simple changes to operation order causes XRT to return incorrect result

The provided test case is mostly automatically generated from an issue found in our runtime build on top of XRT.

depending on when the xrt::bo is created XRT will either work as expected or return incorrect data.

steps to reproduce:

> export XCL_EMULATION_MODE=hw_emu
> unzip reprod.zip
> clang++ -o reprod host.cpp -g -I/opt/xilinx/xrt/include -L/opt/xilinx/xrt/lib -lOpenCL -luuid -lxrt_coreutil
> ./reprod
will work as expected
> clang++ -o reprod host.cpp -g -I/opt/xilinx/xrt/include -L/opt/xilinx/xrt/lib -lOpenCL -luuid -lxrt_coreutil -DFAIL
> ./reprod
will hit an assert because of incorrect outputs

I think this is a bug.

here is the host.cpp and the device.xclbin
reprod.zip

the program is simply writing data given as scalar into a buffer. here is the host code also in reprod.zip:

#include <xrt/xrt_kernel.h>
#include <xrt.h>
#include <array>

int main() {

// from: _pi_platform::_pi_platform(unsigned int) sycl/plugins/xrt/pi_xrt.cpp:476
// call str:xrt::device(i)
auto name0 = xrt::device(((unsigned int)0));

// xclbin buffer size=20927220
// from: pi_result xrt_piProgramCreateWithBinary(pi_context, pi_uint32, const pi_device *, const size_t *, const unsigned char **, size_t, const pi_device_binary_property *, pi_int32 *, pi_program *) sycl/plugins/xrt/pi_xrt.cpp:1846
// call str:xrt::xclbin(reinterpret_cast<const axlf *>(binaries[0]))
auto name1 = xrt::xclbin("device.xclbin");

/// When we do buffer construction amd mapping here the data written by the kernel is incorrect
#ifdef FAIL
// from: void _pi_mem::map_if_needed(const xrt::device &) sycl/plugins/xrt/pi_xrt.cpp:555
// call str:xrt::bo(device, mem.size, XRT_BO_FLAGS_NONE, 0)
auto name6 = xrt::bo(name0, ((unsigned long)16), ((int)0), ((int)0));

// from: void _pi_mem::map_if_needed(const xrt::device &) sycl/plugins/xrt/pi_xrt.cpp:556
// call str:buffer_.map()
auto name7 = name6.map();
#endif

// from: pi_result xrt_piProgramCreateWithBinary(pi_context, pi_uint32, const pi_device *, const size_t *, const unsigned char **, size_t, const pi_device_binary_property *, pi_int32 *, pi_program *) sycl/plugins/xrt/pi_xrt.cpp:1847
// call str:dev->get().load_xclbin(xclbin)
auto name2 = name0.load_xclbin(name1);

/// BUT When we do buffer construction amd mapping here it works as expected
#ifndef FAIL
// from: void _pi_mem::map_if_needed(const xrt::device &) sycl/plugins/xrt/pi_xrt.cpp:555
// call str:xrt::bo(device, mem.size, XRT_BO_FLAGS_NONE, 0)
auto name6 = xrt::bo(name0, ((unsigned long)16), ((int)0), ((int)0));

// from: void _pi_mem::map_if_needed(const xrt::device &) sycl/plugins/xrt/pi_xrt.cpp:556
// call str:buffer_.map()
auto name7 = name6.map();
#endif

// from: pi_result xrt_piKernelCreate(pi_program, const char *, pi_kernel *) sycl/plugins/xrt/pi_xrt.cpp:1699
// call str:xrt::kernel(program->device_->get(), program->uuid_, kernel_name)
auto name3 = xrt::kernel(name0, name2, "dlerEE_clES2_E6Kernel_0i996ruy");

// from: pi_result xrt_piKernelCreate(pi_program, const char *, pi_kernel *) sycl/plugins/xrt/pi_xrt.cpp:1700
// call str:program->bin_.get_kernel(kernel_name)
auto name4 = name1.get_kernel("dlerEE_clES2_E6Kernel_0i996ruy");

