feat: add d4r inference engines and Windows parity tooling

Add native K/M/RR inference engines, HIP kernels, replay and validation
harnesses, and Windows DLSS setup and runtime support. Include GPU
profiling tools, build and packaging scripts, platform integration
patches, and implementation documentation.
This commit is contained in:
ayo committed 2026-10-16 08:54:47 -04:00
1 parent 25493b3198
commit 7c5d3c9157
430 files changed
+76191

No files matched your search

+270
View File
@@ -0,0 +1,270 @@
// Expansion activations are functions of the 256 E4M3 codes, not arbitrary floats. Each row packs binary16
// sigmoid, tanh and the separate-half-op gate .5*tanh(.5*x)+.5. This avoids GLSL half transcendental lowering,
// which differs from the accuracy reference by one half ulp and then crosses normalized-store thresholds.
// Computed by gen_activation_m.py from those formulas alone (sigmoid's f32 exp2(-1.442695*x), correctly rounded
// binary16 tanh); `gen_activation_m.py --check` verifies this table. All four expansion surfaces replay
// bit-identically against the captured reset frame with it.
const uvec2 ACT[256] = uvec2[256](
uvec2(0x00003800u, 0x00003800u),
uvec2(0x18003801u, 0x00003801u),
uvec2(0x1c003802u, 0x00003802u),
uvec2(0x1e003803u, 0x00003803u),
uvec2(0x20003804u, 0x00003804u),
uvec2(0x21003805u, 0x00003805u),
uvec2(0x22003806u, 0x00003806u),
uvec2(0x23003807u, 0x00003807u),
uvec2(0x24003808u, 0x00003808u),
uvec2(0x24803809u, 0x00003809u),
uvec2(0x2500380au, 0x0000380au),
uvec2(0x2580380bu, 0x0000380bu),
uvec2(0x2600380cu, 0x0000380cu),
uvec2(0x2680380du, 0x0000380du),
uvec2(0x2700380eu, 0x0000380eu),
uvec2(0x277f380fu, 0x0000380fu),
uvec2(0x27ff3810u, 0x00003810u),
uvec2(0x28803812u, 0x00003812u),
uvec2(0x28ff3814u, 0x00003814u),
uvec2(0x297f3816u, 0x00003816u),
uvec2(0x29ff3818u, 0x00003818u),
uvec2(0x2a7f381au, 0x0000381au),
uvec2(0x2afe381cu, 0x0000381cu),
uvec2(0x2b7e381eu, 0x0000381eu),
uvec2(0x2bfd3820u, 0x00003820u),
uvec2(0x2c7e3824u, 0x00003824u),
uvec2(0x2cfd3828u, 0x00003828u),
uvec2(0x2d7d382cu, 0x0000382cu),
uvec2(0x2dfc3830u, 0x00003830u),
uvec2(0x2e7a3834u, 0x00003834u),
uvec2(0x2ef93838u, 0x00003838u),
uvec2(0x2f77383cu, 0x0000383cu),
uvec2(0x2ff53840u, 0x00003840u),
uvec2(0x30783848u, 0x00003848u),
uvec2(0x30f63850u, 0x00003850u),
uvec2(0x31723858u, 0x00003858u),
uvec2(0x31ee3860u, 0x00003860u),
uvec2(0x32693868u, 0x00003868u),
uvec2(0x32e43870u, 0x00003870u),
uvec2(0x335e3877u, 0x00003877u),
uvec2(0x33d6387fu, 0x0000387fu),
uvec2(0x3463388fu, 0x0000388fu),
uvec2(0x34d8389fu, 0x0000389fu),
