Open chendo opened 1 month ago
Hi Thank you very much for your help.
Can you provide screenshots of the Sensors view (Vcore, Power, Temperature) when system is idle; single core stressed; all cores stressed ?
Please use one of the integrated Tools > Atomic
and Tools > Conics
I would like also to check the Memory Controller and other results:
corefreq-cli -k -n -B -n -M
Also various Caches and CPPC
corefreq-cli -m -n -Z
Also some new feature bits are pending in the develop
branch. Can you please show results of corefreq-cli -s -n -m
By the way 7600G
with a G
letter is a very mysterious processor name. I don't find its reference at AMD !
+1
Apologies for late reply, it's been a busy week!
Under Atomic load:
Under Conics load:
# corefreq-cli -k -n -B -n -M
Linux:
|- Release [6.1.106-Unraid]
|- Version [#1 SMP PREEMPT_DYNAMIC Wed Aug 21 23:36:07 PDT 2024]
|- Machine [x86_64]
Memory:
|- Total RAM 31987648 KB
|- Shared RAM 407348 KB
|- Free RAM 28458664 KB
|- Buffer RAM 13424 KB
|- Total High 0 KB
|- Free High 0 KB
Clock Source < hpet>
CPU-Freq driver [ amd-pstate]
Governor [ conservative]
CPU-Idle driver [ Missing]
|- Idle Limit [ N/A]
[ 0] American Megatrends Inc.
[ 1] 3056
[ 2] 10/26/2024
[ 3] ASUS
[ 4] System Product Name
[ 5] System Version
[ 6] S---e---e---l---m---
[ 7] SKU
[ 8] To be filled by O.E.M.
[ 9] ASUSTeK COMPUTER INC.
[10] PRIME X670-P WIFI
[11] Rev 1.xx
[12] 2---3---9---1--
[13] Number Of Devices:4\Maximum Capacity:134217728 kilobytes
[14]
[15] DIMM 1\P0 CHANNEL A
[16]
[17]
[18]
[19] Kingston
[20]
[21]
[22]
[23] 9965794-016.A00G
[24]
[25]
Zen UMC [14E0]
Controller #0 Single Channel
Bus Rate 2400 MHz Bus Speed 2396 MHz DDR5 Speed 4792 MT/s
Cha CL RCDr RCDw RP RAS RC RRDs RRDl FAW WTRs WTRl WR clRR clWW
#0 40 39 39 39 77 116 8 12 32 6 24 72 5 17
CWL RTP RdWr WrRd scWW sdWW ddWW scRR sdRR ddRR drRR drWW drWR drRRD
#0 38 18 20 7 1 9 9 1 9 9 0 0 0 0
REFI RFC1 RFC2 RFCsb RCPB RPPB BGS:Alt Ban Page CKE CMD GDM ECC
#0 9347 312 192 312 0 0 ON OFF R0W0 0 0 1T ON 0
MRD:PDA MOD:PDA WRMPR STAG PDM RDDATA WRD WRL RDL XS XP CPDED
#0 34 32 34 32 24 7 0:F:1 28 6 26 34 732 18 12
DIMM Geometry for channel #0
Slot Bank Rank Rows Columns Memory Size (MB)
#0
#1 32 1 65536 1024 16384 9965794-016.A00G
# corefreq-cli -m -n -Z
CPU Pkg Apic Core/Thread Caches (w)rite-Back (i)nclusive
# ID ID CCD CCX ID/ID L1-Inst Way L1-Data Way L2 Way L3 Way
000:BSP 0 0 0 0 0 32 8 32 8 1024 8 i 32768 16w
001: 0 2 0 0 1 0 32 8 32 8 1024 8 i 32768 16w
002: 0 4 0 0 2 0 32 8 32 8 1024 8 i 32768 16w
003: 0 6 0 0 3 0 32 8 32 8 1024 8 i 32768 16w
