New parameters set and simplify sub-parameters add new parameters ie. 7z st for stability test (burn-in test) sub-parameters ie. default (batch test: multi-thread zip compression, RAM bandwidth test( Large block size, Max CPU thread) or etc), all (batch test: multi-thread zip compression, CPU Cache & RAM bandwidth test( Small/Large block size, Max CPU thread) or etc), custom number of threads, time length and etc.
New parameters set and simplify sub-parameters add new parameters ie. 7z -st for stability test (burn-in test) sub-parameters ie. default (batch test: multi-thread zip compression, RAM bandwidth test( Large block size, Max CPU thread) or etc), all (batch test: multi-thread zip compression, CPU Cache & RAM bandwidth test( Small/Large block size, Max CPU thread) or etc), custom number of threads, time length and etc.
New parameters set and simplify sub-parameters add new parameters ie. 7z -st for stability test (burn-in test) sub-parameters ie. default, all, test max thread only, time length and etc
New parameters set and simplify sub-parameters add new parameters ie. 7z -st for stability test sub-parameters ie. default, all, test max thread only, time length and etc
I know your multi-thread zip compression can get Max TDC and EDC (source file cached from RAM), RAM bandwidth test can get 3x+ current difference from TDC/EDC(MAX EDC), Don't have create 7z Stability Test Mode idea?
I know your zip compression can get Max TDC and EDC (source file cached from RAM), RAM bandwidth test can get 3x+ current difference from TDC/EDC(MAX EDC), Don't have create 7z Stability Test Mode idea?
12900KS 1.25MB L2+30MB L3 = 31.2MB (Little bottleneck?) 5900x 512KB L2+32MB L3 = 32.5MB ( single CCD) or 64.5MB (across each CCD?) If use 64MB Dict, R9 is access another CCD L3 or RAM? R9 5900x 64MB Dict, 1T, 1Pass Compressing 5205KB/s 6.343 GIPS Decompressing 116270KB/s 10.490 GIPS (Fast than 12900KS 32MB Dict XD)
12900KS 14MB L2+30MB L3 = 44MB Large than 32MB Dict (no bottleneck?) 5900x 512KB L2+32MB L3 = 32.5MB ( single CCD) or 64.5MB (across each CCD?) If use 64MB Dict, R9 is access another CCD L3 or RAM? R9 5900x 64MB Dict, 1T, 1Pass Compressing 5205KB/s 6.343 GIPS Decompressing 116270KB/s 10.490 GIPS (Fast than 12900KS 32MB Dict XD)
12900KS 14MB L2+30MB L3 = 44MB Large than 32MB Dict (no bottleneck?) 5900x 512KB L2+32MB L3 = 32.5MB ( single CCD) or 64.5MB (across each CCD?) If use 64MB Dict, R9 is access another CCD L3 or RAM? R9 5900x 64MB Dict, 1T, 1Pass Compressing 5205KB/s 6.343 GIPS Decompressing 116270KB/s 10.490 GIPS
12900KS 14MB L2+30MB L3 = 44MB Large than 32MB Dict (no bottleneck?) 5900x 512KB L2+32MB L3 = 32.5MB ( single CCD) or 64.5MB (across each CCD?)
Why 12900KS Core performance slow than Zen3??? 12900KS source: intel https://twitter.com/IntelTech/status/1478079758898446337 7Z Settings:32MB 1T 1Pass 12900KS 5.5G(1T) 6 IPC? DDR5? Compressing 6143KB/s 7.014 GIPS Decompressing 112980KB/s 10.055 GIPS My R9 5900x(stock, no OC) 4.95G?(1T Max Precision boost) 4 IPC? DDR4 (7z 21.07 Win11) Compressing 6531KB/s 7.451 GIPS Decompressing 119000KB/s 10.592 GIPS My Zen3 CPU Fast than 12th gen core? (Compress and Decompress too) XDXDXDXDXDXDXDXDXDXDXDXDXDX...
