├── LICENSE ├── README.md ├── lineitem_small.zip ├── nvparse.h └── test.cu /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # nvParse 2 | **Parsing CSV files with GPU** 3 | 4 | Parsing delimiter-separated files is a common task in data processing. The regular way of extracting the columns from a text file is to use strtok function : 5 | 6 | ```c 7 | char * p = strtok(line, "|"); 8 | while (p != NULL) 9 | { 10 | printf ("%s\n",p); 11 | p = strtok (NULL, "|"); 12 | } 13 | ``` 14 | 15 | However this method of parsing is CPU bound because 16 | 17 | - it doesn't take advantage of multiple cores of modern CPUs. 18 | 19 | - memory bandwidth limitations 20 | 21 | This is how the same task can be done using a GPU : 22 | 23 | ```c++ 24 | auto break_cnt = thrust::count(d_readbuff.begin(), d_readbuff.end(), '\n'); 25 | thrust::device_vector dev_pos(break_cnt); 26 | thrust::copy_if(thrust::make_counting_iterator(0), 27 | thrust::make_counting_iterator(bytes_read-1), 28 | d_readbuff.begin(), dev_pos.begin(), _1 == '\n'); 29 | ``` 30 | 31 | The first line counts the number of lines in a buffer (assuming that file is read into memory and copied to gpu buffer d\_readbuff). 32 | The second line creates a vector in gpu memory that will hold the positions of new line characters. 33 | The last line compares the characters in a buffer to new line character and, if a match is found, copies the position of the character to dev_pos vector. 34 | 35 | Now that we know the starting positions of every line in a buffer, we can launch a gpu procedure that will parse the lines using several thousands gpu cores : 36 | 37 | ```c++ 38 | thrust::counting_iterator begin(0); 39 | parse_functor ff(...); // examples of call's parameters are in test.cu file 40 | thrust::for_each(begin, begin + break_cnt, ff); 41 | ``` 42 | 43 | As a result we get the needed columns in separate arrays in gpu memory and can copy them to host memory. Or convert them to binary values using relevant gpu procedures : 44 | 45 | ```c++ 46 | gpu_atoll atoll_ff(...); 47 | thrust::for_each(begin, begin + break_cnt, atoll_ff); 48 | ``` 49 | 50 | 51 | **Benchmarks !** 52 | 53 | Hardware : PC with one Intel i3-4130, 16GB of RAM, one 2TB hard drive and GTX Titan 54 | 55 | File : 750MB lineitem.tbl text file (6001215 lines) 56 | 57 | **Parsing 1 field using CPU :** 58 | 59 | $ time cut -d "|" -f 6 lineitem.tbl > /dev/null 60 | 61 | real 0m28.764s 62 | 63 | **Parsing 11 fields using hand-written program with strtok : (no threads, no memory-mapped file)** 64 | 65 | 14.5s 66 | 67 | **Parsing 11 fields using GPU :** 68 | 69 | $ time ./test 70 | 71 | 0.77s 72 | 73 | And the actual gpu parsing part is done in just 0.25 seconds. 74 | 75 | P.S. Thanks to Nicolas Guillemot for suggestion on memory-mapping files. 76 | -------------------------------------------------------------------------------- /lineitem_small.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/antonmks/nvParse/339bfbac7cc7a11a21c944f113b7df40c98940e5/lineitem_small.zip -------------------------------------------------------------------------------- /nvparse.h: -------------------------------------------------------------------------------- 1 | struct is_break 2 | { 3 | __host__ __device__ 4 | bool operator()(const char x) 5 | { 6 | return x == 10; 7 | } 8 | }; 9 | 10 | struct gpu_date 11 | { 12 | const char *source; 13 | long long int *dest; 14 | 15 | gpu_date(const char *_source, long