forked from nanoant/flops
-
Notifications
You must be signed in to change notification settings - Fork 0
/
sseflops.cc
182 lines (157 loc) · 4.14 KB
/
sseflops.cc
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
// x86 SSE FLOPs counter
// Based on:
// http://stackoverflow.com/questions/8389648/how-to-achieve-4-flops-per-cycle
#include <stdint.h>
#include <stdlib.h>
#include <iostream>
#include "openmp.h"
using namespace std;
#include <immintrin.h>
double test_dp_mac_SSE(double x,double y,size_t iterations){
register __m128d r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,rA,rB,rC,rD,rE,rF;
// Generate starting data.
r0 = _mm_set1_pd( x);
r1 = _mm_set1_pd( y);
r2 = _mm_set1_pd( y);
r3 = _mm_set1_pd( 1.0);
r4 = _mm_set1_pd(-1.0);
r5 = _mm_set1_pd( 1.0);
r6 = _mm_set1_pd(-1.0);
r7 = _mm_set1_pd( 1.0);
r8 = _mm_set1_pd(-1.0);
r9 = _mm_set1_pd( 1.0);
rA = _mm_set1_pd(-1.0);
rB = _mm_set1_pd( 1.0);
rC = _mm_set1_pd( x);
rD = _mm_set1_pd(-x);
rE = _mm_set1_pd(-y);
rF = _mm_set1_pd( y);
uint64_t iMASK = 0x800fffffffffffffull;
__m128d MASK = _mm_set1_pd(*(double*)&iMASK);
__m128d vONE = _mm_set1_pd(1.0);
size_t c = 0;
while (c < iterations){
size_t i = 0;
while (i < 1000){
// Here's the meat - the part that really matters.
r0 = _mm_mul_pd(r0,rC);
r1 = _mm_add_pd(r1,rD);
r2 = _mm_mul_pd(r2,rE);
r3 = _mm_sub_pd(r3,rF);
r4 = _mm_mul_pd(r4,rC);
r5 = _mm_add_pd(r5,rD);
r6 = _mm_mul_pd(r6,rE);
r7 = _mm_sub_pd(r7,rF);
r8 = _mm_mul_pd(r8,rC);
r9 = _mm_add_pd(r9,rD);
rA = _mm_mul_pd(rA,rE);
rB = _mm_sub_pd(rB,rF);
r0 = _mm_add_pd(r0,rF);
r1 = _mm_mul_pd(r1,rE);
r2 = _mm_sub_pd(r2,rD);
r3 = _mm_mul_pd(r3,rC);
r4 = _mm_add_pd(r4,rF);
r5 = _mm_mul_pd(r5,rE);
r6 = _mm_sub_pd(r6,rD);
r7 = _mm_mul_pd(r7,rC);
r8 = _mm_add_pd(r8,rF);
r9 = _mm_mul_pd(r9,rE);
rA = _mm_sub_pd(rA,rD);
rB = _mm_mul_pd(rB,rC);
r0 = _mm_mul_pd(r0,rC);
r1 = _mm_add_pd(r1,rD);
r2 = _mm_mul_pd(r2,rE);
r3 = _mm_sub_pd(r3,rF);
r4 = _mm_mul_pd(r4,rC);
r5 = _mm_add_pd(r5,rD);
r6 = _mm_mul_pd(r6,rE);
r7 = _mm_sub_pd(r7,rF);
r8 = _mm_mul_pd(r8,rC);
r9 = _mm_add_pd(r9,rD);
rA = _mm_mul_pd(rA,rE);
rB = _mm_sub_pd(rB,rF);
r0 = _mm_add_pd(r0,rF);
r1 = _mm_mul_pd(r1,rE);
r2 = _mm_sub_pd(r2,rD);
r3 = _mm_mul_pd(r3,rC);
r4 = _mm_add_pd(r4,rF);
r5 = _mm_mul_pd(r5,rE);
r6 = _mm_sub_pd(r6,rD);
r7 = _mm_mul_pd(r7,rC);
r8 = _mm_add_pd(r8,rF);
r9 = _mm_mul_pd(r9,rE);
rA = _mm_sub_pd(rA,rD);
rB = _mm_mul_pd(rB,rC);
i++;
}
// Need to renormalize to prevent denormal/overflow.
r0 = _mm_and_pd(r0,MASK);
r1 = _mm_and_pd(r1,MASK);
r2 = _mm_and_pd(r2,MASK);
r3 = _mm_and_pd(r3,MASK);
r4 = _mm_and_pd(r4,MASK);
r5 = _mm_and_pd(r5,MASK);
r6 = _mm_and_pd(r6,MASK);
r7 = _mm_and_pd(r7,MASK);
r8 = _mm_and_pd(r8,MASK);
r9 = _mm_and_pd(r9,MASK);
rA = _mm_and_pd(rA,MASK);
rB = _mm_and_pd(rB,MASK);
r0 = _mm_or_pd(r0,vONE);
r1 = _mm_or_pd(r1,vONE);
r2 = _mm_or_pd(r2,vONE);
r3 = _mm_or_pd(r3,vONE);
r4 = _mm_or_pd(r4,vONE);
r5 = _mm_or_pd(r5,vONE);
r6 = _mm_or_pd(r6,vONE);
r7 = _mm_or_pd(r7,vONE);
r8 = _mm_or_pd(r8,vONE);
r9 = _mm_or_pd(r9,vONE);
rA = _mm_or_pd(rA,vONE);
rB = _mm_or_pd(rB,vONE);
c++;
}
r0 = _mm_add_pd(r0,r1);
r2 = _mm_add_pd(r2,r3);
r4 = _mm_add_pd(r4,r5);
r6 = _mm_add_pd(r6,r7);
r8 = _mm_add_pd(r8,r9);
rA = _mm_add_pd(rA,rB);
r0 = _mm_add_pd(r0,r2);
r4 = _mm_add_pd(r4,r6);
r8 = _mm_add_pd(r8,rA);
r0 = _mm_add_pd(r0,r4);
r0 = _mm_add_pd(r0,r8);
// Prevent Dead Code Elimination
double out = 0;
out += ((double*)&r0)[0];
out += ((double*)&r0)[1];
return out;
}
void test_dp_mac_SSE(int tds,size_t iterations){
double *sum = (double*)malloc(tds * sizeof(double));
double start = get_wtime();
#pragma omp parallel num_threads(tds)
{
double ret = test_dp_mac_SSE(1.1,2.1,iterations);
sum[omp_get_thread_num()] = ret;
}
double secs = get_wtime() - start;
uint64_t ops = 48 * 1000 * iterations * tds * 2;
cout << "Seconds = " << secs << endl;
cout << "FP Ops = " << ops << endl;
cout << "GFLOPs = " << ops / 1e9 / secs << endl;
double out = 0;
int c = 0;
while (c < tds){
out += sum[c++];
}
cout << "sum = " << out << endl;
cout << endl;
free(sum);
}
int main(int argc, char const *argv[])
{
test_dp_mac_SSE(omp_get_max_threads(), argc >= 2 ? atol(argv[1]) : 1000000);
return 0;
}