wouter/d4r
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Build native Windows packages for both RDNA4 targets

Browse Source 
Add explicit gfx1200/gfx1201 builds, runtime selection and per-target
code objects. Guard staging, packaging and installation against mixed
architectures; retain gfx1201 compatibility and strict K/M arithmetic.

Adapt realdody's target configuration and MSVC binary16/BOOL portability
fixes from ae530b0. Do not import its forced gfx12 layout on RDNA3.
Add exhaustive binary16 and C++/PowerShell target contract regressions.

Validation: 20 CTest gates on RX 9070 XT; four software-only gfx1200 gates;
MSVC portability compile checks; exact 4K K async and M control outputs;
isolated package install/restore and mixed-target rejection tests.
No physical gfx1200 validation is claimed.

Co-authored-by: realdody <[email protected]>
This commit is contained in:
xdfnx-devandrealdody committed 2026-10-02 16:18:18 +03:00
1 parent 8f7058d2ba
commit 98de8e3a3e
51 files changed
+636 -127
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tools/windows/native_replay_probe.cpp
+3 -3
View File
@@ -37,7 +37,7 @@ int main(int argc, char** argv) {
throw std::runtime_error("--module, --fixture-dir and --output-dir are required");
HipApi hip(args.hip_root);
hipDeviceProp_t props{};
hip.select_gfx1201(args.device, props);
hip.select_architecture(args.device, props);
const std::filesystem::path input(wide(args.fixture_dir)), output(wide(args.output_dir));
auto parameters = read_file(input / L"args.bin");
if (parameters.empty() || parameters.size() > 4096) throw std::runtime_error("Invalid replay parameter size");
@@ -84,7 +84,7 @@ int main(int argc, char** argv) {
std::memcpy(parameters.data() + offset, &pointer, 8);
}
hipModule_t module = nullptr;
hip.check(hip.hipModuleLoad(&module, args.module.c_str()), "hipModuleLoad(replay gfx1201)");
hip.check(hip.hipModuleLoad(&module, args.module.c_str()), "hipModuleLoad(replay)");
struct Cleanup { HipApi& hip; hipModule_t module; ~Cleanup() { (void)hip.hipModuleUnload(module); } } cleanup{hip, module};
if (const char* debugBlock = std::getenv("D4R_SWIN_DEBUG_BLOCK")) {
int coordinates[2]{};
@@ -240,7 +240,7 @@ int main(int argc, char** argv) {
file.write(reinterpret_cast<const char*>(bytes.data()), std::streamsize(bytes.size()));
if (!file) throw std::runtime_error("Cannot save replay allocation");
}
std::printf("PASS NATIVE_REPLAY architecture=gfx1201 kernel=%s iterations=%u benchmark_pairs=%u numerical_reference=pending\n",
std::printf("PASS NATIVE_REPLAY architecture=%s kernel=%s iterations=%u benchmark_pairs=%u numerical_reference=pending\n", d4r::diag::HipApi::target_arch(),
kernel.c_str(), args.benchmark_module.empty() ? args.iterations : 1, args.benchmark_module.empty() ? 0 : args.iterations);
return 0;
} catch (const std::exception& error) {