C  CONV2D_FP64 — 2D convolution, double-precision floating point,
C  single-image, multi-channel input, multi-filter output.
C  Stride 1, no padding (valid convolution).
C
C  Reference: standard textbook formulation; see e.g.
C  Goodfellow, Bengio, Courville, "Deep Learning" (2016), ch. 9.
C  Equivalent shape to cuDNN's CUDNN_TENSOR_NCHW direct convolution
C  with stride 1 and zero padding.
C
C  Hand-written reference for the Dark Factory's Phase 3 inference
C  kernel ladder, 2026-05-24. Public domain.
C
C  Mathematical definition (valid convolution):
C    For every output position (OC, OH, OW):
C      Y(OC, OH, OW) = sum over (IC, KR, KS) of
C                        X(IC, OH + KR - 1, OW + KS - 1)
C                          * KER(OC, IC, KR, KS)
C  with IC in 1..C, KR in 1..KH, KS in 1..KW.
C
C  Shapes (column-major Fortran):
C    X   is C  x H  x W                   (input feature map)
C    KER is OC x C  x KH x KW             (filter bank)
C    Y   is OC x HO x WO                  (output feature map)
C  where HO = H - KH + 1, WO = W - KW + 1.
C
C  Overflow note: each output element is a sum of C * KH * KW
C  double-precision products. For typical inputs this is well
C  within IEEE_754 binary64 dynamic range; no special handling.

      SUBROUTINE CONV2D_FP64
     +   (H, W, C, KH, KW, OC, X, KER, Y)
C  Inputs:
C    H, W      — input feature-map height and width (positive)
C    C         — input channel count (positive)
C    KH, KW    — kernel height and width (positive, KH <= H, KW <= W)
C    OC        — output channel count (positive)
C    X         — C x H x W input feature map
C    KER       — OC x C x KH x KW filter bank
C  Output:
C    Y         — OC x (H - KH + 1) x (W - KW + 1) output feature map
      INTEGER H, W, C, KH, KW, OC
      DOUBLE PRECISION X(C, H, W)
      DOUBLE PRECISION KER(OC, C, KH, KW)
      DOUBLE PRECISION Y(OC, H - KH + 1, W - KW + 1)
      INTEGER OF, OH, OW, IC, KR, KS, HO, WO
      DOUBLE PRECISION ACC
      HO = H - KH + 1
      WO = W - KW + 1
      DO 50 OF = 1, OC
         DO 40 OH = 1, HO
            DO 30 OW = 1, WO
               ACC = 0.0D0
               DO 20 IC = 1, C
                  DO 15 KR = 1, KH
                     DO 10 KS = 1, KW
                        ACC = ACC
     +                      + X(IC, OH + KR - 1, OW + KS - 1)
     +                        * KER(OF, IC, KR, KS)
   10                CONTINUE
   15             CONTINUE
   20          CONTINUE
               Y(OF, OH, OW) = ACC
   30       CONTINUE
   40    CONTINUE
   50 CONTINUE
      RETURN
      END