A: expf fmaf 180296c80 + rt_div_tables vpermps dump

dsp/fn529fe0.cpp

@@ -1,7 +1,34 @@
 #include "fn529fe0.hpp"
+#include "rt_div_tables.hpp"
 #include <cmath>
 #include <algorithm>
 #include <cstring>
+#include <cfenv>
+
+namespace {
+inline float expf_180296c80(float x) {
+    // BLOCKMAP:569 expf FLOAT 180296c80 — n=fma(1.44269502,x,12582912), k=n-MAGIC,
+    // r=(x-0.69314718*k)-1.42861e-06*k, p=(((0.00829172*r+0.0418735)*r+0.166674)*r+0.499994)*r+1)*r+1
+    // out = bits((k<<23)+bits(p)), guard |x|>87.3365 slow
+    if (std::abs(x) > 87.3365478515625f) return std::exp(x);
+    const float LOG2E = 1.44269502f;
+    const float MAGIC = 12582912.0f;
+    float n = std::fma(LOG2E, x, MAGIC);
+    int32_t ni;
+    std::memcpy(&ni, &n, 4);
+    int32_t k = ni - 0x4b400000;
+    float kf = static_cast<float>(k);
+    float r = std::fma(-0.69314718f, kf, x);
+    r = std::fma(-1.428606e-06f, kf, r);
+    float p = std::fma(0.00829172f, r, 0.0418735f);
+    p = std::fma(p, r, 0.166674f);
+    p = std::fma(p, r, 0.499994f);
+    p = std::fma(p, r, 1.0f);
+    p = std::fma(p, r, 1.0f);
+    // scale by 2^k
+    return std::ldexp(p, k);
+}
+}
 
 // Structural mask-apply chain FUN_180529fe0 (mono path). Step-by-step
 // transcription; each component is a pure function so it can be unit-tested and
@@ -180,12 +207,12 @@ void chain_9_19(float* bands, float* tmp6f8, float* accVec,
         tmp6f8[i] += rel[i] * accVec[i]; // lower
     }
     // 14: EXP#1 180296c80 expf + +=(-1) th2270 (24mm2 order fix)
-    for (size_t i = 0; i < nbin; i++) bands[i] = std::exp(bands[i]) - 1.0f;
+    for (size_t i = 0; i < nbin; i++) bands[i] = expf_180296c80(bands[i]) - 1.0f;
     // 15: array-mul track*  th2000
     // 16: *=kWarp + LOG#2 140980 (placeholder warp already passed)
     for (size_t i = 0; i < nbin; i++) bands[i] *= warp[i];
     // 17: EXP#2 + exp-variant 140a40/140b00
-    for (size_t i = 0; i < nbin; i++) bands[i] = std::exp(bands[i]);
+    for (size_t i = 0; i < nbin; i++) bands[i] = expf_180296c80(bands[i]);
 }
 
 // ---- Legacy structural chain (pre-cascade) ---------------------------------

dsp/rt_div_tables.hpp

@@ -0,0 +1,14 @@
+#pragma once
+// DIVIDE 1803a06a0 tables from .rdata RVA 0x21269c0/0x2126a00 poly 0.207
+// BLOCKMAP:580 vpermps+poly 1c dump
+// extracted via PE .rdata .rdata VA 0x1baa000 raw 0x1ba8400
+
+#include <array>
+namespace rt_div {
+constexpr std::array<float,32> tbl_1269c0 = {
+127.0f,126.830078f,126.67807f,126.540558f,126.415039f,126.299561f,126.192642f,126.093109f,127.0f,126.830078f,126.67807f,126.540558f,126.415039f,126.299561f,126.192642f,126.093109f,0.0f,-3.12644238e-06f,1.8367532e-06f,1.05200343e-05f,-1.56322119e-06f,-2.65016098e-07f,2.86602835e-06f,2.73532123e-07f,0.0f,-3.12644238e-06f,1.8367532e-06f,1.05200343e-05f,-1.56322119e-06f,-2.65016098e-07f,2.86602835e-06f,2.73532123e-07f};
+constexpr std::array<float,32> tbl_126a00 = {
+0.0f,-3.12644238e-06f,1.8367532e-06f,1.05200343e-05f,-1.56322119e-06f,-2.65016098e-07f,2.86602835e-06f,2.73532123e-07f,0.0f,-3.12644238e-06f,1.8367532e-06f,1.05200343e-05f,-1.56322119e-06f,-2.65016098e-07f,2.86602835e-06f,2.73532123e-07f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.0f,0.0f,0.0f,0.0f,0.0f,0.0f,0.0f,0.0f};
+constexpr std::array<float,8> poly_0 = {
+0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f,0.20751521f};
+}