
constexpr uint32_t INPUTS[N] = {
|
|
0x0040'0000,
|
|
0x1780'0000,
|
|
0x3a12'85ff,
|
|
0x4058'e0a3,
|
|
};
|
|
|
|
for (int i = 0; i < N; ++i) {
|
|
float x = float(FPBits(INPUTS[i]));
|
|
EXPECT_MPFR_MATCH_ALL_ROUNDING(mpfr::Operation::Tanh, x,
|
|
__llvm_libc::tanhf(x), 0.5);
|
|
EXPECT_MPFR_MATCH_ALL_ROUNDING(mpfr::Operation::Tanh, -x,
|
|
__llvm_libc::tanhf(-x), 0.5);
|
|
}
|
|
}
|