11{
2- "device_name" : " NVIDIA RTX A4000" ,
3- "kernel_name" : " vector_add" ,
4- "tune_params_keys" : [
5- " block_size_x"
6- ],
7- "tune_params" : {
8- "block_size_x" : [
9- 128 ,
10- 192 ,
11- 256 ,
12- 320 ,
13- 384 ,
14- 448 ,
15- 512 ,
16- 576 ,
17- 640 ,
18- 704 ,
19- 768 ,
20- 832 ,
21- 896 ,
22- 960 ,
23- 1024
24- ]
25- },
26- "cache" : {
27- "128" : {"block_size_x" : 128 , "time" : 0.04073600071881499 , "times" : [0.1268800050020218 , 0.031072000041604042 , 0.027295999228954315 , 0.025472000241279602 , 0.025119999423623085 , 0.025248000398278236 , 0.024064000695943832 ], "compile_time" : 440.9545585513115 , "verification_time" : 0 , "benchmark_time" : 1.091592013835907 , "strategy_time" : 0 , "framework_time" : 0.8587837219238281 },
28- "192" : {"block_size_x" : 192 , "time" : 0.04095085710287094 , "times" : [0.12908799946308136 , 0.03046399913728237 , 0.027744000777602196 , 0.025151999667286873 , 0.024960000067949295 , 0.024992000311613083 , 0.02425600029528141 ], "compile_time" : 436.15153804421425 , "verification_time" : 0 , "benchmark_time" : 1.0972395539283752 , "strategy_time" : 0 , "framework_time" : 1.6656816005706787 },
29- "256" : {"block_size_x" : 256 , "time" : 0.04189257137477398 , "times" : [0.13180799782276154 , 0.031136000528931618 , 0.028095999732613564 , 0.027008000761270523 , 0.025087999179959297 , 0.02505600079894066 , 0.02505600079894066 ], "compile_time" : 436.5839697420597 , "verification_time" : 0 , "benchmark_time" : 1.0691732168197632 , "strategy_time" : 0 , "framework_time" : 1.6054585576057434 },
30- "320" : {"block_size_x" : 320 , "time" : 0.04208914376795292 , "times" : [0.1358720064163208 , 0.030688000842928886 , 0.02768000029027462 , 0.02582399919629097 , 0.025087999179959297 , 0.025312000885605812 , 0.024159999564290047 ], "compile_time" : 438.9761835336685 , "verification_time" : 0 , "benchmark_time" : 1.0976120829582214 , "strategy_time" : 0 , "framework_time" : 1.4494173228740692 },
31- "384" : {"block_size_x" : 384 , "time" : 0.04174171467976911 , "times" : [0.13251200318336487 , 0.03167999908328056 , 0.027871999889612198 , 0.025312000885605812 , 0.024671999737620354 , 0.02505600079894066 , 0.025087999179959297 ], "compile_time" : 440.71199372410774 , "verification_time" : 0 , "benchmark_time" : 1.0499358177185059 , "strategy_time" : 0 , "framework_time" : 1.682564616203308 },
32- "448" : {"block_size_x" : 448 , "time" : 0.03249828570655414 , "times" : [0.0647680014371872 , 0.03167999908328056 , 0.028255999088287354 , 0.025280000641942024 , 0.027103999629616737 , 0.02550400048494339 , 0.02489599958062172 ], "compile_time" : 449.13655519485474 , "verification_time" : 0 , "benchmark_time" : 1.1196956038475037 , "strategy_time" : 0 , "framework_time" : 1.5890561044216156 },
33- "512" : {"block_size_x" : 512 , "time" : 0.04139885599059718 , "times" : [0.13023999333381653 , 0.031136000528931618 , 0.02831999957561493 , 0.02595200017094612 , 0.024607999250292778 , 0.025151999667286873 , 0.024383999407291412 ], "compile_time" : 440.5844733119011 , "verification_time" : 0 , "benchmark_time" : 1.09076127409935 , "strategy_time" : 0 , "framework_time" : 1.853298395872116 },