uvec2(0x354b38aeu, 0x000038aeu),
uvec2(0x35bc38beu, 0x000038beu),
uvec2(0x362a38cdu, 0x000038cdu),
uvec2(0x369638dcu, 0x000038dcu),
uvec2(0x36ff38ecu, 0x000038ecu),
uvec2(0x376538fbu, 0x000038fbu),
uvec2(0x38143919u, 0x00003919u),
uvec2(0x38703936u, 0x00003936u),
uvec2(0x38c53953u, 0x00003953u),
uvec2(0x3915396fu, 0x0000396fu),
uvec2(0x395e398bu, 0x0000398au),
uvec2(0x39a239a5u, 0x000039a6u),
uvec2(0x39df39c0u, 0x000039c0u),
uvec2(0x3a1839d9u, 0x000039d9u),
uvec2(0x3a793a0au, 0x00003a0au),
uvec2(0x3ac93a38u, 0x00003a38u),
uvec2(0x3b0a3a63u, 0x00003a62u),
uvec2(0x3b3e3a8au, 0x00003a8au),
uvec2(0x3b673aafu, 0x00003aafu),
uvec2(0x3b883ad1u, 0x00003ad1u),
uvec2(0x3ba23af0u, 0x00003af0u),
uvec2(0x3bb63b0cu, 0x00003b0cu),
uvec2(0x3bd33b3du, 0x00003b3cu),
uvec2(0x3be53b65u, 0x00003b64u),
uvec2(0x3bef3b85u, 0x00003b85u),
uvec2(0x3bf63b9fu, 0x00003b9fu),
uvec2(0x3bfa3bb4u, 0x00003bb4u),
uvec2(0x3bfc3bc4u, 0x00003bc4u),
uvec2(0x3bfe3bd1u, 0x00003bd1u),
uvec2(0x3bff3bdbu, 0x00003bdbu),
uvec2(0x3bff3be9u, 0x00003beau),
uvec2(0x3c003bf2u, 0x00003bf2u),
uvec2(0x3c003bf8u, 0x00003bf8u),
uvec2(0x3c003bfbu, 0x00003bfbu),
uvec2(0x3c003bfdu, 0x00003bfdu),
uvec2(0x3c003bfeu, 0x00003bfeu),
uvec2(0x3c003bffu, 0x00003bffu),
uvec2(0x3c003bffu, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x3c003c00u, 0x00003c00u),
uvec2(0x7e007e00u, 0x00007e00u),
uvec2(0x80003800u, 0x00003800u),
uvec2(0x980037feu, 0x000037feu),
uvec2(0x9c0037fcu, 0x000037fcu),
uvec2(0x9e0037fau, 0x000037fau),
uvec2(0xa00037f8u, 0x000037f8u),
uvec2(0xa10037f6u, 0x000037f6u),
uvec2(0xa20037f4u, 0x000037f4u),
uvec2(0xa30037f2u, 0x000037f2u),
uvec2(0xa40037f0u, 0x000037f0u),
uvec2(0xa48037eeu, 0x000037eeu),
uvec2(0xa50037ecu, 0x000037ecu),
uvec2(0xa58037eau, 0x000037eau),
uvec2(0xa60037e8u, 0x000037e8u),
uvec2(0xa68037e6u, 0x000037e6u),
uvec2(0xa70037e4u, 0x000037e4u),
uvec2(0xa77f37e2u, 0x000037e2u),
uvec2(0xa7ff37e0u, 0x000037e0u),
uvec2(0xa88037dcu, 0x000037dcu),
uvec2(0xa8ff37d8u, 0x000037d8u),
uvec2(0xa97f37d4u, 0x000037d4u),
uvec2(0xa9ff37d0u, 0x000037d0u),
uvec2(0xaa7f37ccu, 0x000037ccu),
uvec2(0xaafe37c8u, 0x000037c8u),
uvec2(0xab7e37c4u, 0x000037c4u),
uvec2(0xabfd37c0u, 0x000037c0u),
uvec2(0xac7e37b8u, 0x000037b8u),
uvec2(0xacfd37b0u, 0x000037b0u),
uvec2(0xad7d37a8u, 0x000037a8u),
uvec2(0xadfc37a0u, 0x000037a0u),
uvec2(0xae7a3798u, 0x00003798u),
uvec2(0xaef93790u, 0x00003790u),
uvec2(0xaf773788u, 0x00003788u),
uvec2(0xaff53780u, 0x00003780u),
uvec2(0xb0783770u, 0x00003770u),
uvec2(0xb0f63760u, 0x00003760u),
uvec2(0xb1723750u, 0x00003750u),