004: 0 8 0 1 4 0 32 8 32 8 1024 8 i 32768 16w
005: 0 10 0 1 5 0 32 8 32 8 1024 8 i 32768 16w
006: 0 1 0 0 0 1 32 8 32 8 1024 8 i 32768 16w
007: 0 3 0 0 1 1 32 8 32 8 1024 8 i 32768 16w
008: 0 5 0 0 2 1 32 8 32 8 1024 8 i 32768 16w
009: 0 7 0 0 3 1 32 8 32 8 1024 8 i 32768 16w
010: 0 9 0 1 4 1 32 8 32 8 1024 8 i 32768 16w
011: 0 11 0 1 5 1 32 8 32 8 1024 8 i 32768 16w
CoreFreq. Copyright (C) 2015-2024 CYRIL COURTIAT
Usage: corefreq-cli [-Option <argument>] [-Command <argument>]
Interface options
-Oa Absolute frequency
-Op Show Package C-States
-Ok Memory unit in kilobyte
-Om Memory unit in megabyte
-Og Memory unit in gigabyte
-OW Toggle Energy units
-OF Temperature in Fahrenheit
-OJ # SMBIOS string index number
-OE # Color theme index number
-OY Show Secret Data
Command options
-t <v> Show Top (default) with optional <v>iew:
{ frequency, instructions, core, idle, package, tasks,
interrupts, sensors, voltage, power, slices, custom }
-d Show Dashboard
-C <#> Monitor Sensors
-V <#> Monitor Voltage
-W <#> Monitor Power
-g <#> Monitor Package
-c <#> Monitor Counters
-i <#> Monitor Instructions
-s Print System Information
-j Print System Information (json-encoded)
-z Print Performance Capabilities
-M Print Memory Controller
-R Print System Registers
-m Print Topology
-u Print CPUID
-B Print SMBIOS
-k Print Kernel
-n New line
-h Print out this message
-v Print the version number
Exit status:
0 SUCCESS Successful execution
3 CMD_SYNTAX Command syntax error
4 SHM_FILE Shared memory file error
5 SHM_MMAP Shared memory mapping error
6 PERM_ERR Execution not permitted
7 MEM_ERR Memory operation error
8 EXEC_ERR General execution error
9 SYS_CALL System call error
Report bugs to labs[at]cyring.fr
I'm on Unraid so no easy way for me to get develop
I don't think.
My bad, I thought G
is meant to signify onboard GPU. Could have sworn it was part of the model number at least some generations ago.
Thank you very much
Sorry for the command line mistake to read the CPPC which uses a lower z
corefreq-cli -m -n -z
You may also have noticed the wrong DIMM size decoded
DIMM Geometry for channel #0
Slot Bank Rank Rows Columns Memory Size (MB)
#0
#1 32 1 65536 1024 16384 9965794-016.A00G
Size has to be 32 GB
and according to Kingston datasheet I should have decoded 2
ranks rather than 1
I need to dump your 7600 Memory Controller Registers to understand things about DDR5 based on AMD Family 1A specification 57238_C1_pub_4.pdf chapter 9.3 UMC Registers
I made zencli to read such registers.
Can you please compile and dump those addresses ?
