diff --git a/CMakeLists.txt b/CMakeLists.txt
index cb07a13..1f10f1b 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -392,6 +392,7 @@ endif()
 add_library(daedalus_core STATIC
     src/daedalus_core.c
     src/h264_chroma_dc.c
+    src/h264_intra_pred_4x4.c
     src/v3d_runner.c
     ${FFASM_SOURCES}
     ${FFASM_LPF_SOURCES}
@@ -538,13 +539,12 @@ add_executable(test_api_opportunistic_qpu tests/test_api_opportunistic_qpu.c)
 target_link_libraries(test_api_opportunistic_qpu PRIVATE daedalus_core)
 target_compile_options(test_api_opportunistic_qpu PRIVATE -O2)
 
-# H.264 Intra_4x4 luma prediction (9 modes) — reference + tests.
-# Pure CPU + spec-derived; no daedalus_core dependency yet (this is
-# the bit-exact gate for the eventual shader / dispatch wiring).
-add_executable(test_intra_pred_4x4
-    tests/test_intra_pred_4x4.c
-    tests/h264_intra_pred_4x4_ref.c
-)
+# H.264 Intra_4x4 luma prediction (9 modes) — public src primitives.
+# The bodies now live in src/h264_intra_pred_4x4.c (linked into
+# daedalus_core for use by libavcodec.so substitution-arc consumers).
+# This test exercises the public symbols.
+add_executable(test_intra_pred_4x4 tests/test_intra_pred_4x4.c)
+target_link_libraries(test_intra_pred_4x4 PRIVATE daedalus_core)
 target_compile_options(test_intra_pred_4x4 PRIVATE -O2)
 
 # H.264 Intra_16x16 luma prediction (4 modes: V, H, DC, Plane) —
diff --git a/include/daedalus.h b/include/daedalus.h
index 0a565d2..cd76602 100644
--- a/include/daedalus.h
+++ b/include/daedalus.h
@@ -559,6 +559,33 @@ DECLARE_QPEL_AVG(avg_mc33)
  * ----------------------------------------------------------------- */
 void daedalus_h264_chroma_dc_hadamard_2x2(int16_t c[4]);
 
+/* -------------------------------------------------------------------
+ * H.264 Intra_4x4 luma prediction (per H.264 §8.3.1.4).  9 modes.
+ *
+ * Pure CPU primitives — each is a small straightforward fill of a
+ * 4x4 output block from neighbour pixels in the same buffer.  No
+ * substrate-dispatch wrapper (the work is too small to amortise).
+ *
+ * FFmpeg-style interface: `dst` at row 0 col 0 of the 4x4 output.
+ * Reads top-left at dst[-stride-1], top at dst[-stride..-stride+7]
+ * (top-right for DDL/VL), and left at dst[r*stride - 1] for r=0..3.
+ * Caller must ensure all 13 neighbour bytes are valid (interior-MB
+ * assumption — H.264 availability fallback handled at caller).
+ *
+ * Bit-exact validated against tests/test_intra_pred_4x4.c (10-case
+ * spec-derived test suite including the asymmetric Vertical_Right
+ * 16-cell hand-derived case; see fourier PR #12).
+ * ----------------------------------------------------------------- */
+void daedalus_h264_pred_4x4_vertical  (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_horizontal(uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_dc        (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_ddl       (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_ddr       (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_vr        (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_hd        (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_vl        (uint8_t *dst, ptrdiff_t stride);
+void daedalus_h264_pred_4x4_hu        (uint8_t *dst, ptrdiff_t stride);
+
 /* -------------------------------------------------------------------
  * Recipe query — what does the API recommend for each kernel?
  * ----------------------------------------------------------------- */
diff --git a/tests/h264_intra_pred_4x4_ref.c b/src/h264_intra_pred_4x4.c
similarity index 92%
rename from tests/h264_intra_pred_4x4_ref.c
rename to src/h264_intra_pred_4x4.c
index 6cec9ba..bb1db7d 100644
--- a/tests/h264_intra_pred_4x4_ref.c
+++ b/src/h264_intra_pred_4x4.c
@@ -52,7 +52,7 @@ static inline uint8_t avg2(int a, int b)
 }
 
