Hashcat AMD CPU

Trimilur · 18. April 2022

Hi,

ich habe folgendes Problem auf vrsl den meisten Servern mit AMD Cpu

clBuildProgram(): CL_BUILD_PROGRAM_FAILURE

error: unknown target CPU 'athlon-xp'

* Device #1: Kernel /usr/share/hashcat/OpenCL/m01000_a3-pure.cl build failed proceeding without this device.

jemand nen lösungsansatz.

pocl-opencl ist aktuell und intel pakete wie teils auf anderen seiten gelesen helfen genauso wenig wie —force

ubuntu 20.04 und hashcat aus den ubuntu paketquellen

hashcat v5.1.0 und manuell installiert v6.2.5

AutoYaST · 18. April 2022

VPS oder RS? Denn bei den aktuellen VPS steht, wenn ich mich recht erinnere, nur irgendwas mit "QEMU Generic CPU" in den DMI Daten. Vermutlich möchte das Programm aus den DMI Daten etwas mehr auslesen.

Trimilur · 18. April 2022

VPS

KB19 · 18. April 2022

Welchen Befehl führst Du genau aus?

Den nachfolgenden Thread kennst Du?

https://hashcat.net/forum/thread-10634-post-54744.html#pid54744

AutoYaST · 18. April 2022

Ggf. aktuelle OpenCL runtime installieren. Aber da man nicht genau weiß, welche CPU in den VPS verbaut sind, ist das wohl eher schwierig.

Abgesehen davon bist du bei solch CPU lastigen Programmen mit dedizierten Ressourcen wohl besser bedient - und deine VM-Nachbarn werden es dir danken.

Trimilur · 18. April 2022

./hashcat.bin hash.txt -m 1000 -a3 -w4 -i --increment-min=6 --increment-max=10 -1 ???u?l?d! ?1?1?1?1?1?1?1?1?1?1 --force

wahlweise mit und ohne --force

Trimilur · 18. April 2022

Zitat von KB19

Welchen Befehl führst Du genau aus?

Den nachfolgenden Thread kennst Du?

https://hashcat.net/forum/thre…-post-54744.html#pid54744

Wenn ich alles von intel installiere bekomme ich

clGetPlatformIDs(): CL_PLATFORM_NOT_FOUND_KHR

ATTENTION! No OpenCL-compatible, HIP-compatible or CUDA-compatible platform found.

You are probably missing the OpenCL, CUDA or HIP runtime installation.

* AMD GPUs on Linux require this driver:

"AMD ROCm" (4.5 or later)

* Intel CPUs require this runtime:

"OpenCL Runtime for Intel Core and Intel Xeon Processors" (16.1.1 or later)

* NVIDIA GPUs require this runtime and/or driver (both):

"NVIDIA Driver" (440.64 or later)

"CUDA Toolkit" (9.0 or later)

Trimilur · 18. April 2022

CLINFO Output

Hier läufts nicht v5.1.0 und 6.2.5

Number of platforms 1

Platform Name Portable Computing Language

Platform Vendor The pocl project

Platform Version OpenCL 1.2 pocl 1.4, None+Asserts, LLVM 9.0.1, RELOC, SLEEF, DISTRO, POCL_DEBUG

Platform Profile FULL_PROFILE

Platform Extensions cl_khr_icd

Platform Extensions function suffix POCL

Platform Name Portable Computing Language

Number of devices 1

Device Name pthread-QEMU Virtual CPU version 2.5+

Device Vendor AuthenticAMD

Device Vendor ID 0x6c636f70

Device Version OpenCL 1.2 pocl HSTR: pthread-x86_64-pc-linux-gnu-athlon-xp

Driver Version 1.4

Device OpenCL C Version OpenCL C 1.2 pocl

Device Type CPU

Device Profile FULL_PROFILE

Device Available Yes

Compiler Available Yes

Linker Available Yes

Max compute units 16

Max clock frequency 1996MHz

Device Partition (core)

