Caffe Framework Runtest Core dumped error - cuda

Question

I have been installing Caffe Framework with the following GPU:
Geforce 9500 GT
CUDA 6.5 (not work with 7.0)
when I run: make runtest the following errors appeared and I don't know what are the reasons:
make runtest
.build_debug/tools/caffe
caffe: command line brew
usage: caffe <command> <args>
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Run in GPU mode on given device ID.) type: int32 default: -1
-iterations (The number of iterations to run.) type: int32 default: 50
-model (The model definition protocol buffer text file..) type: string
default: ""
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-weights (Optional; the pretrained weights to initialize finetuning. Cannot
be set simultaneously with snapshot.) type: string default: ""
.build_debug/test/test_all.testbin 0 --gtest_shuffle
Cuda number of devices: 1
Setting to use device 0
Current device id: 0
Note: Randomizing tests' orders with a seed of 60641 .
[==========] Running 1356 tests from 214 test cases.
[----------] Global test environment set-up.
[----------] 10 tests from PowerLayerTest/3, where TypeParam = caffe::GPUDevice<double>
[ RUN ] PowerLayerTest/3.TestPower
F0616 20:08:47.978885 31913 math_functions.cu:81] Check failed: error == cudaSuccess (11 vs. 0) invalid argument
*** Check failure stack trace: ***
# 0x2b2716c57daa (unknown)
# 0x2b2716c57ce4 (unknown)
# 0x2b2716c576e6 (unknown)
# 0x2b2716c5a687 (unknown)
# 0x2b27187a66fd caffe::caffe_gpu_memcpy()
# 0x2b27186fa15d caffe::SyncedMemory::to_gpu()
# 0x2b27186f9b44 caffe::SyncedMemory::gpu_data()
# 0x2b27186a4701 caffe::Blob<>::gpu_data()
# 0x2b27187b3a70 caffe::PowerLayer<>::Forward_gpu()
# 0x4adaca caffe::Layer<>::Forward()
# 0x5a033e caffe::PowerLayerTest<>::TestForward()
# 0x59f381 caffe::PowerLayerTest_TestPower_Test<>::TestBody()
# 0x7cf479 testing::internal::HandleSehExceptionsInMethodIfSupported<>()
# 0x7caa12 testing::internal::HandleExceptionsInMethodIfSupported<>()
# 0x7b7e29 testing::Test::Run()
# 0x7b85c2 testing::TestInfo::Run()
# 0x7b8bb0 testing::TestCase::Run()
# 0x7bda3a testing::internal::UnitTestImpl::RunAllTests()
# 0x7d04ac testing::internal::HandleSehExceptionsInMethodIfSupported<>()
# 0x7cb6c9 testing::internal::HandleExceptionsInMethodIfSupported<>()
# 0x7bc7ce testing::UnitTest::Run()
# 0x480a13 main
# 0x2b27196a1ec5 (unknown)
# 0x480819 (unknown)
# (nil) (unknown)
make: *** [runtest] Aborted (core dumped)

Answer 1

It turns out that (as #Jez suggested) my GPU does not support double precision which used by Caffe math functions. That's the reason for crashes. I have searched for workaround on this issue but haven't found one. Maybe the only solution is to use more modern GPU