// from: pi_result xrt_piKernelCreate(pi_program, const char *, pi_kernel *) sycl/plugins/xrt/pi_xrt.cpp:1701
// call str:xrt::run(ker)
auto name5 = xrt::run(name3);

// from: pi_result xrt_piextKernelSetArgMemObj(pi_kernel, pi_uint32, const pi_mem *) sycl/plugins/xrt/pi_xrt.cpp:1726
// call str:kernel->run_.set_arg(arg_index, buf->buffer_)
name5.set_arg(((unsigned int)0), name6);

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1714
std::array<char, 8> name8= {'\x04', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00'};

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1715
// call str:kernel->run_.set_arg(arg_index, arg_value, arg_size)
name5.set_arg(((unsigned int)1), ((const void*)name8.data()), ((unsigned long)8));

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1714
std::array<char, 8> name9= {'\x04', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00'};

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1715
// call str:kernel->run_.set_arg(arg_index, arg_value, arg_size)
name5.set_arg(((unsigned int)2), ((const void*)name9.data()), ((unsigned long)8));

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1714
std::array<char, 8> name10= {'\x00', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00', '\x00'};

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1715
// call str:kernel->run_.set_arg(arg_index, arg_value, arg_size)
name5.set_arg(((unsigned int)3), ((const void*)name10.data()), ((unsigned long)8));

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1714
std::array<char, 16> name11= {'\x00', '\x00', '\x00', '\x00', '\x01', '\x00', '\x00', '\x00', '\x02', '\x00', '\x00', '\x00', '\x03', '\x00', '\x00', '\x00'};

// from: pi_result xrt_piKernelSetArg(pi_kernel, pi_uint32, size_t, const void *) sycl/plugins/xrt/pi_xrt.cpp:1715
// call str:kernel->run_.set_arg(arg_index, arg_value, arg_size)
name5.set_arg(((unsigned int)4), ((const void*)name11.data()), ((unsigned long)16));

// from: pi_result xrt_piEnqueueKernelLaunch(pi_queue, pi_kernel, pi_uint32, const size_t *, const size_t *, const size_t *, pi_uint32, const pi_event *, pi_event *) sycl/plugins/xrt/pi_xrt.cpp:1754
// call str:kernel->run_.start()
name5.start();

// from: pi_result xrt_piEnqueueKernelLaunch(pi_queue, pi_kernel, pi_uint32, const size_t *, const size_t *, const size_t *, pi_uint32, const pi_event *, pi_event *) sycl/plugins/xrt/pi_xrt.cpp:1755
// call str:kernel->run_.wait()
name5.wait();

// from: pi_result xrt_piEnqueueMemBufferRead(pi_queue, pi_mem, pi_bool, size_t, size_t, void *, pi_uint32, const pi_event *, pi_event *) sycl/plugins/xrt/pi_xrt.cpp:1679
// call str:buffer->buffer_.sync(XCL_BO_SYNC_BO_FROM_DEVICE)
name6.sync(((xclBOSyncDirection)1));

// from: pi_result xrt_piEnqueueMemBufferRead(pi_queue, pi_mem, pi_bool, size_t, size_t, void *, pi_uint32, const pi_event *, pi_event *) sycl/plugins/xrt/pi_xrt.cpp:1681
std::array<char, 16> name12= {'\xc0', '\xdc', '\x3a', '\xf7', '\xff', '\x7f', '\x00', '\x00', '\xc0', '\xdc', '\x3a', '\xf7', '\xff', '\x7f', '\x00', '\x00'};

// from: pi_result xrt_piEnqueueMemBufferRead(pi_queue, pi_mem, pi_bool, size_t, size_t, void *, pi_uint32, const pi_event *, pi_event *) sycl/plugins/xrt/pi_xrt.cpp:1682
// call str:(void)std::memcpy(ptr, adjusted_ptr, size)
(void)std::memcpy(((void*)name12.data()), name7, ((unsigned long)16));

int *a_c = ((int *)name12.data());
for (int i = 0; i < 4; i++) {
int res = i;
int val = a_c[i];
assert(val == res);
}
}