 /* Mode 0 — Vertical: each col = top[col]. */
-void daedalus_h264_pred_4x4_vertical_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_vertical(uint8_t *dst, ptrdiff_t stride)
 {
     const uint8_t *top = dst - stride;
     for (int r = 0; r < 4; r++) {
@@ -61,7 +61,7 @@ void daedalus_h264_pred_4x4_vertical_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 1 — Horizontal: each row = left[row]. */
-void daedalus_h264_pred_4x4_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_horizontal(uint8_t *dst, ptrdiff_t stride)
 {
     for (int r = 0; r < 4; r++) {
         uint8_t l = dst[r * stride - 1];
@@ -70,7 +70,7 @@ void daedalus_h264_pred_4x4_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 2 — DC: mean of top 4 + left 4, broadcast. */
-void daedalus_h264_pred_4x4_dc_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_dc(uint8_t *dst, ptrdiff_t stride)
 {
     const uint8_t *top = dst - stride;
     int sum = 4;  /* rounding for ((sum + 4) >> 3) */
@@ -82,7 +82,7 @@ void daedalus_h264_pred_4x4_dc_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 3 — Diagonal_Down_Left.  Uses top[0..7] (incl. top-right). */
-void daedalus_h264_pred_4x4_ddl_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_ddl(uint8_t *dst, ptrdiff_t stride)
 {
     const uint8_t *top = dst - stride;
     int t0 = top[0], t1 = top[1], t2 = top[2], t3 = top[3];
@@ -102,7 +102,7 @@ void daedalus_h264_pred_4x4_ddl_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 4 — Diagonal_Down_Right.  Uses top-left + top[0..3] + left[0..3]. */
-void daedalus_h264_pred_4x4_ddr_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_ddr(uint8_t *dst, ptrdiff_t stride)
 {
     int tl = dst[-stride - 1];
     int t0 = dst[-stride + 0], t1 = dst[-stride + 1];
@@ -123,7 +123,7 @@ void daedalus_h264_pred_4x4_ddr_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 5 — Vertical_Right. */
-void daedalus_h264_pred_4x4_vr_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_vr(uint8_t *dst, ptrdiff_t stride)
 {
     int tl = dst[-stride - 1];
     int t0 = dst[-stride + 0], t1 = dst[-stride + 1];
@@ -153,7 +153,7 @@ void daedalus_h264_pred_4x4_vr_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 6 — Horizontal_Down. */
-void daedalus_h264_pred_4x4_hd_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_hd(uint8_t *dst, ptrdiff_t stride)
 {
     int tl = dst[-stride - 1];
     int t0 = dst[-stride + 0], t1 = dst[-stride + 1], t2 = dst[-stride + 2];
@@ -182,7 +182,7 @@ void daedalus_h264_pred_4x4_hd_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 7 — Vertical_Left.  Uses top[0..7]. */
-void daedalus_h264_pred_4x4_vl_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_vl(uint8_t *dst, ptrdiff_t stride)
 {
     const uint8_t *top = dst - stride;
     int t0=top[0], t1=top[1], t2=top[2], t3=top[3];
@@ -211,7 +211,7 @@ void daedalus_h264_pred_4x4_vl_ref(uint8_t *dst, ptrdiff_t stride)
 }
 
 /* Mode 8 — Horizontal_Up.  Uses left[0..3] only. */
-void daedalus_h264_pred_4x4_hu_ref(uint8_t *dst, ptrdiff_t stride)
+void daedalus_h264_pred_4x4_hu(uint8_t *dst, ptrdiff_t stride)
 {
     int l0 = dst[ 0*stride - 1], l1 = dst[ 1*stride - 1];
     int l2 = dst[ 2*stride - 1], l3 = dst[ 3*stride - 1];
diff --git a/tests/test_intra_pred_4x4.c b/tests/test_intra_pred_4x4.c
index 2a44c1d..07afe10 100644
--- a/tests/test_intra_pred_4x4.c
+++ b/tests/test_intra_pred_4x4.c
@@ -22,15 +22,15 @@
 #include <stdio.h>
 #include <string.h>
 
-extern void daedalus_h264_pred_4x4_vertical_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_horizontal_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_dc_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_ddl_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_ddr_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_vr_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_hd_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_vl_ref(uint8_t *dst, ptrdiff_t stride);
-extern void daedalus_h264_pred_4x4_hu_ref(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_vertical(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_horizontal(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_dc(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_ddl(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_ddr(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_vr(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_hd(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_vl(uint8_t *dst, ptrdiff_t stride);
+extern void daedalus_h264_pred_4x4_hu(uint8_t *dst, ptrdiff_t stride);
 
