radeonsi: add si_nir_load_input_tes()

V2: drop type param and just use ctx->i32

Reviewed-by: Marek Olšák <marek.olsak@amd.com>

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index ef1b460f456a573d2b334279321550e387fcebc0..bb251986ffff097719daafc8fc88bd56e6c1eb6c 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -1229,6 +1229,54 @@ static LLVMValueRef fetch_input_tes(
                           buffer, base, addr, true);
 }
 
+LLVMValueRef si_nir_load_input_tes(struct ac_shader_abi *abi,
+                                  LLVMValueRef vertex_index,
+                                  LLVMValueRef param_index,
+                                  unsigned const_index,
+                                  unsigned location,
+                                  unsigned driver_location,
+                                  unsigned component,
+                                  unsigned num_components,
+                                  bool is_patch,
+                                  bool is_compact)
+{
+       struct si_shader_context *ctx = si_shader_context_from_abi(abi);
+       struct tgsi_shader_info *info = &ctx->shader->selector->info;
+       LLVMValueRef buffer, base, addr;
+
+       driver_location = driver_location / 4;
+
+       buffer = desc_from_addr_base64k(ctx, ctx->param_tcs_offchip_addr_base64k);
+
+       base = LLVMGetParam(ctx->main_fn, ctx->param_tcs_offchip_offset);
+
+       if (param_index) {
+               /* Add the constant index to the indirect index */
+               param_index = LLVMBuildAdd(ctx->ac.builder, param_index,
+                                          LLVMConstInt(ctx->i32, const_index, 0), "");
+       } else {
+               param_index = LLVMConstInt(ctx->i32, const_index, 0);
+       }
+
+       addr = get_tcs_tes_buffer_address_from_generic_indices(ctx, vertex_index,
+                                                              param_index, driver_location,
+                                                              info->input_semantic_name,
+                                                              info->input_semantic_index,
+                                                              is_patch);
+
+       /* TODO: This will generate rather ordinary llvm code, although it
+        * should be easy for the optimiser to fix up. In future we might want
+        * to refactor buffer_load(), but for now this maximises code sharing
+        * between the NIR and TGSI backends.
+        */
+       LLVMValueRef value[4];
+       for (unsigned i = component; i < num_components + component; i++) {
+               value[i] = buffer_load(&ctx->bld_base, ctx->i32, i, buffer, base, addr, true);
+       }
+
+       return ac_build_varying_gather_values(&ctx->ac, value, num_components, component);
+}
+
 static void store_output_tcs(struct lp_build_tgsi_context *bld_base,
                             const struct tgsi_full_instruction *inst,
                             const struct tgsi_opcode_info *info,

diff --git a/src/gallium/drivers/radeonsi/si_shader_internal.h b/src/gallium/drivers/radeonsi/si_shader_internal.h
index e05927c7fd9745986bfe7422cdd6f5061f37b100..378bfc1a7aca4fc50deab4db3591dfbeb2436b0c 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader_internal.h
+++ b/src/gallium/drivers/radeonsi/si_shader_internal.h
@@ -277,6 +277,17 @@ LLVMValueRef si_llvm_emit_fetch(struct lp_build_tgsi_context *bld_base,
                                enum tgsi_opcode_type type,
                                unsigned swizzle);
 
+LLVMValueRef si_nir_load_input_tes(struct ac_shader_abi *abi,
+                                  LLVMValueRef vertex_index,
+                                  LLVMValueRef param_index,
+                                  unsigned const_index,
+                                  unsigned location,
+                                  unsigned driver_location,
+                                  unsigned component,
+                                  unsigned num_components,
+                                  bool is_patch,
+                                  bool is_compact);
+
 LLVMValueRef si_llvm_load_input_gs(struct ac_shader_abi *abi,
                                   unsigned input_index,
                                   unsigned vtx_offset_param,