more intiution...

code/duffle/atom_dsl.h

@@ -459,4 +459,9 @@
  * ============================================================================*/
 
 #define atom_offset(F, T) atom_offset_ ## F ## _ ## T
-#define atom_label(name) /* anchor — see metaprogram documentation */
+/* atom_label is a pure annotation for the metaprogram's offset calculations.
+ * The macro expands to a C comment, so the C preprocessor strips it to
+ * whitespace — NO instruction word is emitted in the asm. The metaprogram
+ * still recognises the literal `atom_label(name)` token in source and
+ * records the marker at the current pos. */
+#define atom_label(name) /* atom_label anchor: name */

code/duffle/gte.h

@@ -1,4 +1,4 @@
-/* ============================================================================
+/* ============================================================================
  *  duffle DSL Suffix Conventions
  *  ============================================================================
  *
@@ -442,6 +442,7 @@ enum { _C2_TX_SUBS_ = 0
 #define gte_cmdw_op     (gte_cmd_base | enc_gte_cmd(gte_cmd_op   ))
 #define gte_cmdw_mvmva  (gte_cmd_base | enc_gte_cmd(gte_cmd_mvmva))
 
+#define gte_cmdw_rotate_translate_perspective_single gte_cmdw_rtps
 #define gte_cmdw_rotate_translate_perspective_triple gte_cmdw_rtpt
 
 /* PsyQ compatibility bits for AVSZ3 (Bits 20, 22, 24 must be set) */
@@ -457,6 +458,8 @@ enum { _C2_TX_SUBS_ = 0
 #define gte_cmd_avsz4 0x2E
 #define gte_cmdw_avsz4 (gte_cmd_base | enc_gte_cmd(gte_cmd_avsz4) | gte_cmdw_psyq_avsz3_compat)
 
+#define gte_cmdw_avg_sort_z4 gte_cmdw_avsz4
+
 /**
  * @brief Loads a single SVECTOR to GTE vector register V0
  *

code/duffle/lottes_tape.h

@@ -119,21 +119,66 @@ FI_ Slice_U4 tb_slice(TapeBuilder  tb) {                             return (Sli
 	, shift_lright(R_AT, R_AT,         S_(polytag_len_bits)) \
 	, store_word(  R_AT, R_T1,         O_(PolyTag,bf_addr_len)) /* OrderingTable[OTZ] = PrimCursor */
 
+/* Words: 3; Emits one (cmd|color) word to R_PrimCursor at the given
+ * byte offset. Internal helper used by the *_format_*_color macros.
+ * Args: off = U4 byte offset, code = GP0 cmd byte (0 for c1/c2/c3 of
+ * a Poly_G4), r/g/b = 8-bit RGB byte values. */
+#define mac_pack_color_word(off, code, r,g,b) \
+		load_upper_i(R_AT, (code) << 8  | (b))    \
+	, or_i_self(   R_AT, ((g)   << 8) | (r))    \
+	, store_word(  R_AT, R_PrimCursor, (off))
+
 /* Words: 3; Emits the F3 command+color word (cmd byte | BLUE | GREEN | RED)
  * Args: _r, _g, _b are 8-bit RGB byte values (not raw 16-bit fields).
  * Migrated from hello_gte_tape.c; takes RGB form per the Phase 3
  * convention. */
-#define mac_format_f3_color(r,g,b)                  \
-	  load_upper_i(R_AT, gp0_cmd_poly_f3 << 8  | (b)) \
-	, or_i_self(   R_AT, ((g)            << 8) | (r)) \
-	, store_word(  R_AT, R_PrimCursor, O_(Poly_F3,color))
+#define mac_format_f3_color(r,g,b) mac_pack_color_word(O_(Poly_F3,color), gp0_cmd_poly_f3, r,g,b)
 
