square can not run under the gpufs #1271

Yongze-zzz · 2024-06-11T06:28:43Z

Yongze-zzz
Jun 11, 2024

Dear authors, I try to run gpufs with a small example during passed week, but there are still some problem happened. I am looking for some help.

docker pull ghcr.io/gem5-test/gcn-gpu:v24-0
docker run --net host -itd --name gcn3-gpu -v /home/yanyz/db/gem5space/:/root/gem5space  ghcr.io/gem5/gcn-gpu:v23-0 bash
//enter to docker container
docker exec -w /root/gem5space -it gcn3-gpu bash
the file structure likes below:
gem5space
        |--gem5(stable branch)
        |--gem5-resources
cd gem5
scons build/GCN3_X86/gem5.opt -j 8
scons build/VEGA_X86/gem5.opt -j 8

//test quare
cd gem5-resources/src/gpu/square
make
gem5/build/GCN3_X86/gem5.opt gem5/configs/example/apu_se.py -n 3 -c gem5-resources/src/gpu/square/bin/square
//output
info: check result
PASSED!
Ticks: 139906310500
Exiting because  exiting with last active thread context

//test gpufs square
vim square.cpp
--------------------------
#include <stdio.h>
#include "hip/hip_runtime.h"
#include <pthread.h>
#define CHECK(cmd) \
{\
    hipError_t error  = cmd;\
    if (error != hipSuccess) { \
      fprintf(stderr, "error: '%s'(%d) at %s:%d\n", hipGetErrorString(error), error,__FILE__, __LINE__); \
    exit(EXIT_FAILURE);\
    }\
}

/*
 *  Thread function for printing "Hello, World!".
 */
void* print_hello(void* arg) {
    int thread_id = *(int*)arg;
    printf("Hello, World! from thread %d\n", thread_id);
    pthread_exit(NULL);
}

/*
 * Square each element in the array A and write to array C.
 */
template <typename T>
__global__ void
vector_square(T *C_d, const T *A_d, size_t N)
{
    size_t offset = (hipBlockIdx_x * hipBlockDim_x + hipThreadIdx_x);
    size_t stride = hipBlockDim_x * hipGridDim_x ;

    for (size_t i=offset; i<N; i+=stride) {
        C_d[i] = A_d[i] * A_d[i];
    }
}

int main(int argc, char *argv[])
{
    float *A_h, *C_h;
    size_t N = 1000000;
    size_t Nbytes = N * sizeof(float);

    hipDeviceProp_t props;
    CHECK(hipGetDeviceProperties(&props, 0/*deviceID*/));
    printf ("info: running on device %s\n", props.name);
    #ifdef __HIP_PLATFORM_HCC__
      printf ("info: architecture on AMD GPU device is: %d\n",props.gcnArch);
    #endif
    printf ("info: allocate host and device mem (%6.2f MB)\n", 2*Nbytes/1024.0/1024.0);
    CHECK(hipHostMalloc(&A_h, Nbytes));
    CHECK(hipHostMalloc(&C_h, Nbytes));
    // Fill with Phi + i
    for (size_t i=0; i<N; i++)
    {
        A_h[i] = 1.618f + i;
    }

    const unsigned blocks = 512;
    const unsigned threadsPerBlock = 256;

    printf ("info: launch 'vector_square' kernel\n");
    hipLaunchKernelGGL(vector_square, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_h, A_h, N);
    hipDeviceSynchronize();

    printf ("info: check result\n");
    for (size_t i=0; i<N; i++)  {
        if (C_h[i] != A_h[i] * A_h[i]) {
            CHECK(hipErrorUnknown);
        }
    }
    printf ("AMDGPU PASSED!\n");
    
    const int NUM_THREADS = 4;
    pthread_t threads[NUM_THREADS];
    int thread_ids[NUM_THREADS];
    // Create threads to print "Hello, World!"
    for (int i = 0; i < NUM_THREADS; i++) {
        thread_ids[i] = i;
        int rc = pthread_create(&threads[i], NULL, print_hello, (void*)&thread_ids[i]);
        if (rc) {
            fprintf(stderr, "Error: unable to create thread %d\n", rc);
            // exit(EXIT_FAILURE);
        }
    }

    // Wait for all threads to complete
    for (int i = 0; i < NUM_THREADS; i++) {
        pthread_join(threads[i], NULL);
    }
    return 0;
}
-------------------------------------------------------------------------

cd /root/gem5space/gem5-resources/src/gpu/square
vim square.rcS
-------sqaure.rcS--------
cd /root/gem5space/gem5-resources/src/gpu/square/bin/
./square
--------------------------
make
/root/gem5space/gem5/build/VEGA_X86/gem5.opt /root/gem5space/gem5/configs/example/gpufs/runfs.py --disk-image /root/gem5space/gem5-resources/src/x86-ubuntu-gpu-ml/disk-image/x86-ubuntu-gpu-ml --kernel /root/gem5space/gem5-resources/src/x86-ubuntu-gpu-ml/vmlinux-gpu-ml --gpu-mmio-trace /root/gem5space/gem5-resources/src/gpu-fs/vega_mmio.log --mem-size=8GB --script /root/gem5space/gem5-resources/src/gpu/square/square.rcS



warn: Physical memory size specified is 8GB which is greater than 3GB.  Twice the number of memory controllers would be created.