34- "576" : {"block_size_x" : 576 , "time" : 0.04189257137477398 , "times" : [0.12995199859142303 , 0.03200000151991844 , 0.028511999174952507 , 0.026623999699950218 , 0.025760000571608543 , 0.02537599951028824 , 0.02502400055527687 ], "compile_time" : 442.16764718294144 , "verification_time" : 0 , "benchmark_time" : 1.1038780212402344 , "strategy_time" : 0 , "framework_time" : 1.8403716385364532 },
35- "640" : {"block_size_x" : 640 , "time" : 0.0411702852163996 , "times" : [0.12796799838542938 , 0.03081599995493889 , 0.02969600073993206 , 0.025439999997615814 , 0.02409599907696247 , 0.02582399919629097 , 0.024351999163627625 ], "compile_time" : 437.98910081386566 , "verification_time" : 0 , "benchmark_time" : 1.0496266186237335 , "strategy_time" : 0 , "framework_time" : 1.8264725804328918 },
36- "704" : {"block_size_x" : 704 , "time" : 0.04184228580977235 , "times" : [0.1343040019273758 , 0.03094400092959404 , 0.02908799983561039 , 0.025151999667286873 , 0.02486399933695793 , 0.024447999894618988 , 0.02409599907696247 ], "compile_time" : 443.51235404610634 , "verification_time" : 0 , "benchmark_time" : 1.1033527553081512 , "strategy_time" : 0 , "framework_time" : 1.6709677875041962 },
37- "768" : {"block_size_x" : 768 , "time" : 0.03175771422684193 , "times" : [0.06230400130152702 , 0.0315839983522892 , 0.02831999957561493 , 0.02672000043094158 , 0.023679999634623528 , 0.023903999477624893 , 0.02579200081527233 ], "compile_time" : 450.4409395158291 , "verification_time" : 0 , "benchmark_time" : 1.101326197385788 , "strategy_time" : 0 , "framework_time" : 1.7531625926494598 },
38- "832" : {"block_size_x" : 832 , "time" : 0.040941715240478516 , "times" : [0.12998400628566742 , 0.03094400092959404 , 0.027103999629616737 , 0.024768000468611717 , 0.025439999997615814 , 0.023903999477624893 , 0.024447999894618988 ], "compile_time" : 439.9200603365898 , "verification_time" : 0 , "benchmark_time" : 1.0421127080917358 , "strategy_time" : 0 , "framework_time" : 2.1368376910686493 },
39- "896" : {"block_size_x" : 896 , "time" : 0.04177371359297207 , "times" : [0.12931199371814728 , 0.03731200098991394 , 0.02812799997627735 , 0.02502400055527687 , 0.02412799932062626 , 0.024768000468611717 , 0.023744000121951103 ], "compile_time" : 439.23527002334595 , "verification_time" : 0 , "benchmark_time" : 1.0946877300739288 , "strategy_time" : 0 , "framework_time" : 2.03637033700943 },
40- "960" : {"block_size_x" : 960 , "time" : 0.042189714631864 , "times" : [0.1335040032863617 , 0.031039999797940254 , 0.02876799926161766 , 0.02579200081527233 , 0.025119999423623085 , 0.02566399984061718 , 0.025439999997615814 ], "compile_time" : 441.7596235871315 , "verification_time" : 0 , "benchmark_time" : 1.1166557669639587 , "strategy_time" : 0 , "framework_time" : 1.7383433878421783 },