Max number of sub-devices 16

Supported partition types equally, by counts

Supported affinity domains (n/a)

Max work item dimensions 3

Max work item sizes 4096x4096x4096

Max work group size 4096

=== CL_PROGRAM_BUILD_LOG ===

error: unknown target CPU 'athlon-xp'

Preferred work group size multiple <getWGsizes:1200: create kernel : error -45>

Preferred / native vector sizes

char 16 / 16

short 8 / 8

int 4 / 4

long 2 / 2

half 0 / 0 (n/a)

float 4 / 4

double 2 / 2 (cl_khr_fp64)

Half-precision Floating-point support (n/a)

Single-precision Floating-point support (core)

Denormals Yes

Infinity and NANs Yes

Round to nearest Yes

Round to zero Yes

Round to infinity Yes

IEEE754-2008 fused multiply-add No

Support is emulated in software No

Correctly-rounded divide and sqrt operations Yes

Double-precision Floating-point support (cl_khr_fp64)

Denormals Yes

Infinity and NANs Yes

Round to nearest Yes

Round to zero Yes

Round to infinity Yes

IEEE754-2008 fused multiply-add Yes

Support is emulated in software No

Address bits 64, Little-Endian

Global memory size 35700076544 (33.25GiB)

Error Correction support No

Max memory allocation 17179869184 (16GiB)

Unified memory for Host and Device Yes

Minimum alignment for any data type 128 bytes

Alignment of base address 1024 bits (128 bytes)

Global Memory cache type Read/Write

Global Memory cache size 16777216 (16MiB)

Global Memory cache line size 64 bytes

Image support Yes

Max number of samplers per kernel 16

Max size for 1D images from buffer 1073741824 pixels

Max 1D or 2D image array size 2048 images

Max 2D image size 32768x32768 pixels

Max 3D image size 2048x2048x2048 pixels

Max number of read image args 128

Max number of write image args 128

Local memory type Global

Local memory size 8388608 (8MiB)

Max number of constant args 8

Max constant buffer size 8388608 (8MiB)

Max size of kernel argument 1024

Queue properties

Out-of-order execution Yes

Profiling Yes

Prefer user sync for interop Yes

Profiling timer resolution 1ns

Execution capabilities

Run OpenCL kernels Yes

Run native kernels Yes

printf() buffer size 16777216 (16MiB)

Built-in kernels (n/a)

Device Extensions cl_khr_byte_addressable_store cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_3d_image_writes cl_khr_fp64 cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64

NULL platform behavior

clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) Portable Computing Language

clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [POCL]

clCreateContext(NULL, ...) [default] Success [POCL]

clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)

Platform Name Portable Computing Language

Device Name pthread-QEMU Virtual CPU version 2.5+

clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) Success (1)

Platform Name Portable Computing Language

Device Name pthread-QEMU Virtual CPU version 2.5+

clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1)

Platform Name Portable Computing Language

Device Name pthread-QEMU Virtual CPU version 2.5+

ICD loader properties

ICD loader Name OpenCL ICD Loader

ICD loader Vendor OCL Icd free software

ICD loader Version 2.2.11

ICD loader Profile OpenCL 2.1

Trimilur · 18. April 2022

Im vergleich hier läufts ubuntu 20 hashcat 5.1.0

Number of platforms 1

Platform Name Portable Computing Language

Platform Vendor The pocl project

Platform Version OpenCL 1.2 pocl 1.4, None+Asserts, LLVM 9.0.1, RELOC, SLEEF, DISTRO, POCL_DEBUG

Platform Profile FULL_PROFILE

Platform Extensions cl_khr_icd

Platform Extensions function suffix POCL

Platform Name Portable Computing Language

Number of devices 1

Device Name pthread-AMD EPYC 7282 16-Core Processor

Device Vendor AuthenticAMD

Device Vendor ID 0x6c636f70

Device Version OpenCL 1.2 pocl HSTR: pthread-x86_64-pc-linux-gnu-znver2

Driver Version 1.4

Device OpenCL C Version OpenCL C 1.2 pocl

Device Type CPU

Device Profile FULL_PROFILE

Device Available Yes

Compiler Available Yes

Linker Available Yes

Max compute units 8

Max clock frequency 2794MHz

Device Partition (core)