Global frequency set at 1000000000000 ticks per second
warn: system.workload.acpi_description_table_pointer.rsdt adopting orphan SimObject param 'entries'
src/mem/dram_interface.cc:690: warn: DRAM device capacity (8192 Mbytes) does not match the address range assigned (4096 Mbytes)
src/sim/kernel_workload.cc:46: info: kernel located at: /root/gem5space/gem5-resources/src/x86-ubuntu-gpu-ml/vmlinux-gpu-ml
src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated.
src/base/stats/storage.hh:278: warn: Bucket size (5) does not divide range [1:75] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:10] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:64] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (5) does not divide range [1:75] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:10] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:64] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (5) does not divide range [1:75] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:10] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:64] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (5) does not divide range [1:75] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:10] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (2) does not divide range [1:64] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up.
src/mem/dram_interface.cc:690: warn: DRAM device capacity (128 Mbytes) does not match the address range assigned (16384 Mbytes)
src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated.
      0: system.pc.south_bridge.cmos.rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
system.pc.com_1.device: Listening for connections on port 3456
src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated.
system.remote_gdb: Listening for connections on port 7000
src/dev/intel_8254_timer.cc:128: warn: Reading current count from inactive timer.
tcmalloc: large alloc 1073741824 bytes == 0x55a8f8020000 @ 
tcmalloc: large alloc 2147483648 bytes == 0x55a939fc2000 @ 
Running the simulation
src/sim/simulate.cc:199: info: Entering event queue @ 0.  Starting simulation...
src/mem/ruby/system/Sequencer.cc:240: panic: Possible Deadlock detected. Aborting!
 version: 0 request.paddr: 0x70000 m_readRequestTable: 1 current time: 250000000 issue_time: 0 difference: 250000000
Memory Usage: 29063328 KBytes
Program aborted at tick 250000000
--- BEGIN LIBC BACKTRACE ---
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem515print_backtraceEv+0x30)[0x55a8ef9076f0]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem512abortHandlerEi+0x4c)[0x55a8ef92edcc]
/lib/x86_64-linux-gnu/libpthread.so.0(+0x14420)[0x7ff140086420]
/lib/x86_64-linux-gnu/libc.so.6(gsignal+0xcb)[0x7ff13f25000b]
/lib/x86_64-linux-gnu/libc.so.6(abort+0x12b)[0x7ff13f22f859]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(+0xdf54c5)[0x55a8eedde4c5]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem54ruby9Sequencer6wakeupEv+0x1c1)[0x55a8efd383a1]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem510EventQueue10serviceOneEv+0xc2)[0x55a8ef91da52]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem59doSimLoopEPNS_10EventQueueE+0x70)[0x55a8ef949de0]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(_ZN4gem58simulateEm+0x28b)[0x55a8ef94a46b]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(+0x2405710)[0x55a8f03ee710]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(+0xd7aeb8)[0x55a8eed63eb8]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x2a8748)[0x7ff14033d748]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalFrameDefault+0x8dd8)[0x7ff140112f48]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalCodeWithName+0x8fb)[0x7ff14025fe4b]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyFunction_Vectorcall+0x94)[0x7ff14033d124]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x74d6d)[0x7ff140109d6d]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalFrameDefault+0x7d86)[0x7ff140111ef6]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x8006b)[0x7ff14011506b]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x74d6d)[0x7ff140109d6d]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalFrameDefault+0x12fd)[0x7ff14010b46d]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalCodeWithName+0x8fb)[0x7ff14025fe4b]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(PyEval_EvalCodeEx+0x42)[0x7ff1402601d2]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(PyEval_EvalCode+0x1f)[0x7ff1402605bf]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x1cfc01)[0x7ff140264c01]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x25f547)[0x7ff1402f4547]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x74d6d)[0x7ff140109d6d]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(_PyEval_EvalFrameDefault+0x12fd)[0x7ff14010b46d]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(+0x8006b)[0x7ff14011506b]
/lib/x86_64-linux-gnu/libpython3.8.so.1.0(PyVectorcall_Call+0x60)[0x7ff14033d840]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(+0x1946e84)[0x55a8ef92fe84]
/root/gem5space/gem5/build/VEGA_X86/gem5.opt(main+0x213)[0x55a8eecf16d3]
--- END LIBC BACKTRACE ---
For more info on how to address this issue, please visit https://www.gem5.org/documentation/general_docs/common-errors/ 