-/* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices to the F3 */
-#define mac_gte_store_f3() \
-	  gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_F3,p0)) \
+/* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices to the F3.
+ * PIPELINE: post-RTPT (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen).
+ * The macro name declares the pipeline position; check #6 (GTE state-
+ * machine validation) verifies the call site matches the declaration. */
+#define mac_gte_store_f3_post_rtpt() \
+		gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_F3,p0)) \
 	, gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_F3,p1)) \
 	, gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_F3,p2))
 
+/* Words: 12; Emits the four (code|color) words of a Poly_G4.
+ * Args: rN,gN,bN are 8-bit RGB byte values for each of the 4 vertices. */
+#define mac_format_g4_color(r0,g0,b0, r1,g1,b1, r2,g2,b2, r3,g3,b3)  \
+		mac_pack_color_word(O_(Poly_G4,c0), gp0_cmd_poly_g4, r0,g0,b0) \
+	, mac_pack_color_word(O_(Poly_G4,c1), 0,               r1,g1,b1) \
+	, mac_pack_color_word(O_(Poly_G4,c2), 0,               r2,g2,b2) \
+	, mac_pack_color_word(O_(Poly_G4,c3), 0,               r3,g3,b3)
+
+/* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices of the
+ * G4 triangle portion to p0/p1/p2.
+ * PIPELINE: post-RTPT, pre-RTPS (SXY0=v0.screen, SXY1=v1.screen,
+ * SXY2=v2.screen). MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2
+ * get overwritten with v3 (RTPS writes only to SXY2, but to keep the
+ * three registers aligned with v0/v1/v2 you must store before RTPS).
+ * The macro name declares the pipeline position; check #6 (GTE state-
+ * machine validation) verifies the call site matches the declaration. */
+#define mac_gte_store_g4_p012_post_rtpt_pre_rtps() \
+		gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_G4,p0))  \
+	, gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_G4,p1))  \
+	, gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p2))
+
+/* Words: 1; Stores the V3 screen coord to the G4's p3 slot.
+ * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its
+ * single-vertex result to SXY2; SXY0 still holds v0.screen from the
+ * earlier RTPT — DO NOT read SXY0 here, that's the bug this name
+ * prevents).
+ * The macro name declares the pipeline position; check #6 (GTE state-
+ * machine validation) verifies the call site matches the declaration.
+ *
+ * History: this macro was named `mac_gte_store_g4_p3` until 2026-07-09
+ * when it was discovered to be reading C2_SXY0 (which held v0.screen)
+ * instead of C2_SXY2 (which holds v3.screen after RTPS). The rename
+ * encodes the pipeline position in the name so the next bug of this
+ * class is impossible. */
+#define mac_gte_store_g4_p3_post_rtps() gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3))
+
 #pragma endregion Macro Atom Components
 
 #pragma region Mips Atom Builder

code/gte_hello/gen/hello_gte_tape.offsets.h

@@ -5,14 +5,24 @@
 #pragma region hello_gte_tape
 
 
-// --- atom: floor_tri (49 words) ---
+// --- atom: cube_g4_face (87 words) ---
 
-#define _atom_offset_culling_floor_tri_exit           15
-#define _atom_offset_bounds_chk_floor_tri_exit        3
+#define _atom_offset_cull_cube_g4_face_exit           48
+#define _atom_offset_bounds_chk_cube_g4_face_exit     12
 
 enum {
-    atom_offset_culling_floor_tri_exit = _atom_offset_culling_floor_tri_exit,
-    atom_offset_bounds_chk_floor_tri_exit = _atom_offset_bounds_chk_floor_tri_exit,
+    atom_offset_cull_cube_g4_face_exit = _atom_offset_cull_cube_g4_face_exit,
+    atom_offset_bounds_chk_cube_g4_face_exit = _atom_offset_bounds_chk_cube_g4_face_exit,
+};
+
+// --- atom: floor_f3_face (66 words) ---
+
+#define _atom_offset_culling_floor_f3_face_exit       29
+#define _atom_offset_bounds_chk_floor_f3_face_exit    13
+
+enum {
+    atom_offset_culling_floor_f3_face_exit = _atom_offset_culling_floor_f3_face_exit,
+    atom_offset_bounds_chk_floor_f3_face_exit = _atom_offset_bounds_chk_floor_f3_face_exit,
 };
 