Max number of sub-devices 8

Supported partition types equally, by counts

Supported affinity domains (n/a)

Max work item dimensions 3

Max work item sizes 4096x4096x4096

Max work group size 4096

Preferred work group size multiple 8

Preferred / native vector sizes

char 16 / 16

short 16 / 16

int 8 / 8

long 4 / 4

half 0 / 0 (n/a)

float 8 / 8

double 4 / 4 (cl_khr_fp64)

Half-precision Floating-point support (n/a)

Single-precision Floating-point support (core)

Denormals Yes

Infinity and NANs Yes

Round to nearest Yes

Round to zero Yes

Round to infinity Yes

IEEE754-2008 fused multiply-add Yes

Support is emulated in software No

Correctly-rounded divide and sqrt operations Yes

Double-precision Floating-point support (cl_khr_fp64)

Denormals Yes

Infinity and NANs Yes

Round to nearest Yes

Round to zero Yes

Round to infinity Yes

IEEE754-2008 fused multiply-add Yes

Support is emulated in software No

Address bits 64, Little-Endian

Global memory size 29410729984 (27.39GiB)

Error Correction support No

Max memory allocation 8589934592 (8GiB)

Unified memory for Host and Device Yes

Minimum alignment for any data type 128 bytes

Alignment of base address 1024 bits (128 bytes)

Global Memory cache type Read/Write

Global Memory cache size 16777216 (16MiB)

Global Memory cache line size 64 bytes

Image support Yes

Max number of samplers per kernel 16

Max size for 1D images from buffer 536870912 pixels

Max 1D or 2D image array size 2048 images

Max 2D image size 16384x16384 pixels

Max 3D image size 2048x2048x2048 pixels

Max number of read image args 128

Max number of write image args 128

Local memory type Global

Local memory size 8388608 (8MiB)

Max number of constant args 8

Max constant buffer size 8388608 (8MiB)

Max size of kernel argument 1024

Queue properties

Out-of-order execution Yes

Profiling Yes

Prefer user sync for interop Yes

Profiling timer resolution 1ns

Execution capabilities

Run OpenCL kernels Yes

Run native kernels Yes

printf() buffer size 16777216 (16MiB)

Built-in kernels (n/a)

Device Extensions cl_khr_byte_addressable_store cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_3d_image_writes cl_khr_fp64 cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64

NULL platform behavior

clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) Portable Computing Language

clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [POCL]

clCreateContext(NULL, ...) [default] Success [POCL]

clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)

Platform Name Portable Computing Language

Device Name pthread-AMD EPYC 7282 16-Core Processor

clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) Success (1)

Platform Name Portable Computing Language

Device Name pthread-AMD EPYC 7282 16-Core Processor

clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform

clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1)

Platform Name Portable Computing Language

Device Name pthread-AMD EPYC 7282 16-Core Processor

ICD loader properties

ICD loader Name OpenCL ICD Loader

ICD loader Vendor OCL Icd free software

ICD loader Version 2.2.11

ICD loader Profile OpenCL 2.1

mainziman · 18. April 2022

AutoYaST Du meinst hier das was man z.B. mit cat /proc/cpuinfo in der/den 'vendor_id'-Zeilen bekommt?

ich denke das steigt hier tiefer ins System rein;

in Assembler würde das z.B. das Ergebnis der CPUID Mnemonic heissen;

Spoiler anzeigen

CPU.asm

Code

;Assembler code for C 32-bit flat library
;--------------------------------------------------------------------------
;void __cdecl getcpuid( unsigned long* pEAX, unsigned long* pEBX, unsigned long* pECX, unsigned long* pEDX );
;--------------------------------------------------------------------------

