tgsi/ureg: make the dst register match the src indirection

[mesa.git] / src / gallium / auxiliary / draw / draw_llvm.c

diff --git a/src/gallium/auxiliary/draw/draw_llvm.c b/src/gallium/auxiliary/draw/draw_llvm.c
index 594b0ec72a3791b25f9dc057145c9cb122ddcbeb..d2821a1463389674e0daa57ac4a7239b110d1251 100644 (file)
--- a/src/gallium/auxiliary/draw/draw_llvm.c
+++ b/src/gallium/auxiliary/draw/draw_llvm.c
@@ -996,18 +996,19 @@ generate_viewport(struct draw_llvm_variant *variant,
    int i;
    struct gallivm_state *gallivm = variant->gallivm;
    struct lp_type f32_type = vs_type;
+   const unsigned pos = draw_current_shader_position_output(variant->llvm->draw);
    LLVMTypeRef vs_type_llvm = lp_build_vec_type(gallivm, vs_type);
-   LLVMValueRef out3 = LLVMBuildLoad(builder, outputs[0][3], ""); /*w0 w1 .. wn*/
+   LLVMValueRef out3 = LLVMBuildLoad(builder, outputs[pos][3], ""); /*w0 w1 .. wn*/
    LLVMValueRef const1 = lp_build_const_vec(gallivm, f32_type, 1.0);       /*1.0 1.0 1.0 1.0*/
    LLVMValueRef vp_ptr = draw_jit_context_viewport(gallivm, context_ptr);
 
    /* for 1/w convention*/
    out3 = LLVMBuildFDiv(builder, const1, out3, "");
-   LLVMBuildStore(builder, out3, outputs[0][3]);
+   LLVMBuildStore(builder, out3, outputs[pos][3]);
 
    /* Viewport Mapping */
    for (i=0; i<3; i++) {
-      LLVMValueRef out = LLVMBuildLoad(builder, outputs[0][i], ""); /*x0 x1 .. xn*/
+      LLVMValueRef out = LLVMBuildLoad(builder, outputs[pos][i], ""); /*x0 x1 .. xn*/
       LLVMValueRef scale;
       LLVMValueRef trans;
       LLVMValueRef scale_i;
@@ -1033,7 +1034,7 @@ generate_viewport(struct draw_llvm_variant *variant,
       out = LLVMBuildFAdd(builder, out, trans, "");
 
       /* store transformed outputs */
-      LLVMBuildStore(builder, out, outputs[0][i]);
+      LLVMBuildStore(builder, out, outputs[pos][i]);
    }
 
 }
@@ -1525,7 +1526,6 @@ draw_llvm_generate(struct draw_llvm *llvm, struct draw_llvm_variant *variant,
 
    lp_build_loop_begin(&lp_loop, gallivm, start);
    {
-      unsigned nr_vertex_elements = vs_info->file_max[TGSI_FILE_INPUT] + 1;
       LLVMValueRef inputs[PIPE_MAX_SHADER_INPUTS][TGSI_NUM_CHANNELS];
       LLVMValueRef aos_attribs[PIPE_MAX_SHADER_INPUTS][LP_MAX_VECTOR_WIDTH / 32] = { { 0 } };
       LLVMValueRef io;
@@ -1564,22 +1564,18 @@ draw_llvm_generate(struct draw_llvm *llvm, struct draw_llvm_variant *variant,
          system_values.vertex_id = LLVMBuildInsertElement(gallivm->builder,
                                                           system_values.vertex_id, true_index,
                                                           lp_build_const_int32(gallivm, i), "");
-         for (j = 0; j < nr_vertex_elements; ++j) {
+         for (j = 0; j < draw->pt.nr_vertex_elements; ++j) {
             struct pipe_vertex_element *velem = &draw->pt.vertex_element[j];
-            if (j < draw->pt.nr_vertex_elements) {
-               LLVMValueRef vb_index =
-                  lp_build_const_int32(gallivm, velem->vertex_buffer_index);
-               LLVMValueRef vb = LLVMBuildGEP(builder, vb_ptr, &vb_index, 1, "");
-               generate_fetch(gallivm, vbuffers_ptr,
-                              &aos_attribs[j][i], velem, vb, true_index,
-                              system_values.instance_id);
-            } else {
-               aos_attribs[j][i] = lp_build_zero(gallivm, lp_float32_vec4_type());
-            }
+            LLVMValueRef vb_index =
+               lp_build_const_int32(gallivm, velem->vertex_buffer_index);
+            LLVMValueRef vb = LLVMBuildGEP(builder, vb_ptr, &vb_index, 1, "");
+            generate_fetch(gallivm, vbuffers_ptr,
+                           &aos_attribs[j][i], velem, vb, true_index,
+                           system_values.instance_id);
          }
       }
       convert_to_soa(gallivm, aos_attribs, inputs,
-                     nr_vertex_elements, vs_type);
+                     draw->pt.nr_vertex_elements, vs_type);
 
       ptr_aos = (const LLVMValueRef (*)[TGSI_NUM_CHANNELS]) inputs;
       generate_vs(variant,
@@ -1667,9 +1663,8 @@ draw_llvm_make_variant_key(struct draw_llvm *llvm, char *store)
     * here, not the number of provided elements to match keysize
     * (and the offset of sampler state in the key).
     */
-   key->nr_vertex_elements =
-      MIN2(llvm->draw->vs.vertex_shader->info.file_max[TGSI_FILE_INPUT] + 1,
-           llvm->draw->pt.nr_vertex_elements);
+   key->nr_vertex_elements = llvm->draw->vs.vertex_shader->info.file_max[TGSI_FILE_INPUT] + 1;
+   assert(key->nr_vertex_elements <= llvm->draw->pt.nr_vertex_elements);
 
    /* will have to rig this up properly later */
    key->clip_xy = llvm->draw->clip_xy;