Aborted (core dumped)

Yongze-zzz · 2024-06-11T08:45:34Z

Yongze-zzz
Jun 11, 2024
Author

/root/gem5space/gem5/build/GCN3_X86/gem5.opt /root/gem5space/gem5/configs/example/apu_se.py -n 3 -c /root/gem5space/gem5-resources/src/matrix-multiply-omp/matrix-omp. I try to run multi thread with apu_se mode, but it report :Thread creation failed: Resource temporarily unavailable. I just need a mode which can run cpu multi-thread and gpu kernel function at the same time.

0 replies

mattsinc · 2024-06-11T16:18:42Z

mattsinc
Jun 11, 2024
Maintainer

I have never tried running multi-threaded CPU programs so unfortunately I cannot provide any advice there -- maybe @BobbyRBruce or @powerjg can.

In terms of the GPU portion, I am confused by what you posted. I see the following:

...
info: check result
PASSED!
Ticks: 139906310500
Exiting because exiting with last active thread context

This seems to imply that square passed. However, I later see:

...
src/mem/ruby/system/Sequencer.cc:240: panic: Possible Deadlock detected. Aborting!
version: 0 request.paddr: 0x70000 m_readRequestTable: 1 current time: 250000000 issue_time: 0 difference: 250000000

So I'm confused how you could have had the test both pass and fail. Are you including two separate runs -- one of which passed and one of which failed?

My guess from trying to parse the text in your message is that a) square is working fine when run in the provided format in SE mode, b) you did not try square in the provided format in FS mode, and c) when you added pthreads to it for a CPU portion and ran in FS mode it has the error you later posted? If so, I think this is not a problem with the GPU support, but rather a question for the CPU folks. But let @abmerop and I know if we're missing something.

0 replies

Yongze-zzz · 2024-06-11T23:37:22Z

Yongze-zzz
Jun 11, 2024
Author

I did two separate runs, first executing square using apu_se.py mode, and it passed. But when I added a separate pthread for square, and executed it in runfs.py mode, it failed.
Indeed, as you might guess, a) square works fine when running in SE mode in the provided format. b) square did not work when tried in FS mode in the provided format, and c) when adding pthreads for the CPU portion and running in FS mode, it gave the error posted later

Also, I tried running square in FS mode in the provided format for the last few hours, and it gave the same problem as adding pthreads

0 replies

abmerop · 2024-06-12T16:39:31Z

abmerop
Jun 12, 2024
Maintainer

Timing CPUs do not work with GPUFS due to the fundamental design of Ruby (TimingSimpleCPU / O3CPU). Please use the top level script configs/example/gpufs/vega10_kvm.py which sets the known working parameters for you.

0 replies

Yongze-zzz · 2024-06-13T05:44:01Z

Yongze-zzz
Jun 13, 2024
Author

Thank you ! I run /root/gem5space/gem5/build/VEGA_X86/gem5.opt /root/gem5space/gem5/configs/example/gpufs/vega10_kvm.py --disk-image /root/gem5space/gem5-resources/src/x86-ubuntu-gpu-ml/disk-image/x86-ubuntu-gpu-ml --kernel /root/gem5space/gem5-resources/src/x86-ubuntu-gpu-ml/vmlinux-gpu-ml --gpu-mmio-trace /root/gem5space/gem5-resources/src/gpu-fs/vega_mmio.log --mem-size=8GB -a /root/gem5space/gem5-resources/src/gpu/square/bin/square.

Then it report src/cpu/kvm/perfevent.cc:217: panic: PerfKvmCounter::attach failed (1).

I try to run "echo "-1" | sudo tee /proc/sys/kernel/perf_event_paranoid". But it stilll report panic: PerfKvmCounter::attach failed (1).\

My gem5 branch is "stable" and "revert-1065-kvm-hybrid-pmu",both of them do not work.