Why 12900KS Core performance slow than Zen3??? 12900KS source: intel https://twitter.com/IntelTech/status/1478079758898446337 7Z Settings:32MB 1T 1Pass 12900KS 14MB L2+30MB L3 = 44MB Large than 32MB Dict (no bottleneck) 5900x 512KB L2+32MB L3 = 32.5MB ( single CCD) or 64.5MB (across each CCD?) 12900KS 5.5G(1T) 6 IPC? DDR5? Compressing 6143KB/s 7.014 GIPS Decompressing 112980KB/s 10.055 GIPS My R9 5900x(stock, no OC) 4.95G?(1T Max Precision boost) 4 IPC? DDR4 (7z 21.07 Win11) Compressing 6531KB/s...
Why 12900KS Core performance slow than Zen3??? 12900KS source: intel https://twitter.com/IntelTech/status/1478079758898446337 7Z Settings:32MB 1T 1Pass 12900KS 5.5G(1T) 6 IPC? DDR5? Compressing 6143KB/s 7.014 GIPS Decompressing 112980KB/s 10.055 GIPS My R9 5900x(stock, no OC) 4.95G?(1T Max Precision boost) 4 IPC? DDR4 (7z 21.07 Win11) Compressing 6531KB/s 7.451 GIPS Decompressing 119000KB/s 10.592 GIPS My Zen3 CPU Fast than 12th gen core? (Compress and Decompress too) XDXDXDXDXDXDXDXDXDXDXDXDXDX...
Why 12900KS Core performance slow than Zen3??? 12900KS source: intel https://twitter.com/IntelTech/status/1478079758898446337 7Z Settings:32MB 1T 1Pass 12900KS 5.5G(1T) 6 IPC? DDR5? Compressing 6143KB/s 7.014 GIPS Decompressing 112980KB/s 10.055 GIPS My R9 5900x(stock, no OC) 4.95G(1T Max Precision boost) 4 IPC? DDR4 (7z 21.07 Win11) Compressing 6531KB/s 7.451 GIPS Decompressing 119000KB/s 10.592 GIPS My Zen3 CPU Fast than 12th gen core? (Compress and Decompress too) XDXDXDXDXDXDXDXDXDXDXDXDXDXD...
Why 12900KS Core performance slow than Zen3??? 12900KS source: intel https://twitter.com/IntelTech/status/1478079758898446337 7Z Settings:32MB 1T 1Pass 12900KS 5.5G(1T) 6 IPC? DDR5? Compressing 6143KB/s 7.014 GIPS Decompressing 112980KB/s 10.055 GIPS My R9 5900x(stock, no OC) 4.95G(1T Max Precision boost) 4 IPC? DDR4 Compressing 6531KB/s 7.451 GIPS Decompressing 119000KB/s 10.592 GIPS My Zen3 CPU Fast than 12th gen core? (Compress and Decompress too) XDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDXDX...
Uncompressed data 1700 uncompressed data log(HP Plan).txt 1700 uncompressed data log(Balanced Plan).txt 1700 uncompressed data log(HP Plan - CPU0246).txt
Ryzen 1700 (DDR4 2666, dual channel) Windows 10 x64 (15063.608) HDD 1700 log(HP Plan).txt High Performance power plan 1700 log(Balanced Plan).txt Balanced power plan 1700 log(HP Plan - CPU0246).txt High Performance power plan CPU affinity: CPU0, CPU2, CPU4, CPU6 (cmd.exe)
Ryzen Windows 10 Pro x64 1703 7zip 17.00 x64, parameters:7z,Ultra,LZMA2,64MB,128,4GB,3/16 threads HWiNFO64 Sensors: CPU (Tctl/Tdie) CPU Core Voltage SoC Voltage CPU Core Current SoC Current CPU Package Power Core #0 Power Core #1 Power Core #2 Power Core #3 Power Core #4 Power Core #5 Power Core #6 Power Core #7 Power CPU Core Power SoC Power CPU +SoC Power
Total time: 2:41 Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU2,CPU8,CPU10
Total time: 2:40 Max Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU8 parameters:7z,Ultra,LZMA2,64MB,128,4GB,2/16 threads Conclusion #2: frequency advantage+8M L3 cache/each thread equal to 3 thread performance = =;
Total time: 2:54 Max Precision Boost Balanced Power Plan Processor affinity(7zG.exe): CPU0,CPU2 parameters:7z,Ultra,LZMA2,64MB,128,4GB,2/16 threads Conclusion #3: 2T(2:54) performance is same as 3T(2:55) on 2C4T environment = =;;
Total time: 2:40 Max Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU8 parameters:7z,Ultra,LZMA2,64MB,128,4GB,2/16 threads Conclusion #2: frequency advantage+8M L3 cache/each thread equal to 3 thread performance = =;
