461f1506e7
This is not necessary, as we must emit an invalidating store before we potentially consume an invalid expression. In fact, we're a bit conservative here in this case for example: int tmp = variable; if (...) { variable = 10; } else { // Consuming tmp here is fine, but it was // invalidated while emitting other branch. // Technically, we need to study if there is an invalidating store // in the CFG between the loading block and this block, and the other // branch will not be a part of that analysis. int tmp2 = tmp * tmp; } Fixing this case means complex CFG traversal *everywhere*, and it feels like overkill. Fixing this exposed a bug with access chains, so fix a bug where expression dependencies were not inherited properly in access chains. Access chains are now considered forwarded if there is at least one dependency which is also forwarded.
28 lines
680 B
Plaintext
28 lines
680 B
Plaintext
#version 450
|
|
#extension GL_ARB_gpu_shader_int64 : require
|
|
#extension GL_ARB_shader_ballot : require
|
|
#extension GL_AMD_shader_ballot : require
|
|
layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout(binding = 0, std430) buffer inputData
|
|
{
|
|
float inputDataArray[];
|
|
} _12;
|
|
|
|
layout(binding = 1, std430) buffer outputData
|
|
{
|
|
float outputDataArray[];
|
|
} _74;
|
|
|
|
void main()
|
|
{
|
|
bool _31 = _12.inputDataArray[gl_LocalInvocationID.x] > 0.0;
|
|
uvec4 _37 = uvec4(unpackUint2x32(ballotARB(_31)), 0u, 0u);
|
|
uint _44 = mbcntAMD(packUint2x32(uvec2(_37.xy)));
|
|
if (_31)
|
|
{
|
|
_74.outputDataArray[_44] = _12.inputDataArray[gl_LocalInvocationID.x];
|
|
}
|
|
}
|
|
|