## Compilation
cc zencli.c -o zencli
## Read as root
## (up to 4 theorical channels)
### DRAM Address Configuration
./zencli smu 0x50040
./zencli smu 0x50044
./zencli smu 0x50048
./zencli smu 0x5004c
### DIMM Configuration
./zencli smu 0x50090
./zencli smu 0x50094
### UMC Configuration
./zencli smu 0x50100
### SDP Control
./zencli smu 0x50104
### DRAM ECC Control
./zencli smu 0x5014c
# corefreq-cli -m -n -z
CPU Pkg Apic Core/Thread Caches (w)rite-Back (i)nclusive
# ID ID CCD CCX ID/ID L1-Inst Way L1-Data Way L2 Way L3 Way
000:BSP 0 0 0 0 0 32 8 32 8 1024 8 i 32768 16w
001: 0 2 0 0 1 0 32 8 32 8 1024 8 i 32768 16w
002: 0 4 0 0 2 0 32 8 32 8 1024 8 i 32768 16w
003: 0 6 0 0 3 0 32 8 32 8 1024 8 i 32768 16w
004: 0 8 0 1 4 0 32 8 32 8 1024 8 i 32768 16w
005: 0 10 0 1 5 0 32 8 32 8 1024 8 i 32768 16w
006: 0 1 0 0 0 1 32 8 32 8 1024 8 i 32768 16w
007: 0 3 0 0 1 1 32 8 32 8 1024 8 i 32768 16w
008: 0 5 0 0 2 1 32 8 32 8 1024 8 i 32768 16w
009: 0 7 0 0 3 1 32 8 32 8 1024 8 i 32768 16w
010: 0 9 0 1 4 1 32 8 32 8 1024 8 i 32768 16w
011: 0 11 0 1 5 1 32 8 32 8 1024 8 i 32768 16w
|- Collaborative Processor Performance Control CPPC < ON>
|- Capabilities Lowest Efficient Guaranteed Highest
|- CPU #0 299.35 ( 3) 1895.89 ( 19) 2394.80 ( 24) 3492.42 ( 35)
|- CPU #1 299.36 ( 3) 1895.93 ( 19) 2394.86 ( 24) 3592.30 ( 36)
|- CPU #2 299.44 ( 3) 1896.45 ( 19) 2395.51 ( 24) 3593.26 ( 36)
|- CPU #3 299.37 ( 3) 1895.99 ( 19) 2394.94 ( 24) 3492.62 ( 35)
|- CPU #4 299.37 ( 3) 1896.02 ( 19) 2394.97 ( 24) 3293.08 ( 33)
|- CPU #5 299.44 ( 3) 1896.44 ( 19) 2395.50 ( 24) 3393.63 ( 34)
|- CPU #6 299.40 ( 3) 1896.20 ( 19) 2395.20 ( 24) 3493.00 ( 35)
|- CPU #7 299.40 ( 3) 1896.22 ( 19) 2395.23 ( 24) 3592.84 ( 36)
|- CPU #8 299.44 ( 3) 1896.46 ( 19) 2395.53 ( 24) 3593.30 ( 36)
|- CPU #9 299.41 ( 3) 1896.25 ( 19) 2395.26 ( 24) 3493.09 ( 35)
|- CPU #10 299.41 ( 3) 1896.24 ( 19) 2395.25 ( 24) 3293.47 ( 33)
|- CPU #11 299.44 ( 3) 1896.46 ( 19) 2395.53 ( 24) 3393.67 ( 34)
Yeah, the RAM is meant to be 32GB. I'll have a crack at compiling zencli
another time when I'm not fighting Docker
Thank you.