 #pragma endregion hello_gte_tape

code/gte_hello/hello_gte.c

@@ -154,6 +154,10 @@ void gp_screen_init_c11(DoubleBuffer* screen_buf, S4* active_buf_id)
 
 	// Initialize and setup the GTE geometry offsets
 	geom_init();
+	// NOTE: geom_set_offset/geom_set_screen are kept as-is (the libgte versions
+	// are known to be broken in this PSYQ 4.7 build — see report 2026-07-09).
+	// The user's research wants the C-side non-tape reference to work as a
+	// known-good baseline for comparison against the tape.
 	geom_set_offset(ScreenRes_CenterX, ScreenRes_CenterY);
 	geom_set_screen(ScreenZ);
 
@@ -201,12 +205,12 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 	S4 flag; //????
 
 	// Draw Cube
-	if (1)
+	if (0)
 	{
 		m3s2_rotation   (& smem.cube.rot,    & smem.tform_world);
 		m3s2_translation(& smem.tform_world, & smem.cube.pos);
 		m3s2_scale      (& smem.tform_world, & smem.cube.scale);
-		gte_matrix_set_rotation   (& smem.tform_world);
+		// gte_matrix_set_rotation   (& smem.tform_world);
 		gte_matrix_set_translation(& smem.tform_world);
 		for (U4 face_id = 0; face_id < Cube_num_faces; face_id += 1)
 		{
@@ -241,7 +245,7 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 		smem.cube.rot.y += 30;
 	}
 	// Draw cube (tape method) - two triangles per face
-	if (0)
+	if (1)
 	{
 		m3s2_rotation   (& smem.cube.rot,    & smem.tform_world);
 		m3s2_translation(& smem.tform_world, & smem.cube.pos);
@@ -254,7 +258,7 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 
 		LP_ U4 mem_temp_tape[512]; FArena tape_arena; farena_init(& tape_arena, slice_ut_arr(mem_temp_tape));
 		TapeBuilder tb = tb_make_old(&tape_arena); tb_scope(& tb) {
-			tb_emit(& tb, code_rbind_cube_tri);
+			tb_emit(& tb, code_rbind_cube_g4_face);
 				tb_data(& tb, prim_cursor);
 				tb_data(& tb, u4_(smem.cube.faces));
 				tb_data(& tb, u4_(smem.cube.verts));
@@ -262,7 +266,7 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 
 			for (U4 i = 0; i < Cube_num_faces; i++) {
 				// Two triangles per quad face: (x,y,z) and (x,z,w)
-				tb_emit(& tb, code_cube_tri);
+				tb_emit(& tb, code_cube_g4_face);
 			}
 
 			tb_emit(& tb, code_sync_primitive_arena);
@@ -350,16 +354,16 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 			tb_emit(& tb, code_set_gte_world);
 				tb_data(& tb, u4_(& smem.tform_world));
 
-			tb_emit(& tb, code_rbind_floor_tri);
+			tb_emit(& tb, code_rbind_floor_f3_face);
 			// TODO(Ed): Just use a single context struct ref
 				tb_data(& tb, prim_cursor);
 				tb_data(& tb, u4_(smem.floor.faces));
 				tb_data(& tb, u4_(smem.floor.verts));
 				tb_data(& tb, u4_(ordering_buf));
 			for (U4 i = 0; i < Floor_num_faces; i++) {
-				tb_emit(& tb, code_floor_tri);
+				tb_emit(& tb, code_floor_f3_face);
 			}
-			// After code_floor_tri iterations complete, the primitive arena's used counter needs updating.
+			// After code_floor_f3_face iterations complete, the primitive arena's used counter needs updating.
 			tb_emit(& tb, code_sync_primitive_arena);
 				tb_data(& tb, u4_(& pa->used));
 				tb_data(& tb, prim_base);
@@ -384,7 +388,7 @@ void update(PrimitiveArena* pa, U4* ordering_buf)
 				// 2. code_diag_color -> Tests OT and Prim Arena memory
 				// 3. code_diag_gte   -> Tests Vertex arrays and GTE Math
 				// tb_emit(& tb, code_diag_yield);
-				tb_emit(& tb, code_diag_color);
+				// tb_emit(& tb, code_diag_color);
 				// tb_emit(& tb, code_diag_gte); 
 			}
 		}

