AbstractPhil commited on
Commit
c9b973c
·
verified ·
1 Parent(s): 087391f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md CHANGED
@@ -136,4 +136,89 @@ done.
136
  All pass: True
137
  Compiled: 0.72× vs cuSOLVER
138
  ========================================================================
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
  ```
 
136
  All pass: True
137
  Compiled: 0.72× vs cuSOLVER
138
  ========================================================================
139
+ ```
140
+
141
+
142
+
143
+ Testing the barrage setup is reveals much information about parallel processing capacity.
144
+
145
+ ```
146
+ ==============================================================================
147
+ Diagnostic: Parallel Root-Finding
148
+ ==============================================================================
149
+ B=512 N=6
150
+ True eigenvalue range: [-2.106, 2.099]
151
+ Diagonal init range: [-1.561, 1.722]
152
+
153
+ --- Test 1: Pure Laguerre (no Aberth) ---
154
+ PurL it= 0 max_err=1.75e+00 min_gap=1.73e-06 |p(z)|=3.93e+00
155
+ PurL it= 1 max_err=1.84e+00 min_gap=1.67e-16 |p(z)|=5.39e-01
156
+ PurL it= 2 max_err=1.89e+00 min_gap=0.00e+00 |p(z)|=2.01e-02
157
+ PurL it= 3 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=1.73e-04
158
+ PurL it= 4 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=7.12e-07
159
+ PurL it= 9 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
160
+ PurL it=14 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
161
+ PurL it=19 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
162
+
163
+ --- Test 2: Laguerre + Aberth (full) ---
164
+ LA-F it= 0 max_err=1.03e+02 min_gap=5.69e-07 |p(z)|=1.33e+12
165
+ LA-F it= 1 max_err=3.70e+02 min_gap=1.71e-06 |p(z)|=2.62e+15
166
+ LA-F it= 2 max_err=4.63e+02 min_gap=5.12e-06 |p(z)|=1.00e+16
167
+ LA-F it= 3 max_err=1.58e+03 min_gap=1.54e-05 |p(z)|=1.59e+19
168
+ LA-F it= 4 max_err=1.98e+03 min_gap=4.61e-05 |p(z)|=6.05e+19
169
+ LA-F it= 9 max_err=6.05e+03 min_gap=5.26e-04 |p(z)|=4.89e+22
170
+ LA-F it=14 max_err=1.85e+04 min_gap=8.50e-04 |p(z)|=3.95e+25
171
+ LA-F it=19 max_err=5.63e+04 min_gap=1.92e-02 |p(z)|=3.19e+28
172
+
173
+ --- Test 3: Laguerre + weak Aberth (0.1x) ---
174
+ LA.1 it= 0 max_err=2.89e+01 min_gap=5.69e-05 |p(z)|=7.50e+08
175
+ LA.1 it= 1 max_err=2.09e+01 min_gap=2.84e-06 |p(z)|=1.23e+08
176
+ LA.1 it= 2 max_err=1.35e+01 min_gap=6.74e-07 |p(z)|=1.06e+07
177
+ LA.1 it= 3 max_err=6.44e+00 min_gap=4.80e-08 |p(z)|=2.25e+05
178
+ LA.1 it= 4 max_err=1.89e+00 min_gap=4.16e-09 |p(z)|=1.99e+01
179
+ LA.1 it= 9 max_err=1.90e+00 min_gap=1.45e-14 |p(z)|=4.90e-03
180
+ LA.1 it=14 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=6.48e-04
181
+ LA.1 it=19 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=8.53e-05
182
+
183
+ --- Test 4: Pure Laguerre + re-sort ---
184
+ PL+S it= 0 max_err=1.75e+00 min_gap=1.73e-06 |p(z)|=3.93e+00
185
+ PL+S it= 1 max_err=1.84e+00 min_gap=1.67e-16 |p(z)|=5.39e-01
186
+ PL+S it= 2 max_err=1.89e+00 min_gap=0.00e+00 |p(z)|=2.01e-02
187
+ PL+S it= 3 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=1.73e-04
188
+ PL+S it= 4 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=7.12e-07
189
+ PL+S it= 9 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
190
+ PL+S it=14 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
191
+ PL+S it=19 max_err=1.90e+00 min_gap=0.00e+00 |p(z)|=2.88e-15
192
+
193
+ --- Test 5: Laguerre + Aberth damped (0.1 → 1.0) ---
194
+ LADa it= 0 max_err=2.89e+01 min_gap=5.69e-05 |p(z)|=7.50e+08
195
+ LADa it= 1 max_err=3.72e+02 min_gap=3.82e-06 |p(z)|=2.69e+15
196
+ LADa it= 2 max_err=1.13e+03 min_gap=4.82e-06 |p(z)|=2.08e+18
197
+ LADa it= 3 max_err=2.26e+03 min_gap=1.90e-06 |p(z)|=1.34e+20
198
+ LADa it= 4 max_err=3.77e+03 min_gap=9.02e-07 |p(z)|=2.88e+21
199
+ LADa it= 9 max_err=1.70e+04 min_gap=2.34e-05 |p(z)|=2.38e+25
200
+ LADa it=14 max_err=5.17e+04 min_gap=2.25e-03 |p(z)|=1.91e+28
201
+ LADa it=19 max_err=1.58e+05 min_gap=8.72e-03 |p(z)|=1.54e+31
202
+
203
+ --- Test 6: Newton + Aberth ---
204
+ NwAb it= 0 max_err=4.35e+02 min_gap=3.29e-05 |p(z)|=6.91e+15
205
+ NwAb it= 1 max_err=1.57e+01 min_gap=9.86e-05 |p(z)|=2.43e+07
206
+ NwAb it= 2 max_err=5.28e+01 min_gap=1.70e-05 |p(z)|=2.54e+10
207
+ NwAb it= 3 max_err=5.37e+01 min_gap=5.22e-05 |p(z)|=2.75e+10
208
+ NwAb it= 4 max_err=3.34e+02 min_gap=1.91e-04 |p(z)|=1.41e+15
209
+ NwAb it= 9 max_err=2.02e+00 min_gap=1.92e-02 |p(z)|=6.78e+02
210
+ NwAb it=14 max_err=1.05e-06 min_gap=1.92e-02 |p(z)|=1.24e-14
211
+ NwAb it=19 max_err=1.05e-06 min_gap=1.92e-02 |p(z)|=1.24e-14
212
+
213
+ --- Test 7: Pure Newton ---
214
+ PurN it= 0 max_err=3.51e+02 min_gap=6.24e-06 |p(z)|=1.93e+15
215
+ PurN it= 1 max_err=2.93e+02 min_gap=1.69e-09 |p(z)|=6.46e+14
216
+ PurN it= 2 max_err=2.44e+02 min_gap=0.00e+00 |p(z)|=2.16e+14
217
+ PurN it= 3 max_err=2.03e+02 min_gap=0.00e+00 |p(z)|=7.25e+13
218
+ PurN it= 4 max_err=1.69e+02 min_gap=0.00e+00 |p(z)|=2.43e+13
219
+ PurN it= 9 max_err=6.69e+01 min_gap=0.00e+00 |p(z)|=1.02e+11
220
+ PurN it=14 max_err=2.60e+01 min_gap=0.00e+00 |p(z)|=4.31e+08
221
+ PurN it=19 max_err=9.63e+00 min_gap=0.00e+00 |p(z)|=1.81e+06
222
+ ==============================================================================
223
+
224
  ```