reading GPU resource data by CPU - buffer

Question

i am learning directx11 these days. and i have been stuck in compute shader section.
so i made four resource and three corresponding view.
immutable input buffer = {1,1,1,1,1} / SRV
immutable input buffer = {2,2,2,2,2} / SRV
output buffer / UAV
staging buffer for reading / No View
and i succeeded to create all things, and dispatch cs function, and copy data from output buffer to staging buffer, and i read/check data.
// INPUT BUFFER1--------------------------------------------------
const int dataSize = 5;
D3D11_BUFFER_DESC vb_dest;
vb_dest.ByteWidth = sizeof(float) * dataSize;
vb_dest.StructureByteStride = sizeof(float);
vb_dest.BindFlags = D3D11_BIND_SHADER_RESOURCE;
vb_dest.Usage = D3D11_USAGE_IMMUTABLE;
vb_dest.CPUAccessFlags = 0;
vb_dest.MiscFlags = 0;
float v1_float[dataSize] = { 1,1,1,1,1 };
D3D11_SUBRESOURCE_DATA v1_data;
v1_data.pSysMem = static_cast<void*>(v1_float);
device->CreateBuffer(
&vb_dest,
&v1_data,
valueBuffer1.GetAddressOf());
D3D11_SHADER_RESOURCE_VIEW_DESC srv_desc;
srv_desc.Format = DXGI_FORMAT_R32_FLOAT;
srv_desc.ViewDimension = D3D11_SRV_DIMENSION_BUFFER;
srv_desc.Buffer.FirstElement = 0;
srv_desc.Buffer.NumElements = dataSize;
srv_desc.Buffer.ElementWidth = sizeof(float);
device->CreateShaderResourceView(
valueBuffer1.Get(),
&srv_desc,
inputSRV1.GetAddressOf());
// INPUT BUFFER2-----------------------------------------------------------
float v2_float[dataSize] = { 2,2,2,2,2 };
D3D11_SUBRESOURCE_DATA v2_data;
v2_data.pSysMem = static_cast<void*>(v2_float);
device->CreateBuffer(
&vb_dest,
&v2_data,
valueBuffer2.GetAddressOf());
device->CreateShaderResourceView(
valueBuffer2.Get(),
&srv_desc,
inputSRV2.GetAddressOf());
// OUTPUT BUFFER-----------------------------------------------------------
D3D11_BUFFER_DESC ov_desc;
ov_desc.ByteWidth = sizeof(float) * dataSize;
ov_desc.StructureByteStride = sizeof(float);
ov_desc.BindFlags = D3D11_BIND_UNORDERED_ACCESS;
ov_desc.Usage = D3D11_USAGE_DEFAULT;
ov_desc.CPUAccessFlags = 0;
ov_desc.MiscFlags = 0;
device->CreateBuffer(
&ov_desc,
nullptr,
outputResource.GetAddressOf());
D3D11_UNORDERED_ACCESS_VIEW_DESC outputUAV_desc;
outputUAV_desc.Format = DXGI_FORMAT_R32_FLOAT;
outputUAV_desc.ViewDimension = D3D11_UAV_DIMENSION_BUFFER;
outputUAV_desc.Buffer.FirstElement = 0;
outputUAV_desc.Buffer.NumElements = dataSize;
outputUAV_desc.Buffer.Flags = 0;
device->CreateUnorderedAccessView(
outputResource.Get(),
&outputUAV_desc,
outputUAV.GetAddressOf());
// BUFFER FOR COPY-----------------------------------------------------------
D3D11_BUFFER_DESC rb_desc;
rb_desc.ByteWidth = sizeof(float) * dataSize;
rb_desc.StructureByteStride = sizeof(float);
rb_desc.Usage = D3D11_USAGE_STAGING;
rb_desc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
rb_desc.BindFlags = 0;
rb_desc.MiscFlags = 0;
device->CreateBuffer(
&rb_desc,
nullptr,
readResource.GetAddressOf());
// DISPATCH and COPY and GET DATA
dContext->CSSetShaderResources(0, 1, inputSRV1.GetAddressOf());
dContext->CSSetShaderResources(1, 1, inputSRV2.GetAddressOf());
dContext->CSSetUnorderedAccessViews(0, 1, outputUAV.GetAddressOf(), nullptr);
dContext->CSSetShader(cs.Get(), nullptr, 0);
dContext->Dispatch(1, 1, 1);
dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
and this is compute shader code
StructuredBuffer<float> inputA : register(t0);
StructuredBuffer<float> inputB : register(t1);
RWStructuredBuffer<float> output : register(u0);
[numthreads(5, 1, 1)]
void main(int3 id : SV_DispatchThreadID)
{
output[id.x] = inputA[id.x] + inputB[id.x];
}
in CS, it's adding two input buffer data and store into output buffer.
so expected answer would be {3,3,3,3,3}.
but the result is {3,0,0,0,0} only first idx has proper answer.
any advice would be amazing.

Answer 1

dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
this code should be like this.
CopyResource();
Map();
Declare and allocate 'data'
zeromemory(data);
memcopy(data, resource's pointer);
unMap();
for some reason, i have to use the memcopy instead of just reading resource directly with the pointer that i get from mapping.