41- "1024" : {"block_size_x" : 1024 , "time" : 0.04114742816558906 , "times" : [0.13087999820709229 , 0.03049599938094616 , 0.027936000376939774 , 0.02486399933695793 , 0.0244159996509552 , 0.024320000782608986 , 0.025119999423623085 ], "compile_time" : 442.8337663412094 , "verification_time" : 0 , "benchmark_time" : 1.0683201253414154 , "strategy_time" : 0 , "framework_time" : 1.9918642938137054 }}
42- }
2+ "device_name" : " NVIDIA RTX A4000" ,
3+ "kernel_name" : " vector_add" ,
4+ "tune_params_keys" : [
5+ " block_size_x"
6+ ],
7+ "tune_params" : {
8+ "block_size_x" : [
9+ 128 ,
10+ 192 ,
11+ 256 ,
12+ 320 ,
13+ 384 ,
14+ 448 ,
15+ 512 ,
16+ 576 ,
17+ 640 ,
18+ 704 ,
19+ 768 ,
20+ 832 ,
21+ 896 ,
22+ 960 ,
23+ 1024
24+ ]
25+ },
26+ "cache" : {
27+ "128" : {
28+ "block_size_x" : 128 ,
29+ "time" : 0.04073600071881499 ,
30+ "times" : [
31+ 0.1268800050020218 ,
32+ 0.031072000041604042 ,
33+ 0.027295999228954315 ,
34+ 0.025472000241279602 ,
35+ 0.025119999423623085 ,
36+ 0.025248000398278236 ,
37+ 0.024064000695943832
38+ ],
39+ "compile_time" : 440.9545585513115 ,
40+ "verification_time" : 0 ,
41+ "benchmark_time" : 1.091592013835907 ,
42+ "strategy_time" : 0 ,
43+ "framework_time" : 0.8587837219238281 ,
44+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
45+ },
46+ "192" : {
47+ "block_size_x" : 192 ,
48+ "time" : 0.04095085710287094 ,
49+ "times" : [
50+ 0.12908799946308136 ,
51+ 0.03046399913728237 ,
52+ 0.027744000777602196 ,
53+ 0.025151999667286873 ,
54+ 0.024960000067949295 ,
55+ 0.024992000311613083 ,
56+ 0.02425600029528141
57+ ],
58+ "compile_time" : 436.15153804421425 ,
59+ "verification_time" : 0 ,
60+ "benchmark_time" : 1.0972395539283752 ,
61+ "strategy_time" : 0 ,
62+ "framework_time" : 1.6656816005706787 ,
63+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
64+ },
65+ "256" : {
66+ "block_size_x" : 256 ,
67+ "time" : 0.04189257137477398 ,
68+ "times" : [
69+ 0.13180799782276154 ,
70+ 0.031136000528931618 ,
71+ 0.028095999732613564 ,
72+ 0.027008000761270523 ,
73+ 0.025087999179959297 ,
74+ 0.02505600079894066 ,
75+ 0.02505600079894066
76+ ],
77+ "compile_time" : 436.5839697420597 ,
78+ "verification_time" : 0 ,
79+ "benchmark_time" : 1.0691732168197632 ,
80+ "strategy_time" : 0 ,
81+ "framework_time" : 1.6054585576057434 ,
82+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
83+ },
84+ "320" : {
85+ "block_size_x" : 320 ,
86+ "time" : 0.04208914376795292 ,
87+ "times" : [
88+ 0.1358720064163208 ,
89+ 0.030688000842928886 ,
90+ 0.02768000029027462 ,
91+ 0.02582399919629097 ,
92+ 0.025087999179959297 ,
93+ 0.025312000885605812 ,
94+ 0.024159999564290047
95+ ],
96+ "compile_time" : 438.9761835336685 ,
97+ "verification_time" : 0 ,
98+ "benchmark_time" : 1.0976120829582214 ,
99+ "strategy_time" : 0 ,
100+ "framework_time" : 1.4494173228740692 ,
101+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
102+ },
103+ "384" : {
104+ "block_size_x" : 384 ,
105+ "time" : 0.04174171467976911 ,
106+ "times" : [