Fyi, your outputs are listed at Ryzen 5 7600
in the Wiki/CPU-support
Could you please print the CPUID using corefreq-cli -u
The tree of CPU #0
will be enough
_Because I want to decode the CPUID_Fn80000026_ECX_x0[0...3] [Extended CPU Topology]
for CCX enumeration_
CPU #0 function EAX EBX ECX EDX
|- 00000000:00000000 00000010 68747541 444d4163 69746e65
|- Largest Standard Function=00000010
|- 80000000:00000000 80000028 68747541 444d4163 69746e65
|- Largest Extended Function=80000028
|- 00000001:00000000 00a60f12 000c0800 7ed8320b 178bfbff
|- 00000002:00000000 00000000 00000000 00000000 00000000
|- 00000003:00000000 00000000 00000000 00000000 00000000
|- 00000004:00000000 00000000 00000000 00000000 00000000
|- 00000004:00000001 00000000 00000000 00000000 00000000
|- 00000004:00000002 00000000 00000000 00000000 00000000
|- 00000004:00000003 00000000 00000000 00000000 00000000
|- 00000005:00000000 00000040 00000040 00000003 00000011
|- 00000006:00000000 00000004 00000000 00000001 00000000
|- 00000007:00000000 00000001 f1bf97a9 00405fde 10000010
|- 00000007:00000001 00000020 00000000 00000000 00000000
|- 00000007:00000002 00000000 00000000 00000000 00000000
|- 00000009:00000000 00000000 00000000 00000000 00000000
|- 0000000a:00000000 00000000 00000000 00000000 00000000
|- 0000000b:00000000 00000001 00000002 00000100 00000000
|- 0000000d:00000000 000002e7 00000988 00000988 00000000
|- 0000000d:00000001 0000000f 00000988 00001800 00000000
|- 0000000d:00000002 00000100 00000240 00000000 00000000
|- 0000000d:00000003 00000000 00000000 00000000 00000000
|- 0000000d:00000004 00000000 00000000 00000000 00000000
|- 0000000d:00000009 00000008 00000980 00000000 00000000
|- 0000000d:0000000b 00000010 00000000 00000001 00000000
|- 0000000d:0000000c 00000018 00000000 00000001 00000000
|- 0000000d:0000003e 00000000 00000000 00000000 00000000
|- 0000000f:00000000 00000000 000000ff 00000000 00000002
|- 0000000f:00000001 00000014 00000040 000000ff 00000007
|- 00000010:00000000 00000000 00000002 00000000 00000000
|- 00000010:00000001 0000000f 00000000 00000004 0000000f
|- 00000010:00000002 00000000 00000000 00000000 00000000
|- 00000010:00000003 00000000 00000000 00000000 00000000
|- 00000012:00000000 00000000 00000000 00000000 00000000
|- 00000012:00000001 00000000 00000000 00000000 00000000
|- 00000012:00000002 00000000 00000000 00000000 00000000
|- 00000014:00000000 00000000 00000000 00000000 00000000
|- 00000014:00000001 00000000 00000000 00000000 00000000
|- 00000015:00000000 00000000 00000000 00000000 00000000
|- 00000016:00000000 00000000 00000000 00000000 00000000
|- 00000017:00000000 00000000 00000000 00000000 00000000
|- 00000017:00000001 00000000 00000000 00000000 00000000
|- 00000017:00000002 00000000 00000000 00000000 00000000
|- 00000017:00000003 00000000 00000000 00000000 00000000
|- 00000018:00000000 00000000 00000000 00000000 00000000
|- 00000018:00000001 00000000 00000000 00000000 00000000
|- 00000018:00000002 00000000 00000000 00000000 00000000
|- 00000018:00000003 00000000 00000000 00000000 00000000
|- 00000018:00000004 00000000 00000000 00000000 00000000
|- 00000019:00000000 00000000 00000000 00000000 00000000
|- 0000001a:00000000 00000000 00000000 00000000 00000000
|- 0000001b:00000000 00000000 00000000 00000000 00000000
|- 0000001c:00000000 00000000 00000000 00000000 00000000
|- 0000001d:00000000 00000000 00000000 00000000 00000000
|- 0000001d:00000001 00000000 00000000 00000000 00000000
|- 0000001e:00000000 00000000 00000000 00000000 00000000
|- 0000001f:00000000 00000000 00000000 00000000 00000000