code/gte_hello/hello_gte_tape.c

@@ -22,7 +22,7 @@ typedef Struct_(Binds_CubeTri) {
 	U4 VertBase;
 	U4 OtBase;
 };
-internal MipsAtom_(rbind_cube_tri) {
+internal MipsAtom_(rbind_cube_g4_face) {
 	/* Pop 4 arguments from the tape directly into the workspace registers */
 	load_word(R_PrimCursor, R_TapePtr, O_(Binds_CubeTri,PrimCursor)), 
 	load_word(R_FaceCursor, R_TapePtr, O_(Binds_CubeTri,FaceCursor)), 
@@ -35,112 +35,78 @@ internal MipsAtom_(rbind_cube_tri) {
 };
 
 /* ============================================================================
- *  cube_tri — Draw one cube face (Gouraud-shaded quad) via the GTE tape pipeline
+ *  cube_g4_face — Draw one cube face (Gouraud-shaded quad) via the GTE tape pipeline
  * ============================================================================
  *
  *  Reads 4 indices from R_FaceCur (V4_S2 = 8 bytes), loads 4 vertices into
  *  the GTE, runs the PsyQ RotAverageNclip4 sequence, and renders a Poly_G4.
  */
-	atom_region  (cube_tri, REGION_PRIM_ARENA)
-	atom_group   (cube_tri, GROUP_RENDER_PRIMS)
-	atom_cadence (cube_tri, CADENCE_FRAME)
-	atom_annot(cube_tri, phase_work,
-		tape_regs(R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase),
-		tape_regs(R_PrimCursor, R_FaceCursor))
+	atom_region  (cube_g4_face, REGION_PRIM_ARENA)
+	atom_group   (cube_g4_face, GROUP_RENDER_PRIMS)
+	atom_cadence (cube_g4_face, CADENCE_FRAME)
+	atom_annot(cube_g4_face, phase_work,
+			atom_reads( R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase),
+			atom_writes(R_PrimCursor, R_FaceCursor))
 internal 
-MipsAtom_(cube_tri) {
-	/* ── 1. Load 4 face indices from R_FaceCur ──────────────────────────── */
-	load_half_u(R_T0, R_FaceCursor, 0),  /* T0 = face->x (vertex 0 index) */
-	load_half_u(R_T1, R_FaceCursor, 2),  /* T1 = face->y (vertex 1 index) */
-	load_half_u(R_T2, R_FaceCursor, 4),  /* T2 = face->z (vertex 2 index) */
-	load_half_u(R_T3, R_FaceCursor, 6),  /* T3 = face->w (vertex 3 index) */
+MipsAtom_(cube_g4_face) {
+	/* ── 1. Load 4 face indices from R_FaceCur (V4_S2 = 8 bytes) ───────── */
+	load_half_u(R_T0, R_FaceCursor, 0 * S_(S2)),
+	load_half_u(R_T1, R_FaceCursor, 1 * S_(S2)),
+	load_half_u(R_T2, R_FaceCursor, 2 * S_(S2)),
+	load_half_u(R_T3, R_FaceCursor, 3 * S_(S2)),
 