107+ 0.13251200318336487 ,
108+ 0.03167999908328056 ,
109+ 0.027871999889612198 ,
110+ 0.025312000885605812 ,
111+ 0.024671999737620354 ,
112+ 0.02505600079894066 ,
113+ 0.025087999179959297
114+ ],
115+ "compile_time" : 440.71199372410774 ,
116+ "verification_time" : 0 ,
117+ "benchmark_time" : 1.0499358177185059 ,
118+ "strategy_time" : 0 ,
119+ "framework_time" : 1.682564616203308 ,
120+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
121+ },
122+ "448" : {
123+ "block_size_x" : 448 ,
124+ "time" : 0.03249828570655414 ,
125+ "times" : [
126+ 0.0647680014371872 ,
127+ 0.03167999908328056 ,
128+ 0.028255999088287354 ,
129+ 0.025280000641942024 ,
130+ 0.027103999629616737 ,
131+ 0.02550400048494339 ,
132+ 0.02489599958062172
133+ ],
134+ "compile_time" : 449.13655519485474 ,
135+ "verification_time" : 0 ,
136+ "benchmark_time" : 1.1196956038475037 ,
137+ "strategy_time" : 0 ,
138+ "framework_time" : 1.5890561044216156 ,
139+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
140+ },
141+ "512" : {
142+ "block_size_x" : 512 ,
143+ "time" : 0.04139885599059718 ,
144+ "times" : [
145+ 0.13023999333381653 ,
146+ 0.031136000528931618 ,
147+ 0.02831999957561493 ,
148+ 0.02595200017094612 ,
149+ 0.024607999250292778 ,
150+ 0.025151999667286873 ,
151+ 0.024383999407291412
152+ ],
153+ "compile_time" : 440.5844733119011 ,
154+ "verification_time" : 0 ,
155+ "benchmark_time" : 1.09076127409935 ,
156+ "strategy_time" : 0 ,
157+ "framework_time" : 1.853298395872116 ,
158+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
159+ },
160+ "576" : {
161+ "block_size_x" : 576 ,
162+ "time" : 0.04189257137477398 ,
163+ "times" : [
164+ 0.12995199859142303 ,
165+ 0.03200000151991844 ,
166+ 0.028511999174952507 ,
167+ 0.026623999699950218 ,
168+ 0.025760000571608543 ,
169+ 0.02537599951028824 ,
170+ 0.02502400055527687
171+ ],
172+ "compile_time" : 442.16764718294144 ,
173+ "verification_time" : 0 ,
174+ "benchmark_time" : 1.1038780212402344 ,
175+ "strategy_time" : 0 ,
176+ "framework_time" : 1.8403716385364532 ,
177+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
178+ },
179+ "640" : {
180+ "block_size_x" : 640 ,
181+ "time" : 0.0411702852163996 ,
182+ "times" : [
183+ 0.12796799838542938 ,
184+ 0.03081599995493889 ,
185+ 0.02969600073993206 ,
186+ 0.025439999997615814 ,
187+ 0.02409599907696247 ,
188+ 0.02582399919629097 ,
189+ 0.024351999163627625
190+ ],
191+ "compile_time" : 437.98910081386566 ,
192+ "verification_time" : 0 ,
193+ "benchmark_time" : 1.0496266186237335 ,
194+ "strategy_time" : 0 ,
195+ "framework_time" : 1.8264725804328918 ,
196+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
197+ },
198+ "704" : {
199+ "block_size_x" : 704 ,
200+ "time" : 0.04184228580977235 ,
201+ "times" : [
202+ 0.1343040019273758 ,
203+ 0.03094400092959404 ,
204+ 0.02908799983561039 ,
205+ 0.025151999667286873 ,
206+ 0.02486399933695793 ,
207+ 0.024447999894618988 ,
208+ 0.02409599907696247
209+ ],
210+ "compile_time" : 443.51235404610634 ,
