ayo
2558fcbd39
- Match render/compute adapters and gate RR models by GPU capabilities - Add RDNA2 native texture kernels and fix FP16 rounding - Harden model builds, cache validation and packaging - Add startup tracing, timeouts, documentation and regression tests
36 lines
1.3 KiB
C++
36 lines
1.3 KiB
C++
#pragma once
|
|
#include <vulkan/vulkan_core.h>
|
|
#include <sstream>
|
|
#include <string>
|
|
|
|
// Inspect metadata before constructing any pipeline. Old default D/E and F models require FP8;
|
|
// only the explicitly marked gfx11 D/E models use widened f16 cooperative matrices.
|
|
inline bool d4r_rr_model_compatible(const std::string& metadata, bool f16Matrices, bool fp8Matrices)
|
|
{
|
|
std::istringstream lines(metadata);
|
|
std::string line;
|
|
if (!std::getline(lines, line)) return false;
|
|
if (!line.empty() && line.back() == '\r') line.pop_back();
|
|
if (line == "D4RR0002") return fp8Matrices;
|
|
if (line != "D4RR0001") return false;
|
|
bool widened = false;
|
|
while (std::getline(lines, line))
|
|
{
|
|
std::istringstream fields(line);
|
|
std::string key, value; fields >> key >> value;
|
|
if (key == "arithmetic")
|
|
{
|
|
if (value != "gfx11") return false;
|
|
widened = true;
|
|
}
|
|
}
|
|
return widened ? f16Matrices : fp8Matrices;
|
|
}
|
|
|
|
inline bool d4r_matrix_tuple(const VkCooperativeMatrixPropertiesKHR& p, VkComponentTypeKHR operand)
|
|
{
|
|
return p.MSize == 16 && p.NSize == 16 && p.KSize == 16 && p.scope == VK_SCOPE_SUBGROUP_KHR &&
|
|
p.AType == operand && p.BType == operand && p.CType == VK_COMPONENT_TYPE_FLOAT32_KHR &&
|
|
p.ResultType == VK_COMPONENT_TYPE_FLOAT32_KHR && !p.saturatingAccumulation;
|
|
}
|