@@ -190,48 +190,50 @@ <h1><a class="anchor" id="autotoc_md71"></a>
190190< tr class ="markdownTableRowOdd ">
191191< td class ="markdownTableBodyRight "> AMD EPYC 7763 </ td > < td class ="markdownTableBodyRight "> Milan </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 64 cores </ td > < td class ="markdownTableBodyRight "> 4.1 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4.0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
192192< tr class ="markdownTableRowEven ">
193- < td class ="markdownTableBodyRight "> NVIDIA A10 </ td > < td class ="markdownTableBodyRight "> FP32-only GPU </ td > < td class ="markdownTableBodyRight "> GPU </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 4.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> TAMU Faster </ td > </ tr >
193+ < td class ="markdownTableBodyRight "> Intel Xeon 6740E </ td > < td class ="markdownTableBodyRight "> Sierra Forest </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 92 cores </ td > < td class ="markdownTableBodyRight "> 4.2 </ td > < td class ="markdownTableBodyLeft "> Intel 2024.2 </ td > < td class ="markdownTableBodyLeft "> Intel AI Cloud </ td > </ tr >
194194< tr class ="markdownTableRowOdd ">
195- < td class ="markdownTableBodyRight "> AMD EPYC 7713 </ td > < td class ="markdownTableBodyRight "> Milan </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 64 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
195+ < td class ="markdownTableBodyRight "> NVIDIA A10 </ td > < td class ="markdownTableBodyRight "> FP32-only GPU </ td > < td class ="markdownTableBodyRight "> GPU </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 4.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> TAMU Faster </ td > </ tr >
196196< tr class ="markdownTableRowEven ">
197- < td class ="markdownTableBodyRight "> Intel Xeon 8480CL </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 56 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
197+ < td class ="markdownTableBodyRight "> AMD EPYC 7713 </ td > < td class ="markdownTableBodyRight "> Milan </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 64 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
198198< tr class ="markdownTableRowOdd ">
199- < td class ="markdownTableBodyRight "> Intel Xeon 6454S </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 5.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
199+ < td class ="markdownTableBodyRight "> Intel Xeon 8480CL </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 56 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
200200< tr class ="markdownTableRowEven ">
201- < td class ="markdownTableBodyRight "> Intel Xeon 8462Y+ </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.2 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
201+ < td class ="markdownTableBodyRight "> Intel Xeon 6454S </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 5.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
202202< tr class ="markdownTableRowOdd ">
203- < td class ="markdownTableBodyRight "> Intel Xeon 6548Y + </ td > < td class ="markdownTableBodyRight "> Emerald Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> Intel 2021.9 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
203+ < td class ="markdownTableBodyRight "> Intel Xeon 8462Y + </ td > < td class ="markdownTableBodyRight "> Sapphire Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.2 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
204204< tr class ="markdownTableRowEven ">
205- < td class ="markdownTableBodyRight "> Intel Xeon 8352Y </ td > < td class ="markdownTableBodyRight "> Ice Lake </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
205+ < td class ="markdownTableBodyRight "> Intel Xeon 6548Y+ </ td > < td class ="markdownTableBodyRight "> Emerald Rapids </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> Intel 2021.9 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
206206< tr class ="markdownTableRowOdd ">
207- < td class ="markdownTableBodyRight "> Ampere Altra Q80-28 </ td > < td class ="markdownTableBodyRight "> Arm, Neoverse-N1 </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 80 cores </ td > < td class ="markdownTableBodyRight "> 6.8 </ td > < td class ="markdownTableBodyLeft "> GNU 12.2.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
207+ < td class ="markdownTableBodyRight "> Intel Xeon 8352Y </ td > < td class ="markdownTableBodyRight "> Ice Lake </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
208208< tr class ="markdownTableRowEven ">
209- < td class ="markdownTableBodyRight "> AMD EPYC 7513 </ td > < td class ="markdownTableBodyRight "> Milan </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 7.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
209+ < td class ="markdownTableBodyRight "> Ampere Altra Q80-28 </ td > < td class ="markdownTableBodyRight "> Arm, Neoverse-N1 </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 80 cores </ td > < td class ="markdownTableBodyRight "> 6.8 </ td > < td class ="markdownTableBodyLeft "> GNU 12.2 .0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
210210< tr class ="markdownTableRowOdd ">
211- < td class ="markdownTableBodyRight "> AMD EPYC 7452 </ td > < td class ="markdownTableBodyRight "> Rome </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 8 .4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
211+ < td class ="markdownTableBodyRight "> AMD EPYC 7513 </ td > < td class ="markdownTableBodyRight "> Milan </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 7 .4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
212212< tr class ="markdownTableRowEven ">
213- < td class ="markdownTableBodyRight "> NVIDIA T4 </ td > < td class ="markdownTableBodyRight "> FP32-only GPU </ td > < td class ="markdownTableBodyRight "> GPU </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 8.8 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> TAMU Faster </ td > </ tr >
213+ < td class ="markdownTableBodyRight "> AMD EPYC 7452 </ td > < td class ="markdownTableBodyRight "> Rome </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 8.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
214214< tr class ="markdownTableRowOdd ">
215- < td class ="markdownTableBodyRight "> IBM Power10 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 24 cores </ td > < td class ="markdownTableBodyRight "> 10 </ td > < td class ="markdownTableBodyLeft "> GNU 13.3. 1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