-	/* ── 2. Load V0, V1, V2 into GTE ────────────────────────────────────── */
-	/* V0 = verts[face->x] */
-	shift_lleft(R_AT, R_T0, 3), add_u(R_AT, R_AT, R_VertBase),
-	load_word(R_V0, R_AT, 0), load_word(R_V1, R_AT, 4),
-	gte_mv_to_data_r(R_V0, C2_VXY0), gte_mv_to_data_r(R_V1, C2_VZ0),
-
-	/* V1 = verts[face->y] */
-	shift_lleft(R_AT, R_T1, 3), add_u(R_AT, R_AT, R_VertBase),
-	load_word(R_V0, R_AT, 0), load_word(R_V1, R_AT, 4),
-	gte_mv_to_data_r(R_V0, C2_VXY1), gte_mv_to_data_r(R_V1, C2_VZ1),
-
-	/* V2 = verts[face->z] */
-	shift_lleft(R_AT, R_T2, 3), add_u(R_AT, R_AT, R_VertBase),
-	load_word(R_V0, R_AT, 0), load_word(R_V1, R_AT, 4),
-	gte_mv_to_data_r(R_V0, C2_VXY2), gte_mv_to_data_r(R_V1, C2_VZ2),
+	/* ── 2. Load V0, V1, V2 into GTE (parallel to mac_load_tri_verts) ── */
+	mac_load_tri_verts(R_T0, R_T1, R_T2),
 
 	/* ── 3. RTPT — transforms V0/V1/V2 → SXY0/SXY1/SXY2 + SZ1/SZ2/SZ3 ─── */
-	nop, nop, gte_cmdw_rtpt,
+	nop2, gte_cmdw_rotate_translate_perspective_triple,
 
 	/* ── 4. NCLIP — backface culling on SXY0/SXY1/SXY2 (p0,p1,p2) ──────── */
-	/*     MUST be done BEFORE RTPS overwrites SXY0 with p3!                */
-	nop, nop, gte_cmdw_nclip,
-	nop, nop,
+	/*     MUST be done BEFORE V3-RTPS overwrites SXY0 with p3.             */
+	nop2, gte_cmdw_nclip,
 
 	/* ── 5. Cull check: skip format/insert if MAC0 ≤ 0 (backface) ───────── */
-	gte_mv_from_data_r(R_T0, C2_MAC0),
-	nop,
-	branch_le_zero(R_T0, 49),  /* Skip 49 if MAC0 ≤ 0 (backface) → cull */
-	nop,                        /* BD slot */
+	nop2,  gte_mv_from_data_r(R_T0, C2_MAC0),
+	nop,                                                          /* COP2 stall */
+	branch_le_zero(R_T0, atom_offset(cull, cube_g4_face_exit)),
+	nop,                                                          /* BD slot    */
 
-	/* ── 6. Store p0,p1,p2 to primitive buffer (BEFORE RTPS overwrites) ─── */
-	store_word(R_0, R_PrimCursor, 0),
+	/* ── 6. Format c0..c3 (color+code words) BEFORE V3-RTPS ─────────────── */
+	store_word(R_0, R_PrimCursor, O_(Poly_G4, tag)),
+	mac_format_g4_color(
+		/* c0 magenta */ 0xFF, 0x00, 0xFF,
+		/* c1 yellow  */ 0xFF, 0xFF, 0x00,
+		/* c2 cyan    */ 0x00, 0xFF, 0xFF,
+		/* c3 green   */ 0x00, 0xFF, 0x00),
 
-	/* Word 1: c0 (BGR) + code = 0x38FF00FF (magenta, opcode 0x38) */
-	load_upper_i(R_AT, 0x38FF), or_i(R_AT, R_AT, 0x00FF),
-	store_word(R_AT, R_PrimCursor, 4),
+	/* ── 7. Store p0..p2 BEFORE V3-RTPS overwrites SXY0 ─────────────────── */
+	mac_gte_store_g4_p012_post_rtpt_pre_rtps(),
 
-	/* Word 2: p0 = SXY0 (stored BEFORE RTPS overwrites it) */
-	gte_sw(C2_SXY0, R_PrimCursor, 8),
+	/* ── 8. Load V3 = verts[face->w] into V0 ─────────────────────────────── */
+	shift_lleft(R_AT, R_T3, v3s2_byteoff), add_u(R_AT, R_AT, R_VertBase),
+	load_word(R_V0, R_AT, O_(V3_S2, x)),   load_word(R_V1, R_AT, O_(V3_S2, z)),
+	gte_mv_to_data_r(R_V0, C2_VXY0),       gte_mv_to_data_r(R_V1, C2_VZ0),
 