long int *_dest): 16 | source(_source), dest(_dest) {} 17 | template 18 | __host__ __device__ 19 | void operator()(const IndexType & i) { std ::cout << std::endl; 20 | const char *s; 21 | long long int acc; 22 | int z = 0, c; 23 | 24 | s = source + 10*i; 25 | c = (unsigned char) *s++; 26 | 27 | for (acc = 0; z < 10; c = (unsigned char) *s++) { 28 | if(c != '-') { 29 | c -= '0'; 30 | acc *= 10; 31 | acc += c; 32 | }; 33 | z++; 34 | } 35 | dest[i] = acc; 36 | } 37 | }; 38 | 39 | 40 | struct gpu_atof 41 | { 42 | const char *source; 43 | double *dest; 44 | const unsigned int *len; 45 | 46 | gpu_atof(const char *_source, double *_dest, const unsigned int *_len): 47 | source(_source), dest(_dest), len(_len) {} 48 | template 49 | __host__ __device__ 50 | void operator()(const IndexType & i) { 51 | const char *p; 52 | int frac; 53 | double sign, value, scale; 54 | 55 | p = source + len[0]*i; 56 | 57 | while (*p == ' ') { 58 | p += 1; 59 | } 60 | 61 | sign = 1.0; 62 | if (*p == '-') { 63 | sign = -1.0; 64 | p += 1; 65 | } else if (*p == '+') { 66 | p += 1; 67 | } 68 | 69 | for (value = 0.0; *p >= '0' && *p <= '9'; p += 1) { 70 | value = value * 10.0 + (*p - '0'); 71 | } 72 | 73 | if (*p == '.') { 74 | double pow10 = 10.0; 75 | p += 1; 76 | while (*p >= '0' && *p <= '9') { 77 | value += (*p - '0') / pow10; 78 | pow10 *= 10.0; 79 | p += 1; 80 | } 81 | } 82 | 83 | frac = 0; 84 | scale = 1.0; 85 | 86 | dest[i] = sign * (frac ? (value / scale) : (value * scale)); 87 | } 88 | }; 89 | 90 | 91 | struct gpu_atoll 92 | { 93 | const char *source; 94 | long long int *dest; 95 | const unsigned int *len; 96 | 97 | gpu_atoll(const char *_source, long long int *_dest, const unsigned int *_len): 98 | source(_source), dest(_dest), len(_len) {} 99 | template 100 | __host__ __device__ 101 | void operator()(const IndexType & i) { 102 | const char *s; 103 | long long int acc; 104 | int c; 105 | int neg; 106 | 107 | s = source + len[0]*i; 108 | 109 | do { 110 | c = (unsigned char) *s++; 111 | } while (c == ' '); 112 | 113 | if (c == '-') { 114 | neg = 1; 115 | c = *s++; 116 | } else { 117 | neg = 0; 118 | if (c == '+') 119 | c = *s++; 120 | } 121 | 122 | for (acc = 0;; c = (unsigned char) *s++) { 123 | if (c >= '0' && c <= '9') 124 | c -= '0'; 125 | else 126 | break; 127 | if (c >= 10) 128 | break; 129 | if (neg) { 130 | acc *= 10; 131 | acc -= c; 132 | } 133 | else { 134 | acc *= 10; 135 | acc += c; 136 | } 137 | } 138 | dest[i] = acc; 139 | } 140 | }; 141 | 142 | struct parse_functor 143 | { 144 | const char *source; 145 | char **dest; 146 | const unsigned int *ind; 147 | const unsigned int *cnt; 148 | const char *separator; 149 | const int *src_ind; 150 | const unsigned int *dest_len; 151 | 152 | parse_functor(const char* _source, char** _dest, const unsigned int* _ind, const unsigned int* _cnt, const char* _separator, 153 | const int* _src_ind, const unsigned int* _dest_len): 154 | source(_source), dest(_dest), ind(_ind), cnt(_cnt), separator(_separator), src_ind(_src_ind), dest_len(_dest_len) {} 155 | 156 | template 157 | __host__ __device__ 158 | void operator()(const IndexType & i) { 159 | unsigned int curr_cnt = 0, dest_curr = 0, j = 0, t, pos; 160 | pos = src_ind[i]+1; 161 | 162 | while(dest_curr < *cnt) { 163 | if(ind[dest_curr] == curr_cnt) { //process 164 | t = 0; 165 | while(source[pos+j] != *separator) { 166 | if(source[pos+j] != 0) { 167 | dest[dest_curr][dest_len[dest_curr]*i+t] = source[pos+j]; 168 | t++; 169 | }; 170 | j++; 171 | }; 172 | j++; 173 | dest_curr++; 174 | } 175 | else { 176 | while(source[pos+j] != *separator) { 177 | j++; 178 | }; 179 | j++; 180 | }; 181 | curr_cnt++; 182 | } 183 | } 184 | }; -------------------------------------------------------------------------------- /test.cu: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | #include 5 | #include "nvparse.h" 6 | 7 | #ifdef _WIN64 8 | #define atoll(S) _atoi64(S) 9 | #include 10 | #else 11 | #include 12 | #include 13 | #include 14 | #include 15 | #include 16 | #include 17 | #endif 18 | 19 | int main() { 20 | 21 | std::clock_t start1 = std::clock(); 22 | FILE* f = fopen("lineitem.tbl", "r" ); 23 | fseek(f, 0, SEEK_END); 24 | long fileSize = ftell(f); 25 | thrust::device_vector dev(fileSize); 26 | fclose(f); 27 | 28 | #ifdef _WIN64 29 | HANDLE file = CreateFileA("lineitem.tbl", GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL | FILE_FLAG_SEQUENTIAL_SCAN, NULL); 30 | assert(file != INVALID_HANDLE_VALUE); 31 | 32 | HANDLE fileMapping = CreateFileMapping(file, NULL, PAGE_READONLY, 0, 0, NULL); 33 | assert(fileMapping != INVALID_HANDLE_VALUE); 34 | 35 | LPVOID fileMapView = MapViewOfFile(fileMapping, FILE_MAP_READ, 0, 0, 0); 36 | auto fileMapViewChar = (const char*)fileMapView; 37 | assert(fileMapView != NULL); 38 | 39 | thrust::copy(fileMapViewChar, fileMapViewChar+fileSize, dev.begin()); 40 | #else 41 | 42 | struct stat sb; 43 | char *p; 44 | int fd; 45 | 46 | fd = open ("lineitem.tbl", O_RDONLY); 47 | if (fd == -1) { 48 | perror ("open"); 49 | return 1; 50 | } 51 | 52 | if (fstat (fd, &sb) == -1) { 53 | perror ("fstat"); 54 | return 1; 55 | } 56 | 57 | if (!S_ISREG (sb.st_mode)) { 58 | fprintf (stderr, "%s is not a file\n", "lineitem.tbl"); 59 | return 1; 60 | } 61 | 62 | p = (char*)mmap (0, fileSize, PROT_READ, MAP_SHARED, fd, 0); 63 | 64 | if (p == MAP_FAILED) { 65 | perror ("mmap"); 66 | return 1; 67 | } 68 | 69 | if (close (fd) == -1) { 70 | perror ("close"); 71 | return 1; 72 | } 73 | 74 | thrust::copy(p, p+fileSize, dev.begin()); 75 | 76 | #endif 77 | 78 | int cnt = thrust::count(dev.begin(), dev.end(), '\n'); 79 | std::cout << "There are " << cnt << " total lines in a file" << std::endl; 80 | 81 | thrust::device_vector dev_pos(cnt+1); 82 | dev_pos[0] = -1; 83 | 84 | thrust::copy_if(thrust::make_counting_iterator((unsigned int)0), thrust::make_counting_iterator((unsigned int)fileSize), 85 | dev.begin(), dev_pos.begin()+1, is_break()); 86 | 87 | thrust::device_vector dev_res1(cnt*15); 88 | thrust::fill(dev_res1.begin(), dev_res1.end(), 0); 89 | thrust::device_vector dev_res2(cnt*15); 90 | thrust::fill(dev_res2.begin(), dev_res2.end(), 0); 91 | thrust::device_vector dev_res3(cnt*15); 92 | thrust::fill(dev_res3.begin(), dev_res3.end(), 0); 93 | thrust::device_vector dev_res4(cnt*15); 94 | thrust::fill(dev_res4.begin(), dev_res4.end(), 0); 95 | thrust::device_vector dev_res5(cnt*15); 96 | thrust::fill(dev_res5.begin(), dev_res5.end(), 0); 97 | thrust::device_vector dev_res6(cnt*15); 98 | thrust::fill(dev_res6.begin(), dev_res6.end(), 0); 99 | thrust::device_vector dev_res7(cnt*15); 100 | thrust::fill(dev_res7.begin(), dev_res7.end(), 0); 101 | thrust::device_vector dev_res8(cnt*15); 102 | thrust::fill(dev_res8.begin(), dev_res8.end(), 0); 103 | thrust::device_vector dev_res9(cnt); 104 | thrust::fill(dev_res9.begin(), dev_res9.end(), 0); 105 | thrust::device_vector dev_res10(cnt); 106 | thrust::fill(dev_res10.begin(), dev_res10.end(), 0); 107 | thrust::device_vector dev_res11(cnt*10); 108 | thrust::fill(dev_res11.begin(), dev_res11.end(), 0); 109 | 110 | thrust::device_vector dest(11); 111 | dest[0] = thrust::raw_pointer_cast(dev_res1.data()); 112 | dest[1] = thrust::raw_pointer_cast(dev_res2.data()); 113 | dest[2] = thrust::raw_pointer_cast(dev_res3.data()); 114 | dest[3] = thrust::raw_pointer_cast(dev_res4.data()); 115 | dest[4] = thrust::raw_pointer_cast(dev_res5.data()); 116 | dest[5] = thrust::raw_pointer_cast(dev_res6.data()); 117 | dest[6] = thrust::raw_pointer_cast(dev_res7.data()); 118 | dest[7] = thrust::raw_pointer_cast(dev_res8.data()); 119 | dest[8] = thrust::raw_pointer_cast(dev_res9.data()); 120 | dest[9] = thrust::raw_pointer_cast(dev_res10.data()); 121 | dest[10] = thrust::raw_pointer_cast(dev_res11.data()); 122 | 123 | thrust::device_vector ind(11); //fields positions 124 | ind[0] = 0; 125 | ind[1] = 1; 126 | ind[2] = 2; 127 | ind[3] = 3; 128 | ind[4] = 4; 129 | ind[5] = 5; 130 | ind[6] = 6; 131 | ind[7] = 7; 132 | ind[8] = 8; 133 | ind[9] = 9; 134 | ind[10] = 10; 135 | 136 | thrust::device_vector dest_len(11); //fields max lengths 137 | dest_len[0] = 15; 138 | dest_len[1] = 15; 139 | dest_len[2] = 15; 140 | dest_len[3] = 15; 141 | dest_len[4] = 15; 142 | dest_len[5] = 15; 143 | dest_len[6] = 15; 144 | dest_len[7] = 15; 145 | dest_len[8] = 1; 146 | dest_len[9] = 1; 147 | dest_len[10] = 10; 148 | 149 | thrust::device_vector ind_cnt(1); //fields count 150 | ind_cnt[0] = 10; 151 | 152 | thrust::device_vector sep(1); 153 | sep[0] = '|'; 154 | 155 | thrust::counting_iterator begin(0); 156 | parse_functor ff((const char*)thrust::raw_pointer_cast(dev.data()),(char**)thrust::raw_pointer_cast(dest.data()), thrust::raw_pointer_cast(ind.data()), 157 | thrust::raw_pointer_cast(ind_cnt.data()), thrust::raw_pointer_cast(sep.data()), thrust::raw_pointer_cast(dev_pos.data()), thrust::raw_pointer_cast(dest_len.data())); 158 | thrust::for_each(begin, begin + cnt, ff); // now dev_pos vector contains the indexes of new line characters 159 | 160 | std::cout<< "time0 " << ( ( std::clock() - start1 ) / (double)CLOCKS_PER_SEC ) << '\n'; 161 | 162 | thrust::device_vector d_int(cnt); 163 | thrust::device_vector d_float(cnt); 164 | 165 | //check the text results in dev_res array : 166 | for(int i = 0; i < 100; i++) 167 | std::cout << dev_res9[i]; 168 | std ::cout << std::endl; 169 | 170 | for(int i = 0; i < 100; i++) 171 | std::cout << dev_res10[i]; 172 | std ::cout << std::endl; 173 | 174 | //binary integer results 175 | ind_cnt[0] = 15; 176 | gpu_atoll atoll_ff((const char*)thrust::raw_pointer_cast(dev_res3.data()),(long long int*)thrust::raw_pointer_cast(d_int.data()), 177 | thrust::raw_pointer_cast(ind_cnt.data())); 178 | thrust::for_each(begin, begin + cnt, atoll_ff); 179 | 180 | for(int i = 0; i < 10; i++) 181 | std::cout << d_int[i] << std::endl; 182 | 183 | std::cout << std::endl; 184 | 185 | //binary float results 186 | gpu_atof atof_ff((const char*)thrust::raw_pointer_cast(dev_res6.data()),(double*)thrust::raw_pointer_cast(d_float.data()), 187 | thrust::raw_pointer_cast(ind_cnt.data())); 188 | thrust::for_each(begin, begin + cnt, atof_ff); 189 | 190 | std::cout.precision(10); 191 | for(int i = 0; i < 10; i++) 192 | std::cout << d_int[i] << std::endl; 193 | 194 | 195 | return 0; 196 | 197 | } 198 | --------------------------------------------------------------------------------