215+ < td class ="markdownTableBodyRight "> NVIDIA T4 </ td > < td class ="markdownTableBodyRight "> FP32-only GPU </ td > < td class ="markdownTableBodyRight "> GPU </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 8.8 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24. 1 </ td > < td class ="markdownTableBodyLeft "> TAMU Faster </ td > </ tr >
216216< tr class ="markdownTableRowEven ">
217- < td class ="markdownTableBodyRight "> AMD EPYC 7401 </ td > < td class ="markdownTableBodyRight "> Naples </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 24 cores </ td > < td class ="markdownTableBodyRight "> 10 </ td > < td class ="markdownTableBodyLeft "> GNU 10 .3.1 </ td > < td class ="markdownTableBodyLeft "> LLNL Corona </ td > </ tr >
217+ < td class ="markdownTableBodyRight "> IBM Power10 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 24 cores </ td > < td class ="markdownTableBodyRight "> 10 </ td > < td class ="markdownTableBodyLeft "> GNU 13 .3.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
218218< tr class ="markdownTableRowOdd ">
219- < td class ="markdownTableBodyRight "> Intel Xeon 6226 </ td > < td class ="markdownTableBodyRight "> Cascade Lake </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 12 cores </ td > < td class ="markdownTableBodyRight "> 17 </ td > < td class ="markdownTableBodyLeft "> GNU 12 .3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
219+ < td class ="markdownTableBodyRight "> AMD EPYC 7401 </ td > < td class ="markdownTableBodyRight "> Naples </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 24 cores </ td > < td class ="markdownTableBodyRight "> 10 </ td > < td class ="markdownTableBodyLeft "> GNU 10 .3.1 </ td > < td class ="markdownTableBodyLeft "> LLNL Corona </ td > </ tr >
220220< tr class ="markdownTableRowEven ">
221- < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 10 cores </ td > < td class ="markdownTableBodyRight "> 20 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
221+ < td class ="markdownTableBodyRight "> Intel Xeon 6226 </ td > < td class ="markdownTableBodyRight "> Cascade Lake </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 12 cores </ td > < td class ="markdownTableBodyRight "> 17 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
222222< tr class ="markdownTableRowOdd ">
223- < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 20 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 9 .1.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
223+ < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 10 cores </ td > < td class ="markdownTableBodyRight "> 20 </ td > < td class ="markdownTableBodyLeft "> GNU 14 .1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
224224< tr class ="markdownTableRowEven ">
225- < td class ="markdownTableBodyRight "> Cavium ThunderX2 </ td > < td class ="markdownTableBodyRight "> Arm </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 13.2 .0 </ td > < td class ="markdownTableBodyLeft "> SBU Ookami </ td > </ tr >
225+ < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 20 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 9.1 .0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
226226< tr class ="markdownTableRowOdd ">
227- < td class ="markdownTableBodyRight "> Arm Cortex-A78AE </ td > < td class ="markdownTableBodyRight "> Arm, BlueField3 </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 16 cores </ td > < td class ="markdownTableBodyRight "> 25 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
227+ < td class ="markdownTableBodyRight "> Cavium ThunderX2 </ td > < td class ="markdownTableBodyRight "> Arm </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 32 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 13.2.0 </ td > < td class ="markdownTableBodyLeft "> SBU Ookami </ td > </ tr >
228228< tr class ="markdownTableRowEven ">
229- < td class ="markdownTableBodyRight "> Intel Xeon E5-2650V4 </ td > < td class ="markdownTableBodyRight "> Broadwell </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 12 cores </ td > < td class ="markdownTableBodyRight "> 27 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23 .5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
229+ < td class ="markdownTableBodyRight "> Arm Cortex-A78AE </ td > < td class ="markdownTableBodyRight "> Arm, BlueField3 </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 16 cores </ td > < td class ="markdownTableBodyRight "> 25 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24 .5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
230230< tr class ="markdownTableRowOdd ">
231- < td class ="markdownTableBodyRight "> Apple M2 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 8 cores </ td > < td class ="markdownTableBodyRight "> 32 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
231+ < td class ="markdownTableBodyRight "> Intel Xeon E5-2650V4 </ td > < td class ="markdownTableBodyRight "> Broadwell </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 12 cores </ td > < td class ="markdownTableBodyRight "> 27 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
232232< tr class ="markdownTableRowEven ">
233- < td class ="markdownTableBodyRight "> Intel Xeon E7-4850V3 </ td > < td class ="markdownTableBodyRight "> Haswell </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 14 cores </ td > < td class ="markdownTableBodyRight "> 34 </ td > < td class ="markdownTableBodyLeft "> GNU 9.4 .0 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
233+ < td class ="markdownTableBodyRight "> Apple M2 </ td > < td class ="markdownTableBodyRight "> </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 8 cores </ td > < td class ="markdownTableBodyRight "> 32 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
234234< tr class ="markdownTableRowOdd ">
235+ < td class ="markdownTableBodyRight "> Intel Xeon E7-4850V3 </ td > < td class ="markdownTableBodyRight "> Haswell </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 14 cores </ td > < td class ="markdownTableBodyRight "> 34 </ td > < td class ="markdownTableBodyLeft "> GNU 9.4.0 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
236+ < tr class ="markdownTableRowEven ">
235237< td class ="markdownTableBodyRight "> Fujitsu A64FX </ td > < td class ="markdownTableBodyRight "> Arm </ td > < td class ="markdownTableBodyRight "> CPU </ td > < td class ="markdownTableBodyRight "> 48 cores </ td > < td class ="markdownTableBodyRight "> 63 </ td > < td class ="markdownTableBodyLeft "> GNU 13.2.0 </ td > < td class ="markdownTableBodyLeft "> SBU Ookami </ td > </ tr >
236238</ table >
237239< 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