-	/* Word 3: c1 (BGR) + pad = 0x0000FFFF (yellow) */
-	load_upper_i(R_AT, 0x0000), or_i(R_AT, R_AT, 0xFFFF),
-	store_word(R_AT, R_PrimCursor, 12),
+	/* ── 9. RTPS — transforms V0 (now V3) → SXY0 (p3) + SZ3 ─────────────── */
+	nop2, gte_cmdw_rotate_translate_perspective_single,
+	mac_gte_store_g4_p3_post_rtps(),
 
-	/* Word 4: p1 = SXY1 */
-	gte_sw(C2_SXY1, R_PrimCursor, 16),
+	/* ── 10. AVSZ4 — average Z from SZ0/SZ1/SZ2/SZ3 ─────────────────────── */
+	nop2, gte_cmdw_avg_sort_z4,
+	nop2, gte_mv_from_data_r(R_T1, C2_OTZ),
 
-	/* Word 5: c2 (BGR) + pad = 0x00FFFF00 (cyan) */
-	load_upper_i(R_AT, 0x00FF), or_i(R_AT, R_AT, 0xFF00),
-	store_word(R_AT, R_PrimCursor, 20),
+	/* ── 11. Bounds check OTZ < OrderingTbl_Len ─────────────────────────── */
+	add_ui(      R_AT, R_0,  OrderingTbl_Len),
+	set_lt_u(    R_AT, R_T1, R_AT),
+	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, cube_g4_face_exit)), nop,
 
-	/* Word 6: p2 = SXY2 */
-	gte_sw(C2_SXY2, R_PrimCursor, 24),
+	/* ── 12. Insert into Ordering Table (length = 8 words for Poly_G4) ──── */
+	mac_insert_ot_tag(R_T1, Poly_G4),
 
-	/* Word 7: c3 (BGR) + pad = 0x0000FF00 (green) */
-	load_upper_i(R_AT, 0x0000), or_i(R_AT, R_AT, 0xFF00),
-	store_word(R_AT, R_PrimCursor, 28),
-
-	/* ── 7. Load V3 = verts[face->w] into V0 ─────────────────────────────── */
-	shift_lleft(R_AT, R_T3, 3), add_u(R_AT, R_AT, R_VertBase),
-	load_word(R_V0, R_AT, 0), load_word(R_V1, R_AT, 4),
-	gte_mv_to_data_r(R_V0, C2_VXY0), gte_mv_to_data_r(R_V1, C2_VZ0),
-
-	/* ── 8. RTPS — transforms V0 (now V3) → SXY0 (p3) + SZ0 ─────────────── */
-	nop, nop, gte_cmdw_rtps,
-
-	/* Word 8: p3 = SXY0 (written AFTER RTPS with V3's screen coords) */
-	gte_sw(C2_SXY0, R_PrimCursor, 32),
-
-	/* ── 9. AVSZ4 — average Z from SZ0/SZ1/SZ2/SZ3 ────────────── */
-	nop, nop, gte_cmdw_avsz4,
-	nop, nop,
-	gte_mv_from_data_r(R_T1, C2_OTZ),
-
-	/* ── 10. Bounds check OTZ < 2048 ─────────────────────────────────────── */
-	add_ui(      R_AT, R_0,  2048),
-	set_lt_u(       R_AT, R_T1, R_AT),
-	branch_equal(R_AT, R_0,  13),  /* Skip 13 → land at add_ui(R_FaceCur,...) */
-	nop,                            /* BD slot */
-
-	/* ── 11. Insert into Ordering Table (length = 8 for Poly_G4) ─────────── */
-	mac_insert_ot_tag(R_T1, Poly_G4),  /* 0x0800 = 8 << 8 = length 8 in tag */
-
-	/* ── 12. Advance cursors & yield ─────────────────────────────────────── */
-	add_ui(R_PrimCursor, R_PrimCursor, 36),  /* 9 words × 4 bytes */
-	add_ui(R_FaceCursor, R_FaceCursor, 8),   /* 4 × S2 = 8 bytes */
+	/* ── 13. Advance cursors & yield (both branch targets land here) ────── */
+atom_label(cube_g4_face_exit)
+	add_ui_self(R_PrimCursor, S_(Poly_G4)),     /* 9 words = Poly_G4 */
+	add_ui_self(R_FaceCursor, S_(S2) * 4),      /* 4 × S2 = 8 bytes */
 	mac_yield()
 };
 