0 replies

abmerop · 2024-06-13T18:33:56Z

abmerop
Jun 13, 2024
Maintainer

You could try adding --no-kvm-perf to the command. If KVM does not work at all, there is also a configs/example/gpufs/vega10_atomic.py. With atomic CPU however, your simulation is going to take hours instead of minutes and you might have to rely on things like checkpointing

0 replies

Yongze-zzz · 2024-06-14T01:46:06Z

Yongze-zzz
Jun 14, 2024
Author

src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up. src/base/stats/storage.hh:278: warn: Bucket size (10000) does not divide range [1:1.6e+06] into equal-sized buckets. Rounding up. src/mem/dram_interface.cc:690: warn: DRAM device capacity (128 Mbytes) does not match the address range assigned (16384 Mbytes) src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated. 0: system.pc.south_bridge.cmos.rtc: Real-time clock set to Sun Jan 1 00:00:00 2012 system.pc.com_1.device: Listening for connections on port 3456 src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated. system.remote_gdb: Listening for connections on port 7000 src/dev/intel_8254_timer.cc:128: warn: Reading current count from inactive timer. tcmalloc: large alloc 2147483648 bytes == 0x5604c2ff6000 @ Running the simulation src/cpu/kvm/base.cc:169: info: KVM: Coalesced MMIO disabled by config. src/sim/simulate.cc:199: info: Entering event queue @ 0. Starting simulation... src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x3a) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x309) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x30a) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x30b) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x38d) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x38e) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x38f) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x390) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc1) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc2) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc3) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc4) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc5) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc6) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc7) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc8) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x186) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x187) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x188) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x189) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x18a) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x18b) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x18c) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x18d) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x12) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x11) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d01) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d00) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000000) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000001) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000020) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000021) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000022) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000023) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000100) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000101) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000102) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000103) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000104) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000105) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000003) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000002) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000010) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000080) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000b0) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000073) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000106) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000107) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x40000108) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000ff) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000f1) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000f2) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000f3) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000f4) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x400000f5) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d02) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d03) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d04) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d06) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d07) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x3b) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x6e0) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x10a) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x345) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x1a0) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4d0) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x9e) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x34) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xce) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x140) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x1fc) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x8b) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x480) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48d) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48e) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48f) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x490) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x485) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x486) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x488) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48a) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48b) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x48c) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x491) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0xc0010015) unsupported by gem5. Skipping. src/arch/x86/kvm/x86_cpu.cc:1653: warn: kvm-x86: MSR (0x4b564d05) unsupported by gem5. Skipping. src/dev/x86/pc.cc:117: warn: Don't know what interrupt to clear for console. src/arch/x86/interrupts.cc:530: hack: Assuming logical destinations are 1 << id. src/dev/amdgpu/amdgpu_vm.hh:254: warn: Accessing unsupported MMIO aperture! Assuming NBIO Exiting @ tick 6061858002000 because m5_exit instruction encountered src/cpu/kvm/base.cc:591: hack: Pretending totalOps is equivalent to totalInsts()

I try to add --no-kvm-perf , then run square. The script seems like execute successful, but there is a problem, the system.pc.com_1.device report :Running /root/gem5space/gem5-resources/src/gpu/square/bin/square ./myapp: error while loading shared libraries: libamdhip64.so.4: cannot open shared object file: No such file or directory

0 replies

abmerop · 2024-06-14T15:09:18Z

abmerop
Jun 14, 2024
Maintainer

You will need to build square for ROCm 6.1 (the version on the disk image). There is a docker provided to help with that here: docker run ghcr.io/gem5/gpu-fs:latest

0 replies

ivanaamit · 2024-06-14T16:58:13Z

ivanaamit
Jun 14, 2024
Maintainer

This seems to be a discussion rather than a gem5 bug. Please let me know if that is the case so that I can convert it into discussion. Thanks.

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

gem5

square can not run under the gpufs #1271

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Replies: 9 comments

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

Select a reply

gem5

square can not run under the gpufs #1271

Yongze-zzz Jun 11, 2024

Replies: 9 comments

Yongze-zzz Jun 11, 2024 Author

mattsinc Jun 11, 2024 Maintainer

Yongze-zzz Jun 11, 2024 Author

abmerop Jun 12, 2024 Maintainer

Yongze-zzz Jun 13, 2024 Author

abmerop Jun 13, 2024 Maintainer

Yongze-zzz Jun 14, 2024 Author

abmerop Jun 14, 2024 Maintainer

ivanaamit Jun 14, 2024 Maintainer

Yongze-zzz
Jun 11, 2024

Yongze-zzz
Jun 11, 2024
Author

mattsinc
Jun 11, 2024
Maintainer

Yongze-zzz
Jun 11, 2024
Author

abmerop
Jun 12, 2024
Maintainer

Yongze-zzz
Jun 13, 2024
Author

abmerop
Jun 13, 2024
Maintainer

Yongze-zzz
Jun 14, 2024
Author

abmerop
Jun 14, 2024
Maintainer

ivanaamit
Jun 14, 2024
Maintainer