Total time: 2:41 Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU2,CPU8,CPU10
Total time: 2:42 Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU2,CPU4
Total time: 2:42 Precision Boost High Performance Power Plan Processor affinity(7zG.exe): CPU0,CPU1,CPU2,CPU3,CPU4,CPU5 Conclusion #1: SMT+frequency advantage can't better than one physical core :(
Total time: 2:56 Max Precision Boost Balanced Power Plan Processor affinity(7zG.exe): CPU1,CPU2,CPU3
Total time: 2:55 Max Precision Boost Balanced Power Plan Processor affinity(7zG.exe): all
Ryzen HWiNFO64 Windows 10 Pro x64 1703 7zip 17.00 x64, parameters:7z,Ultra,LZMA2,64MB,128,4GB,3/16 threads
My system work fine (except 7zip LargePages I run PRIME95 x64 w/LargePages, Blend stress test(custom1 thread ) but no bsod or error = =;;;
You are right, but I can't cancel this operation, click cancel box again n again,no effect. bad experience :(
Larger executable compression fail on LZMA2 4 threads or above https://www.geforce.com/games-applications/pc-applications/a-new-dawn ~2xxMB EXE use 4 threads LZMA2 compression no problem 5xxMB/7xxMB EXE use 1~3 threads LZMA2 compression no problem 5xxMB/7xxMB EXE use 4+ threads LZMA2 compression fail 1~4GB ISO use 4+ threads LZMA2 compression no problem Ryzen Windows 10 Pro x64 1703 7zip 17.00 x64, parameters:7z,Ultra,LZMA2,64MB,64,4GB,4/16 threads
Larger executable compression fail on LZMA2 4 threads or above https://www.geforce.com/games-applications/pc-applications/a-new-dawn ~2xxMB EXE use 4 threads LZMA2 compression no problem 5xxMB/7xxMB EXE use 1~3 threads LZMA2 compression no problem 5xxMB/7xxMB EXE use 4+ threads LZMA2 compression fail Ryzen Windows 10 Pro x64 1703 7zip 17.00 x64, parameters:7z,Ultra,LZMA2,64MB,64,4GB,4/16 threads
World why like to shirk responsibility, amd/asrock not confirm it? I trust your program, Please say "this problem is not with your program, is Ryzen or Windows problem" External link1:https://community.amd.com/thread/216049 External link2:http://forum.asrock.com/forum_posts.asp?TID=5388&title=ryzen-large-pages-not-compatible-on-windows-10 PS:eng is not my native lang The BSOD Gift from Ryzen~~~~~~~~~
World why like to shirk responsibility, not confirm it? Please say "this problem is not with you program, is Ryzen or Windows problem" External link1:https://community.amd.com/thread/216049 External link2:http://forum.asrock.com/forum_posts.asp?TID=5388&title=ryzen-large-pages-not-compatible-on-windows-10 PS:eng is not my native lang The BSOD Gift from Ryzen~~~~~~~~~
World why like to shirk responsibility, not confirm it? Please say "this problem is not with you program, is Ryzen or Windows problem" External link1:https://community.amd.com/thread/216049 External link2:http://forum.asrock.com/forum_posts.asp?TID=5388&title=ryzen-large-pages-not-compatible-on-windows-10 PS:eng is not my native lang
World why like to shirk responsibility, not confirm it? Please say "this problem is not with you program, is Ryzen or Windows problem" External link1:https://community.amd.com/thread/216049 External link2:http://forum.asrock.com/forum_posts.asp?TID=5388&title=ryzen-large-pages-not-compatible-on-windows-10 PS:eng is not my native lang
post to amd forum, no response from amd post to asrock forum, tell me to ask 7-zip author
World why like to shirk responsibility, not confirm it? Please say "this problem is not with you program, is Ryzen or Windows problem" External link1:https://community.amd.com/thread/216049 External link2:http://forum.asrock.com/forum_posts.asp?TID=5388&title=ryzen-large-pages-not-compatible-on-windows-10 PS:eng is not my native lang