@@ -150,14 +116,14 @@ typedef Struct_(Binds_FloorTri) {
 	U4 VertBase;
 	U4 OtBase;
 };
-	atom_region(rbind_floor_tri, REGION_PRIM_ARENA)
-	atom_group(rbind_floor_tri, GROUP_RENDER_FLOOR)
-	atom_cadence(rbind_floor_tri, CADENCE_FRAME)
-	atom_annot(rbind_floor_tri, phase_bind
+	atom_region(rbind_floor_f3_face, REGION_PRIM_ARENA)
+	atom_group(rbind_floor_f3_face, GROUP_RENDER_FLOOR)
+	atom_cadence(rbind_floor_f3_face, CADENCE_FRAME)
+	atom_annot(rbind_floor_f3_face, phase_bind
 		, atom_reads()
 		, atom_writes(R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase))
 internal 
-MipsAtom_(rbind_floor_tri) {
+MipsAtom_(rbind_floor_f3_face) {
 	/* Pop 4 arguments from the tape directly into the workspace registers */
 	load_word(R_PrimCursor, R_TapePtr, O_(Binds_FloorTri,PrimCursor)), 
 	load_word(R_FaceCursor, R_TapePtr, O_(Binds_FloorTri,FaceCursor)), 
@@ -167,27 +133,27 @@ MipsAtom_(rbind_floor_tri) {
 	mac_yield()
 };
 
-	atom_region( floor_tri, REGION_PRIM_ARENA)
-	atom_group(  floor_tri, GROUP_RENDER_FLOOR)
-	atom_cadence(floor_tri, CADENCE_FRAME)
-	atom_annot(  floor_tri, phase_work,
+	atom_region( floor_f3_face, REGION_PRIM_ARENA)
+	atom_group(  floor_f3_face, GROUP_RENDER_FLOOR)
+	atom_cadence(floor_f3_face, CADENCE_FRAME)
+	atom_annot(  floor_f3_face, phase_work,
 		atom_reads( R_PrimCursor, R_FaceCursor, R_VertBase, R_OtBase),
 		atom_writes(R_PrimCursor, R_FaceCursor)) 
 internal 
-MipsAtom_(floor_tri) {
+MipsAtom_(floor_f3_face) {
 	mac_load_tri_indices(R_T0, R_T1, R_T2),
 	mac_load_tri_verts(  R_T0, R_T1, R_T2),
 	nop2, gte_cmdw_rotate_translate_perspective_triple,
 	nop2, gte_cmdw_nclip,
-	nop2, 
+ 
 	/* Culling (Branch forward if Backface) */
-	gte_mv_from_data_r(R_T0, C2_MAC0),
-	nop, branch_le_zero(R_T0, atom_offset(culling, floor_tri_exit)), 
-	nop,                      
+	nop2, gte_mv_from_data_r(R_T0, C2_MAC0),
+	nop,
+	branch_le_zero(R_T0, atom_offset(culling, floor_f3_face_exit)), nop,
 	/* Format Primitive */
 	// mac_format_f3_color(0x20FF, 0xFFFF),  // works
 	mac_format_f3_color(0xFF, 0xFF, 0xFF),  // RGB-form (R=FF, G=FF, B=FF = white)
-	mac_gte_store_f3(),
+	mac_gte_store_f3_post_rtpt(),
 	
