st/nine: Implement TEXM3x3SPEC

Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Axel Davy <axel.davy@ens.fr>
Cc: "10.4" <mesa-stable@lists.freedesktop.org>

diff --git a/src/gallium/state_trackers/nine/nine_shader.c b/src/gallium/state_trackers/nine/nine_shader.c
index 38055128d39bb31c691739d70ebb4c6d9d0276a7..0edf7e8b66961049ff52ead8f97370e1f47753e0 100644 (file)
--- a/src/gallium/state_trackers/nine/nine_shader.c
+++ b/src/gallium/state_trackers/nine/nine_shader.c
@@ -2170,7 +2170,44 @@ DECL_SPECIAL(TEXM3x3PAD)
 
 DECL_SPECIAL(TEXM3x3SPEC)
 {
-    STUB(D3DERR_INVALIDCALL);
+    struct ureg_program *ureg = tx->ureg;
+    struct ureg_dst dst = tx_dst_param(tx, &tx->insn.dst[0]);
+    struct ureg_src E = tx_src_param(tx, &tx->insn.src[1]);
+    struct ureg_src sample;
+    struct ureg_dst tmp;
+    const int m = tx->insn.dst[0].idx - 2;
+    const int n = tx->insn.src[0].idx;
+    assert(m >= 0 && m > n);
+
+    tx_texcoord_alloc(tx, m);
+    tx_texcoord_alloc(tx, m+1);
+    tx_texcoord_alloc(tx, m+2);
+
+    ureg_DP3(ureg, ureg_writemask(dst, TGSI_WRITEMASK_X), tx->regs.vT[m], ureg_src(tx->regs.tS[n]));
+    ureg_DP3(ureg, ureg_writemask(dst, TGSI_WRITEMASK_Y), tx->regs.vT[m+1], ureg_src(tx->regs.tS[n]));
+    ureg_DP3(ureg, ureg_writemask(dst, TGSI_WRITEMASK_Z), tx->regs.vT[m+2], ureg_src(tx->regs.tS[n]));
+
+    sample = ureg_DECL_sampler(ureg, m + 2);
+    tx->info->sampler_mask |= 1 << (m + 2);
+    tmp = ureg_writemask(tx_scratch(tx), TGSI_WRITEMASK_XYZ);
+
+    /* At this step, dst = N = (u', w', z').
+     * We want dst to be the texture sampled at (u'', w'', z''), with
+     * (u'', w'', z'') = 2 * (N.E / N.N) * N - E */
+    ureg_DP3(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_src(dst), ureg_src(dst));
+    ureg_RCP(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X));
+    /* at this step tmp.x = 1/N.N */
+    ureg_DP3(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_Y), ureg_src(dst), E);
+    /* at this step tmp.y = N.E */
+    ureg_MUL(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X), ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_Y));
+    /* at this step tmp.x = N.E/N.N */
+    ureg_MUL(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X), ureg_imm1f(ureg, 2.0f));
+    ureg_MUL(ureg, tmp, ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X), ureg_src(dst));
+    /* at this step tmp.xyz = 2 * (N.E / N.N) * N */
+    ureg_SUB(ureg, tmp, ureg_src(tmp), E);
+    ureg_TEX(ureg, dst, ps1x_sampler_type(tx->info, m + 2), ureg_src(tmp), sample);
+
+    return D3D_OK;
 }
 
 DECL_SPECIAL(TEXREG2RGB)