This allows running the TES on different CU's than the
TCS which results in performance improvements.
Signed-off-by: Bas Nieuwenhuizen <b...@basnieuwenhuizen.nl>
---
src/gallium/drivers/radeonsi/si_shader.c | 11 ++++++++---
src/gallium/drivers/radeonsi/si_state_shaders.c | 2 +-
2 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/src/gallium/drivers/radeonsi/si_shader.c
b/src/gallium/drivers/radeonsi/si_shader.c
index 4516ea2..5728be0 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2583,12 +2583,17 @@ static void si_write_tess_factors(struct
lp_build_tgsi_context *bld_base,
byteoffset = LLVMBuildMul(gallivm->builder, rel_patch_id,
lp_build_const_int32(gallivm, 4 * stride),
"");
- /* Store the outputs. */
+ /* Store the dynamic HS control word. */
+ build_tbuffer_store_dwords(ctx, buffer,
+ lp_build_const_int32(gallivm, 0x80000000),
+ 1, lp_build_const_int32(gallivm, 0),
tf_base, 0);
+
+ /* Store the tessellation factors. */
build_tbuffer_store_dwords(ctx, buffer, vec0,
- MIN2(stride, 4), byteoffset, tf_base, 0);
+ MIN2(stride, 4), byteoffset, tf_base, 4);
if (vec1)
build_tbuffer_store_dwords(ctx, buffer, vec1,
- stride - 4, byteoffset, tf_base, 16);
+ stride - 4, byteoffset, tf_base, 20);
lp_build_endif(&if_ctx);
}
diff --git a/src/gallium/drivers/radeonsi/si_state_shaders.c
b/src/gallium/drivers/radeonsi/si_state_shaders.c
index f48582a..43f4a84 100644
--- a/src/gallium/drivers/radeonsi/si_state_shaders.c
+++ b/src/gallium/drivers/radeonsi/si_state_shaders.c
@@ -1873,7 +1873,7 @@ static void si_update_vgt_shader_config(struct si_context
*sctx)
if (sctx->tes_shader.cso) {
stages |= S_028B54_LS_EN(V_028B54_LS_STAGE_ON) |
- S_028B54_HS_EN(1);
+ S_028B54_HS_EN(1) | S_028B54_DYNAMIC_HS(1);
if (sctx->gs_shader.cso)
stages |= S_028B54_ES_EN(V_028B54_ES_STAGE_DS) |
--
2.8.2
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