|- 00000020:00000000 00000000 00000000 00000000 00000000
|- 00000023:00000000 00000000 00000000 00000000 00000000
|- 00000023:00000001 00000000 00000000 00000000 00000000
|- 00000023:00000002 00000000 00000000 00000000 00000000
|- 00000023:00000003 00000000 00000000 00000000 00000000
|- 80000001:00000000 00a60f12 00000000 75c237ff 2fd3fbff
|- 80000002:00000000 20444d41 657a7952 2035206e 30303637
|- 80000003:00000000 432d3620 2065726f 636f7250 6f737365
|- 80000004:00000000 20202072 20202020 20202020 00202020
|- 80000005:00000000 ff48ff40 ff48ff40 20080140 20080140
|- 80000006:00000000 5c002200 6c004200 04006140 01009140
|- 80000007:00000000 00000000 0000003b 00000000 00006799
|- 80000008:00000000 00003030 791ef257 0000400b 00010000
|- 8000000a:00000000 00000001 00008000 00000000 1ebfbcff
|- 80000019:00000000 f048f040 f0400000 00000000 00000000
|- 8000001a:00000000 00000006 00000000 00000000 00000000
|- 8000001b:00000000 00000bff 00000000 00000000 00000000
|- 8000001c:00000000 00000000 00000000 00000000 00000000
|- 8000001d:00000000 00004121 01c0003f 0000003f 00000000
|- 8000001d:00000001 00004122 01c0003f 0000003f 00000000
|- 8000001d:00000002 00004143 01c0003f 000007ff 00000002
|- 8000001d:00000003 0002c163 03c0003f 00007fff 00000001
|- 8000001d:00000004 00000000 00000000 00000000 00000000
|- 8000001e:00000000 00000000 00000100 00000000 00000000
|- 8000001f:00000000 00000001 000000b3 00000000 00000000
|- 80000020:00000000 00000000 0000001e 00000000 00000000
|- 80000020:00000001 0000000b 00000000 00000000 0000000f
|- 80000020:00000002 0000000b 00000000 00000000 0000000f
|- 80000020:00000003 00000000 00000002 0000007f 00000000
|- 80000021:00000000 00062fcf 0000015c 00000000 00000000
|- 80000022:00000000 00000007 00044106 00000001 00000000
|- 80000023:00000000 00000000 00000000 00000000 00000000
|- 80000026:00000000 00000001 00000002 00000100 00000000
|- 80000026:00000001 00000004 0000000c 00000201 00000000
|- 80000026:00000002 00000004 0000000c 00000302 00000000
|- 80000026:00000003 00000004 0000000c 00000403 00000000
|- 40000000:00000000 00000000 00000000 00000000 00000000
|- 40000001:00000000 00000000 00000000 00000000 00000000
|- 40000002:00000000 00000000 00000000 00000000 00000000
|- 40000003:00000000 00000000 00000000 00000000 00000000
|- 40000004:00000000 00000000 00000000 00000000 00000000
|- 40000005:00000000 00000000 00000000 00000000 00000000
|- 40000006:00000000 00000000 00000000 00000000 00000000
Thank you. May ask you CPUID for all CPUs ?
" how to determine the number of CCD " question has been asked at community.amd.com
My understanding is that Core Complex in Raphael is available with 7950X but not with 7600
@tofurky and @amfern : can you please post all CPUID dump from your 7950X ?
corefreq-cli -u
My understanding is that Core Complex in Raphael is available with 7950X but not with 7600
@tofurky and @amfern : can you please post all CPUID dump from your 7950X ?
corefreq-cli -u
@chendo Hello, I really need the whole CPUID of your 7600 to debug the CPU cluster map
corefreq-cli -u
Thank you
Since first Zen families (Ryzen, TR, EPYC) with less than 256 CPUs, I could simply compute CCD = (APIC_ID & 0xf0) >> 4
In wiki, especially among EPYC, I don't have samples with more than 256 CPUs to evaluate the APIC ID, but if it relies in a range mask of [0xfff - 0x100]
then CCD = (APIC_ID & 0xf00) >> 8
CCX should be derived from something. So far code is employing the Core ID but CCD would be more appropriated to derive cases of 4 or 8 cluster size.
I don't see how I can introduce code changes without those EPYC for non regression or improvement tests ?
