@@ -151,56 +151,58 @@ <h1><a class="anchor" id="autotoc_md67"></a>
151151< tr class ="markdownTableRowEven ">
152152< td class ="markdownTableBodyRight "> NVIDIA H100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.45 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
153153< tr class ="markdownTableRowOdd ">
154- < td class ="markdownTableBodyRight "> NVIDIA A100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.62 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
154+ < td class ="markdownTableBodyRight "> AMD MI300A </ td > < td class ="markdownTableBodyRight "> 1 < b > GCD </ b > </ td > < td class ="markdownTableBodyRight "> 0.61 </ td > < td class ="markdownTableBodyLeft "> CCE 18.0.0 </ td > < td class ="markdownTableBodyLeft "> LLNL Tioga </ td > </ tr >
155155< tr class ="markdownTableRowEven ">
156- < td class ="markdownTableBodyRight "> NVIDIA V100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.99 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
156+ < td class ="markdownTableBodyRight "> NVIDIA A100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.62 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
157157< tr class ="markdownTableRowOdd ">
158- < td class ="markdownTableBodyRight "> NVIDIA A30 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.1 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
158+ < td class ="markdownTableBodyRight "> NVIDIA V100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.99 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
159159< tr class ="markdownTableRowEven ">
160- < td class ="markdownTableBodyRight "> AMD MI250X </ td > < td class ="markdownTableBodyRight "> 1 < b > GCD </ b > </ td > < td class ="markdownTableBodyRight "> 1.1 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0. 1 </ td > < td class ="markdownTableBodyLeft "> OLCF Frontier </ td > </ tr >
160+ < td class ="markdownTableBodyRight "> NVIDIA A30 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.1 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24. 1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
161161< tr class ="markdownTableRowOdd ">
162- < td class ="markdownTableBodyRight "> AMD MI100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.4 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> Cray internal system </ td > </ tr >
162+ < td class ="markdownTableBodyRight "> AMD MI250X </ td > < td class ="markdownTableBodyRight "> 1 < b > GCD </ b > </ td > < td class ="markdownTableBodyRight "> 1.1 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> OLCF Frontier </ td > </ tr >
163163< tr class ="markdownTableRowEven ">
164- < td class ="markdownTableBodyRight "> NVIDIA L40S (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.7 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
164+ < td class ="markdownTableBodyRight "> AMD MI100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.4 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> Cray internal system </ td > </ tr >
165165< tr class ="markdownTableRowOdd ">
166- < td class ="markdownTableBodyRight "> NVIDIA P100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 2.4 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23 .5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
166+ < td class ="markdownTableBodyRight "> NVIDIA L40S (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.7 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24 .5 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
167167< tr class ="markdownTableRowEven ">
168- < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 2.7 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
168+ < td class ="markdownTableBodyRight "> NVIDIA P100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 2.4 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
169169< tr class ="markdownTableRowOdd ">
170- < td class ="markdownTableBodyRight "> NVIDIA A40 (SP GPU ) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
170+ < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa ) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 2.7 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
171171< tr class ="markdownTableRowEven ">
172- < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2 ) </ td > < td class ="markdownTableBodyRight "> 72/72 cores </ td > < td class ="markdownTableBodyRight "> 3.7 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
172+ < td class ="markdownTableBodyRight "> NVIDIA A40 (SP GPU ) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
173173< tr class ="markdownTableRowOdd ">
174- < td class ="markdownTableBodyRight "> NVIDIA RTX6000 (SP GPU ) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.9 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
174+ < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2 ) </ td > < td class ="markdownTableBodyRight "> 72/72 cores </ td > < td class ="markdownTableBodyRight "> 3.7 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
175175< tr class ="markdownTableRowEven ">
176- < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan ) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 4.1 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4.0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
176+ < td class ="markdownTableBodyRight "> NVIDIA RTX6000 (SP GPU ) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.9 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
177177< tr class ="markdownTableRowOdd ">
178- < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
178+ < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 4.1 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4 .0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
179179< tr class ="markdownTableRowEven ">
180- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8480CL (Sapphire Rapids ) </ td > < td class ="markdownTableBodyRight "> 56/56 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
180+ < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan ) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
181181< tr class ="markdownTableRowOdd ">
182- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 5.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
182+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8480CL (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 56/56 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
183183< tr class ="markdownTableRowEven ">
184- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y+ (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.2 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
184+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 5.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
185185< tr class ="markdownTableRowOdd ">
186- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6548Y + (Emerald Rapids) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> Intel oneAPI 2021.9 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
186+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y + (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.2 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
187187< tr class ="markdownTableRowEven ">
188- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8352Y (Ice Lake ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
188+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6548Y+ (Emerald Rapids ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> Intel oneAPI 2021.9 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
189189< tr class ="markdownTableRowOdd ">
190- < td class ="markdownTableBodyRight "> Ampere Altra Max Q80-28 (Arm, Neoverse-N1 ) </ td > < td class ="markdownTableBodyRight "> 80/80 cores </ td > < td class ="markdownTableBodyRight "> 6.8 </ td > < td class ="markdownTableBodyLeft "> GNU 12.2.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
190+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8352Y (Ice Lake ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
191191< tr class ="markdownTableRowEven ">
192- < td class ="markdownTableBodyRight "> AMD EPYC 7513 (Milan ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 7.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
192+ < td class ="markdownTableBodyRight "> Ampere Altra Max Q80-28 (Arm, Neoverse-N1 ) </ td > < td class ="markdownTableBodyRight "> 80/80 cores </ td > < td class ="markdownTableBodyRight "> 6.8 </ td > < td class ="markdownTableBodyLeft "> GNU 12.2 .0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
193193< tr class ="markdownTableRowOdd ">
194- < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 8 .4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
194+ < td class ="markdownTableBodyRight "> AMD EPYC 7513 (Milan ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 7 .4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
195195< tr class ="markdownTableRowEven ">
196- < td class ="markdownTableBodyRight "> Apple M1 Pro </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 14 </ td > < td class ="markdownTableBodyLeft "> GNU 13.2 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
196+ < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 8.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
197197< tr class ="markdownTableRowOdd ">
198- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 17 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
198+ < td class ="markdownTableBodyRight "> Apple M1 Pro </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 14 </ td > < td class ="markdownTableBodyLeft "> GNU 13.2 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
199199< tr class ="markdownTableRowEven ">
200- < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 18 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
200+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 17 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
201201< tr class ="markdownTableRowOdd ">
202- < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> 20/21 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 9 .1.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
202+ < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 18 </ td > < td class ="markdownTableBodyLeft "> GNU 14 .1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
203203< tr class ="markdownTableRowEven ">
204+ < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> 20/21 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 9.1.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
205+ < tr class ="markdownTableRowOdd ">
204206< td class ="markdownTableBodyRight "> Intel Xeon E5-2650V4 (Broadwell) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 27 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
205207</ table >
206208< p > < b > All grind times are in nanoseconds (ns) per grid point (gp) per equation (eq) per right-hand side (rhs) evaluation, so X ns/gp/eq/rhs. Lower is better.</ b > </ p >
0 commit comments