woutermans
798e25611c
Patch 0011 merges a complete accumulator-register pair overwrite into one shadow-layout conversion (reads, rewritten shadow accesses and block boundaries prevent it; partial writes keep read/modify/write), and requests eight waves per SIMD for gfx12 native-FP8 functions. Patch 0012 keeps signs in the native conversion: finite overflow clamped, NaNs mapped to signed infinity, post-conversion sign masks gone; plain and ReLU remain exhaustive-table identical to the software codec. Eighty-frame harness at 720p->4K, excluding the first twenty: control 24.764 ms, coalescing 23.340 ms, plus eight waves 20.135 ms, plus signed conversion 16.234 ms (15.144 ms with the harness idle gap removed); all eighty saved frames byte-identical to the matching control. Twelve- and ten-wave budgets regress (25.56/24.61 ms); fast math changes the image (18.92 ms) and is not selected.
35 lines
2.2 KiB
Diff
35 lines
2.2 KiB
Diff
diff --git a/ptx/lib/zluda_ptx_impl.cpp b/ptx/lib/zluda_ptx_impl.cpp
|
|
--- a/ptx/lib/zluda_ptx_impl.cpp
|
|
+++ b/ptx/lib/zluda_ptx_impl.cpp
|
|
@@ -877,21 +877,18 @@
|
|
typedef _Float16 half_vector __attribute__((ext_vector_type(2)));
|
|
typedef uint16_t magnitude_vector __attribute__((ext_vector_type(2)));
|
|
const uint32_t bits = std::bit_cast<uint32_t>(input);
|
|
- // Positive half encodings are ordered by magnitude. Clamp both lanes
|
|
- // with one packed integer min, then retain NaNs as positive quiet NaNs.
|
|
- // Restore original signs after conversion, including negative zero.
|
|
const magnitude_vector magnitude = std::bit_cast<magnitude_vector>(bits & 0x7fff7fffu);
|
|
- const magnitude_vector saturated =
|
|
+ // Clamp finite overflow and infinities explicitly. Map NaNs to signed
|
|
+ // infinity: native infinity encodes as 0x7f/0xff, whereas native NaN is
|
|
+ // always 0xff. This preserves the sign without post-conversion masks.
|
|
+ const magnitude_vector bounded =
|
|
__builtin_elementwise_min(magnitude, magnitude_vector{0x5f00u, 0x5f00u});
|
|
const magnitude_vector kept{
|
|
- magnitude[0] > 0x7c00u ? uint16_t(0x7e00u) : saturated[0],
|
|
- magnitude[1] > 0x7c00u ? uint16_t(0x7e00u) : saturated[1]};
|
|
- const half_vector halves = std::bit_cast<half_vector>(kept);
|
|
- const float x = float(halves[0]), y = float(halves[1]);
|
|
- const uint32_t encoded = d4r_cvt_pk_fp8_f32(x, y, 0, false);
|
|
- // AMD canonicalizes NaNs to 0xff. PTX retains each input's sign.
|
|
- const uint16_t packed = uint16_t((encoded & 0x7f7fu) |
|
|
- ((bits >> 8) & 0x80u) | ((bits >> 16) & 0x8000u));
|
|
+ magnitude[0] > 0x7c00u ? uint16_t(0x7c00u) : bounded[0],
|
|
+ magnitude[1] > 0x7c00u ? uint16_t(0x7c00u) : bounded[1]};
|
|
+ const uint32_t signed_bits = std::bit_cast<uint32_t>(kept) | (bits & 0x80008000u);
|
|
+ const half_vector halves = std::bit_cast<half_vector>(signed_bits);
|
|
+ const uint16_t packed = uint16_t(d4r_cvt_pk_fp8_f32(float(halves[0]), float(halves[1]), 0, false));
|
|
return std::bit_cast<Fp8x2>(packed);
|
|
}
|
|
|