36d93e03c8
Nothing changes for the default class: the pinned packs are byte-identical (tests/packs.rs), the v2 draw stream is untouched.
LoadClass {mix, load_slots, scratch}: fixed widths w16, w64, w64x4 (4 loads of 64 B), era mixes 50/35/15 and 25/50/25 drawn per load with one extra below(100) roll, and the scratch variant scr0/2/4/8 (persistent warps, 1 MiB per warp, tagged lazy fill, measurement only). A wide load reads the W-aligned address and folds every word: x = dst ^ w0; x = (rotl(x, 11) * 0x9e3779b1) ^ w[j]. Program ids carry the class. proto-opencl/host.c taken from opencl-rdna4 20ceac6 (--memprobe, select read-back).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
71 lines
4.3 KiB
C
71 lines
4.3 KiB
C
/* Unit tests for the host-side rules of host.c that need no device (5 October 2026): the duplicate-platform fold
|
|
* (markDuplicates, driverNumber). host.c is included with its main renamed. Build and run: ./test-host.sh */
|
|
#define main host_main
|
|
#include "host.c"
|
|
#undef main
|
|
|
|
static int failures = 0;
|
|
#define CHECK(cond, what) do { if (!(cond)) { printf("FAIL: %s (line %d)\n", what, __LINE__); ++failures; } else printf("ok: %s\n", what); } while (0)
|
|
|
|
static DeviceInfo dev(const char* platform, const char* version, const char* name, const char* vendor, const char* driver, cl_ulong mem, cl_uint cus) {
|
|
DeviceInfo d;
|
|
memset(&d, 0, sizeof(d));
|
|
strncpy(d.platformName, platform, 255); strncpy(d.platformVersion, version, 255);
|
|
strncpy(d.name, name, 255); strncpy(d.vendor, vendor, 255); strncpy(d.driver, driver, 255);
|
|
d.globalMem = mem; d.computeUnits = cus; d.type = CL_DEVICE_TYPE_GPU; d.dupOf = -1;
|
|
return d;
|
|
}
|
|
|
|
int main(void) {
|
|
const char* AMD = "AMD Accelerated Parallel Processing";
|
|
const char* V_NEW = "OpenCL 2.1 AMD-APP (3683.0)", *V_OLD = "OpenCL 2.1 AMD-APP (3652.0)", *V_OLDER = "OpenCL 2.1 AMD-APP (3600.0)";
|
|
const char* AMDV = "Advanced Micro Devices, Inc.";
|
|
CHECK(driverNumber("3683.0 (PAL,LC)") == 3683.0, "driverNumber reads the AMD string");
|
|
CHECK(driverNumber("617.14") > 617.1 && driverNumber("617.14") < 617.2, "driverNumber reads the NVIDIA string");
|
|
CHECK(driverNumber("") == 0.0, "driverNumber of an empty string is 0");
|
|
{
|
|
/* PC 1 on 5 October 2026: the new platform first, the old one second, NVIDIA last */
|
|
DeviceInfo l[5];
|
|
l[0] = dev(AMD, V_NEW, "gfx1036", AMDV, "3683.0 (PAL,LC)", 59589ull << 20, 1);
|
|
l[1] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[2] = dev(AMD, V_OLD, "gfx1036", AMDV, "3652.0 (PAL,LC)", 59589ull << 20, 1);
|
|
l[3] = dev(AMD, V_OLD, "gfx1201", AMDV, "3652.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[4] = dev("NVIDIA CUDA", "OpenCL 3.0 CUDA 13.4.96", "NVIDIA GeForce RTX 5090", "NVIDIA Corporation", "617.14", 32579ull << 20, 170);
|
|
CHECK(markDuplicates(l, 5) == 2, "PC 1: two duplicates marked");
|
|
CHECK(l[0].dupOf == -1 && l[1].dupOf == -1 && l[4].dupOf == -1, "PC 1: the new platform's cards and the NVIDIA card stay");
|
|
CHECK(l[2].dupOf == 0 && l[3].dupOf == 1, "PC 1: the old platform's entries point at the new ones");
|
|
}
|
|
{
|
|
/* the old platform enumerated first: the newer entry must still be the one kept */
|
|
DeviceInfo l[2];
|
|
l[0] = dev(AMD, V_OLD, "gfx1201", AMDV, "3652.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[1] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
CHECK(markDuplicates(l, 2) == 1, "old first: one duplicate");
|
|
CHECK(l[0].dupOf == 1 && l[1].dupOf == -1, "old first: the older entry is the duplicate");
|
|
}
|
|
{
|
|
/* two real cards of one model on ONE platform: never folded */
|
|
DeviceInfo l[2];
|
|
l[0] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[1] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
CHECK(markDuplicates(l, 2) == 0 && l[0].dupOf == -1 && l[1].dupOf == -1, "two identical cards on one platform stay two cards");
|
|
}
|
|
{
|
|
/* three registrations of one card: one stays */
|
|
DeviceInfo l[3];
|
|
l[0] = dev(AMD, V_OLD, "gfx1201", AMDV, "3652.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[1] = dev(AMD, V_OLDER, "gfx1201", AMDV, "3600.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[2] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
CHECK(markDuplicates(l, 3) == 2, "three platforms: two duplicates");
|
|
CHECK(l[2].dupOf == -1 && l[0].dupOf == 2 && l[1].dupOf == 2, "three platforms: the newest stays and both duplicates point at it");
|
|
}
|
|
{
|
|
/* a different card with the same name but other memory (an 8 GB and a 16 GB model) on two platforms: not folded */
|
|
DeviceInfo l[2];
|
|
l[0] = dev(AMD, V_NEW, "gfx1201", AMDV, "3683.0 (PAL,LC)", 16304ull << 20, 32);
|
|
l[1] = dev(AMD, V_OLD, "gfx1201", AMDV, "3652.0 (PAL,LC)", 8000ull << 20, 32);
|
|
CHECK(markDuplicates(l, 2) == 0, "different memory sizes are different cards");
|
|
}
|
|
printf("%s: %d failure(s)\n", failures ? "FAIL" : "PASS", failures);
|
|
return failures ? 1 : 0;
|
|
}
|