uvec2(0xb1ee3741u, 0x00003740u),
uvec2(0xb2693731u, 0x00003731u),
uvec2(0xb2e43721u, 0x00003721u),
uvec2(0xb35e3711u, 0x00003711u),
uvec2(0xb3d63701u, 0x00003701u),
uvec2(0xb46336e2u, 0x000036e2u),
uvec2(0xb4d836c3u, 0x000036c2u),
uvec2(0xb54b36a3u, 0x000036a4u),
uvec2(0xb5bc3684u, 0x00003684u),
uvec2(0xb62a3666u, 0x00003666u),
uvec2(0xb6963647u, 0x00003647u),
uvec2(0xb6ff3629u, 0x00003628u),
uvec2(0xb765360au, 0x0000360au),
uvec2(0xb81435cfu, 0x000035ceu),
uvec2(0xb8703594u, 0x00003594u),
uvec2(0xb8c5355au, 0x0000355au),
uvec2(0xb9153522u, 0x00003522u),
uvec2(0xb95e34ebu, 0x000034ebu),
uvec2(0xb9a234b5u, 0x000034b5u),
uvec2(0xb9df3481u, 0x00003480u),
uvec2(0xba18344eu, 0x0000344eu),
uvec2(0xba7933d8u, 0x000033d8u),
uvec2(0xbac93320u, 0x00003320u),
uvec2(0xbb0a3275u, 0x00003276u),
uvec2(0xbb3e31d6u, 0x000031d6u),
uvec2(0xbb673144u, 0x00003144u),
uvec2(0xbb8830bdu, 0x000030bcu),
uvec2(0xbba23041u, 0x00003042u),
uvec2(0xbbb62fa1u, 0x00002fa0u),
uvec2(0xbbd32e1au, 0x00002e1cu),
uvec2(0xbbe52cdbu, 0x00002cdcu),
uvec2(0xbbef2bb1u, 0x00002bb0u),
uvec2(0xbbf62a12u, 0x00002a10u),
uvec2(0xbbfa28c7u, 0x000028c8u),
uvec2(0xbbfc2781u, 0x00002780u),
uvec2(0xbbfe25e2u, 0x000025e0u),
uvec2(0xbbff249bu, 0x000024a0u),
uvec2(0xbbff21a0u, 0x000021a0u),
uvec2(0xbc001edau, 0x00001ec0u),
uvec2(0xbc001c2bu, 0x00001c40u),
uvec2(0xbc001910u, 0x00001900u),
uvec2(0xbc001626u, 0x00001600u),
uvec2(0xbc001377u, 0x00001400u),
uvec2(0xbc001087u, 0x00001000u),
uvec2(0xbc000d7fu, 0x00000c00u),
uvec2(0xbc00080bu, 0x00000c00u),
uvec2(0xbc0002fau, 0x00000000u),
uvec2(0xbc000118u, 0x00000000u),
uvec2(0xbc000067u, 0x00000000u),
uvec2(0xbc000026u, 0x00000000u),
uvec2(0xbc00000eu, 0x00000000u),
uvec2(0xbc000005u, 0x00000000u),
uvec2(0xbc000002u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0xbc000000u, 0x00000000u),
uvec2(0x7e00fe00u, 0x00007e00u)
);
uint actIndex(float16_t v) { uint h = uint(float16BitsToUint16(v)); uint a = h & 32767u; if (a > 0x7c00u) return ((h >> 8u) & 128u) | 127u; return ((h >> 8u) & 128u) | (a >= 0x2400u ? (a >> 7u) - 64u : uint(abs(float(v)) * 512.0)); }
float16_t sig16(float16_t v) { return uint16BitsToFloat16(uint16_t(ACT[actIndex(v)].x & 65535u)); }
float16_t tan16(float16_t v) { return uint16BitsToFloat16(uint16_t(ACT[actIndex(v)].x >> 16u)); }
float16_t gate16(float16_t v) { return uint16BitsToFloat16(uint16_t(ACT[actIndex(v)].y)); }
f16vec4 tan16(f16vec4 v) { return f16vec4(tan16(v.x),tan16(v.y),tan16(v.z),tan16(v.w)); }
f16vec4 gate16(f16vec4 v) { return f16vec4(gate16(v.x),gate16(v.y),gate16(v.z),gate16(v.w)); }