211+ "verification_time" : 0 ,
212+ "benchmark_time" : 1.1033527553081512 ,
213+ "strategy_time" : 0 ,
214+ "framework_time" : 1.6709677875041962 ,
215+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
216+ },
217+ "768" : {
218+ "block_size_x" : 768 ,
219+ "time" : 0.03175771422684193 ,
220+ "times" : [
221+ 0.06230400130152702 ,
222+ 0.0315839983522892 ,
223+ 0.02831999957561493 ,
224+ 0.02672000043094158 ,
225+ 0.023679999634623528 ,
226+ 0.023903999477624893 ,
227+ 0.02579200081527233
228+ ],
229+ "compile_time" : 450.4409395158291 ,
230+ "verification_time" : 0 ,
231+ "benchmark_time" : 1.101326197385788 ,
232+ "strategy_time" : 0 ,
233+ "framework_time" : 1.7531625926494598 ,
234+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
235+ },
236+ "832" : {
237+ "block_size_x" : 832 ,
238+ "time" : 0.040941715240478516 ,
239+ "times" : [
240+ 0.12998400628566742 ,
241+ 0.03094400092959404 ,
242+ 0.027103999629616737 ,
243+ 0.024768000468611717 ,
244+ 0.025439999997615814 ,
245+ 0.023903999477624893 ,
246+ 0.024447999894618988
247+ ],
248+ "compile_time" : 439.9200603365898 ,
249+ "verification_time" : 0 ,
250+ "benchmark_time" : 1.0421127080917358 ,
251+ "strategy_time" : 0 ,
252+ "framework_time" : 2.1368376910686493 ,
253+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
254+ },
255+ "896" : {
256+ "block_size_x" : 896 ,
257+ "time" : 0.04177371359297207 ,
258+ "times" : [
259+ 0.12931199371814728 ,
260+ 0.03731200098991394 ,
261+ 0.02812799997627735 ,
262+ 0.02502400055527687 ,
263+ 0.02412799932062626 ,
264+ 0.024768000468611717 ,
265+ 0.023744000121951103
266+ ],
267+ "compile_time" : 439.23527002334595 ,
268+ "verification_time" : 0 ,
269+ "benchmark_time" : 1.0946877300739288 ,
270+ "strategy_time" : 0 ,
271+ "framework_time" : 2.03637033700943 ,
272+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
273+ },
274+ "960" : {
275+ "block_size_x" : 960 ,
276+ "time" : 0.042189714631864 ,
277+ "times" : [
278+ 0.1335040032863617 ,
279+ 0.031039999797940254 ,
280+ 0.02876799926161766 ,
281+ 0.02579200081527233 ,
282+ 0.025119999423623085 ,
283+ 0.02566399984061718 ,
284+ 0.025439999997615814
285+ ],
286+ "compile_time" : 441.7596235871315 ,
287+ "verification_time" : 0 ,
288+ "benchmark_time" : 1.1166557669639587 ,
289+ "strategy_time" : 0 ,
290+ "framework_time" : 1.7383433878421783 ,
291+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
292+ },
293+ "1024" : {
294+ "block_size_x" : 1024 ,
295+ "time" : 0.04114742816558906 ,
296+ "times" : [
297+ 0.13087999820709229 ,
298+ 0.03049599938094616 ,
299+ 0.027936000376939774 ,
300+ 0.02486399933695793 ,
301+ 0.0244159996509552 ,
302+ 0.024320000782608986 ,
303+ 0.025119999423623085
304+ ],
305+ "compile_time" : 442.8337663412094 ,
306+ "verification_time" : 0 ,
307+ "benchmark_time" : 1.0683201253414154 ,
308+ "strategy_time" : 0 ,
309+ "framework_time" : 1.9918642938137054 ,
310+ "timestamp" : " 2022-12-23 12:11:26.411558+00:00"
311+ }
312+ }
313+ }
0 commit comments