@amfern @tofurky @chendo
Can you please have a try to the branch develop_amd_ext_apic_id and post the output of corefreq-cli -m
@amfern @tofurky @chendo Can you please have a try to the branch develop_amd_ext_apic_id and post the output of
corefreq-cli -m
root@aquos:/usr/src/corefreqk-1.98# corefreq-cli -m
CPU Pkg Apic Core/Thread Caches (w)rite-Back (i)nclusive
# ID ID CCD CCX ID/ID L1-Inst Way L1-Data Way L2 Way L3 Way
000:BSP 0 0 0 0 0 32 8 32 8 1024 8 i 65536 16w
001: 0 2 0 0 1 0 32 8 32 8 1024 8 i 65536 16w
002: 0 4 0 0 2 0 32 8 32 8 1024 8 i 65536 16w
003: 0 6 0 0 3 0 32 8 32 8 1024 8 i 65536 16w
004: 0 8 0 1 4 0 32 8 32 8 1024 8 i 65536 16w
005: 0 10 0 1 5 0 32 8 32 8 1024 8 i 65536 16w
006: 0 12 0 1 6 0 32 8 32 8 1024 8 i 65536 16w
007: 0 14 0 1 7 0 32 8 32 8 1024 8 i 65536 16w
008: 0 16 1 2 8 0 32 8 32 8 1024 8 i 65536 16w
009: 0 18 1 2 9 0 32 8 32 8 1024 8 i 65536 16w
010: 0 20 1 2 10 0 32 8 32 8 1024 8 i 65536 16w
011: 0 22 1 2 11 0 32 8 32 8 1024 8 i 65536 16w
012: 0 24 1 3 12 0 32 8 32 8 1024 8 i 65536 16w
013: 0 26 1 3 13 0 32 8 32 8 1024 8 i 65536 16w
014: 0 28 1 3 14 0 32 8 32 8 1024 8 i 65536 16w
015: 0 30 1 3 15 0 32 8 32 8 1024 8 i 65536 16w
016: 0 1 0 0 0 1 32 8 32 8 1024 8 i 65536 16w
017: 0 3 0 0 1 1 32 8 32 8 1024 8 i 65536 16w
018: 0 5 0 0 2 1 32 8 32 8 1024 8 i 65536 16w
019: 0 7 0 0 3 1 32 8 32 8 1024 8 i 65536 16w
020: 0 9 0 1 4 1 32 8 32 8 1024 8 i 65536 16w
021: 0 11 0 1 5 1 32 8 32 8 1024 8 i 65536 16w
022: 0 13 0 1 6 1 32 8 32 8 1024 8 i 65536 16w
023: 0 15 0 1 7 1 32 8 32 8 1024 8 i 65536 16w
024: 0 17 1 2 8 1 32 8 32 8 1024 8 i 65536 16w
025: 0 19 1 2 9 1 32 8 32 8 1024 8 i 65536 16w
026: 0 21 1 2 10 1 32 8 32 8 1024 8 i 65536 16w
027: 0 23 1 2 11 1 32 8 32 8 1024 8 i 65536 16w
028: 0 25 1 3 12 1 32 8 32 8 1024 8 i 65536 16w
029: 0 27 1 3 13 1 32 8 32 8 1024 8 i 65536 16w
030: 0 29 1 3 14 1 32 8 32 8 1024 8 i 65536 16w
031: 0 31 1 3 15 1 32 8 32 8 1024 8 i 65536 16w
@tofurky Thank you Result is what I was expecting among CCD numbering Please let me know if sensors (temps, voltage) are not aligned with CCD clusters
@tofurky Thank you Result is what I was expecting among CCD numbering Please let me know if sensors (temps, voltage) are not aligned with CCD clusters
In some brief testing when loading specific cores, it seemed correct.
@tofurky Thank you Result is what I was expecting among CCD numbering Please let me know if sensors (temps, voltage) are not aligned with CCD clusters
In some brief testing when loading specific cores, it seemed correct.
Thank you for your answer
Thank you for this project.
I've supplied the
corefreq-cli -s
for a Ryzen 5 7600G. Let me know if you'd like any other output.