 	/* Calculate Depth */
 	nop2, gte_avg_sort_z3,            
@@ -195,15 +161,14 @@ MipsAtom_(floor_tri) {
 	/* Bounds Check OTZ < 2048 (Branch forward to skip insertion) */
 	add_ui(      R_AT, R_0,  OrderingTbl_Len),   
 	set_lt_u(    R_AT, R_T1, R_AT), 
-	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, floor_tri_exit)),   
-	nop, 
+	branch_equal(R_AT, R_0,  atom_offset(bounds_chk, floor_f3_face_exit)), nop, 
 	/* Insert into Ordering Table Linked List */
 	mac_insert_ot_tag(R_T1, Poly_F3),
 	add_ui_self(R_PrimCursor, S_(Poly_F3)), /* Advance Prim Cursor (5 words) */
 		// Note(Ed): No bounds checking, should be checked before atom runs.
 
 /* Advance Input Cursor & Yield (Both branch targets land here) */
-atom_label(floor_tri_exit) 
+atom_label(floor_f3_face_exit) 
 	add_ui_self(R_FaceCursor, S_(S2) * 4),  /* Advance Face Cursor (4 * S2 = 8 bytes) */
 	mac_yield()
 };

code/gte_hello/tape_atom.metadata.h

@@ -18,10 +18,10 @@ WORD_COUNT(call_addr,                        1)
 WORD_COUNT(branch_le_zero,                   1)
 WORD_COUNT(branch_equal,                     1)
 WORD_COUNT(add_ui,                           1)
-WORD_COUNT(set_lt_u,                          1)
-WORD_COUNT(set_lt_s,                          1)
-WORD_COUNT(set_lt_si,                         1)
-WORD_COUNT(set_lt_ui,                         1)
+WORD_COUNT(set_lt_u,                         1)
+WORD_COUNT(set_lt_s,                         1)
+WORD_COUNT(set_lt_si,                        1)
+WORD_COUNT(set_lt_ui,                        1)
 WORD_COUNT(load_word,                        1)
 WORD_COUNT(load_half_u,                      1)
 WORD_COUNT(store_word,                       1)
@@ -37,7 +37,7 @@ WORD_COUNT(shift_lleft_self,                 1)
 WORD_COUNT(shift_lright,                     1)
 WORD_COUNT(shift_aright,                     1)
 WORD_COUNT(mask_upper,                       2)
-WORD_COUNT(gte_mv_from_data_r,              1)
+WORD_COUNT(gte_mv_from_data_r,               1)
 WORD_COUNT(gte_mv_from_ctrl_r,               1)
 WORD_COUNT(gte_mv_to_data_r,                 1)
 WORD_COUNT(gte_mv_to_ctrl_r,                 1)
@@ -45,10 +45,16 @@ WORD_COUNT(gte_sw,                           1)
 WORD_COUNT(gte_cmdw_rtpt,                    1)
 WORD_COUNT(gte_cmdw_nclip,                   1)
 WORD_COUNT(gte_avg_sort_z3,                  1)
+WORD_COUNT(sub_u,                            1)
+WORD_COUNT(nop2,                             2)
 WORD_COUNT(mac_load_tri_indices,             3)
 WORD_COUNT(mac_load_tri_verts,              18)
 WORD_COUNT(mac_format_f3_color,              3)
-WORD_COUNT(mac_gte_store_f3,                 3)
+WORD_COUNT(mac_gte_store_f3_post_rtpt,       3)
+WORD_COUNT(mac_pack_color_word,              3)
+WORD_COUNT(mac_format_g4_color,             12)
+WORD_COUNT(mac_gte_store_g4_p012_post_rtpt_pre_rtps, 3)
+WORD_COUNT(mac_gte_store_g4_p3_post_rtps,    1)
 WORD_COUNT(mac_insert_ot_tag,               11)
 WORD_COUNT(mac_yield,                        4)