.586

;--------------------------------------------------------------------------

.MODEL    FLAT, C

;==========================================================================

getcpuid    PROTO    NEAR32    C    pEAX : NEAR32 PTR DWORD, pEBX : NEAR32 PTR DWORD, pECX : NEAR32 PTR DWORD, pEDX : NEAR32 PTR DWORD

;--------------------------------------------------------------------------

.CODE

;--------------------------------------------------------------------------

getcpuid    PROC    NEAR32    C    USES EAX EBX ECX EDX EDI,    pEAX : NEAR32 PTR DWORD, pEBX : NEAR32 PTR DWORD, pECX : NEAR32 PTR DWORD, pEDX : NEAR32 PTR DWORD

    MOV    EDI,pEAX
    MOV    EAX,[EDI]

    CPUID

    MOV    [EDI],EAX
    MOV    EDI,pEBX
    MOV    [EDI],EBX
    MOV    EDI,pECX
    MOV    [EDI],ECX
    MOV    EDI,pEDX
    MOV    [EDI],EDX

    RET

getcpuid    ENDP

;--------------------------------------------------------------------------

END

Alles anzeigen

MAIN.cxx

C

// MAIN.cxx, model: 32-bit

#include <stdio.h>

#ifdef __cplusplus
extern "C" {
#endif

void __cdecl getcpuid( unsigned long* pEAX, unsigned long* pEBX, unsigned long* pECX, unsigned long* pEDX );

#ifdef __cplusplus
}
#endif

int main( int argc, char* argv[] )
{
    unsigned long ulEAX, ulEBX, ulECX, ulEDX;

    ulEAX = 0UL;
    getcpuid( &ulEAX, &ulEBX, &ulECX, &ulEDX );

    char* pchEBX = (char*) &ulEBX;
    char* pchECX = (char*) &ulECX;
    char* pchEDX = (char*) &ulEDX;

    printf( "%c%c%c%c %c%c%c%c %c%c%c%c", *( pchEBX ), *( pchEBX + 1 ), *( pchEBX + 2 ), *( pchEBX + 3 ),
        *( pchECX ), *( pchECX + 1 ), *( pchECX + 2 ), *( pchECX + 3 ),
        *( pchEDX ), *( pchEDX + 1 ), *( pchEDX + 2 ), *( pchEDX + 3 ) );

    return 0;
}

Alles anzeigen

zusammengeflickt würde das in etwa so:

ml /c /coff CPU.asm

und

cl MAIN.cxx CPU.obj

die Ausgabe auf einem VPS der Gen7, bei welchem noch Intel CPUs im Einsatz waren sieht dann so aus:

Genu ntel ineI, lt. Spec. des CPUID Befehls, ist die Reihenfolge EBX, EDX, ECX

und übergibt man im EAX Register den Wert 1, dann erhält man Dinge wie: Family, Model, Stepping;

in dem VPS wo ich des getestet habe, ist es Family 6 Model 13 Stepping 3

in Tabellen kann man nachsehen, welche CPU das ist ..., hab ich jetzt nicht gemacht;

AutoYaST · 18. April 2022

@mainziman Ja, genau - dachte, das würde nur dort (bzw. im dmidecode equivalent) nachsehen.

Interessant, netter Testcode! Danke für's ausprobieren.

Trimilur · 21. April 2022

Wenn jemand noch ne Idee hat wäre ich dankbar

m_ueberall · 21. April 2022

Zitat von Trimilur

Wenn jemand noch ne Idee hat wäre ich dankbar

Wenn's eilig ist: Server wechseln (etwa über die Tauschbörse hier).

Ansonsten: Solange in den einschlägigen Diskussionsforen (beispielsweise hier) keine Lösung veröffentlicht wurde, wird es derzeit einfach nicht funktionieren – ergo: Abwarten und Tee trinken.

Tags