 #define STRIDE 9
 typedef void (*pred_fn)(uint8_t *dst, ptrdiff_t stride);
@@ -82,7 +82,7 @@ int main(void)
         int t[8] = { 10, 20, 30, 40,  0, 0, 0, 0 };
         int l[4] = {  0,  0,  0,  0 };
         set_ctx(buf, tl, t, l);
-        daedalus_h264_pred_4x4_vertical_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_vertical(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {10,20,30,40}, {10,20,30,40}, {10,20,30,40}, {10,20,30,40}
         };
@@ -95,7 +95,7 @@ int main(void)
         int t[8] = { 0,0,0,0, 0,0,0,0 };
         int l[4] = { 50, 60, 70, 80 };
         set_ctx(buf, 0, t, l);
-        daedalus_h264_pred_4x4_horizontal_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_horizontal(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {50,50,50,50}, {60,60,60,60}, {70,70,70,70}, {80,80,80,80}
         };
@@ -110,7 +110,7 @@ int main(void)
         int t[8] = { 1,1,1,1, 0,0,0,0 };
         int l[4] = { 3,3,3,3 };
         set_ctx(buf, 99, t, l);   /* tl unused for DC */
-        daedalus_h264_pred_4x4_dc_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_dc(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {2,2,2,2}, {2,2,2,2}, {2,2,2,2}, {2,2,2,2}
         };
@@ -125,7 +125,7 @@ int main(void)
         int t[8] = { 100,100,100,100, 100,100,100,100 };
         int l[4] = { 0,0,0,0 };
         set_ctx(buf, 0, t, l);
-        daedalus_h264_pred_4x4_ddl_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_ddl(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {100,100,100,100}, {100,100,100,100},
             {100,100,100,100}, {100,100,100,100}
@@ -140,7 +140,7 @@ int main(void)
         int t[8] = { 200,200,200,200, 0,0,0,0 };
         int l[4] = { 200,200,200,200 };
         set_ctx(buf, 200, t, l);
-        daedalus_h264_pred_4x4_ddr_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_ddr(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {200,200,200,200}, {200,200,200,200},
             {200,200,200,200}, {200,200,200,200}
@@ -155,7 +155,7 @@ int main(void)
         int t[8] = { 80,80,80,80, 0,0,0,0 };
         int l[4] = { 80,80,80,80 };
         set_ctx(buf, 80, t, l);
-        daedalus_h264_pred_4x4_vr_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_vr(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {80,80,80,80}, {80,80,80,80}, {80,80,80,80}, {80,80,80,80}
         };
@@ -168,7 +168,7 @@ int main(void)
         int t[8] = { 120,120,120,120, 0,0,0,0 };
         int l[4] = { 120,120,120,120 };
         set_ctx(buf, 120, t, l);
-        daedalus_h264_pred_4x4_hd_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_hd(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {120,120,120,120}, {120,120,120,120},
             {120,120,120,120}, {120,120,120,120}
@@ -182,7 +182,7 @@ int main(void)
         int t[8] = { 64,64,64,64, 64,64,64,64 };
         int l[4] = { 0,0,0,0 };
         set_ctx(buf, 0, t, l);
-        daedalus_h264_pred_4x4_vl_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_vl(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {64,64,64,64}, {64,64,64,64}, {64,64,64,64}, {64,64,64,64}
         };
@@ -195,7 +195,7 @@ int main(void)
         int t[8] = { 0,0,0,0, 0,0,0,0 };
         int l[4] = { 200,200,200,200 };
         set_ctx(buf, 0, t, l);
-        daedalus_h264_pred_4x4_hu_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_hu(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             {200,200,200,200}, {200,200,200,200},
             {200,200,200,200}, {200,200,200,200}
@@ -230,7 +230,7 @@ int main(void)
         int t[8] = { 10,20,30,40, 0,0,0,0 };
         int l[4] = { 50,60,70,0 };
         set_ctx(buf, 5, t, l);
-        daedalus_h264_pred_4x4_vr_ref(&buf[1][1], STRIDE);
+        daedalus_h264_pred_4x4_vr(&buf[1][1], STRIDE);
         uint8_t exp[4][4] = {
             { 8,15,25,35},
             {18,11,20,30},