---
src/amd/common/ac_nir_to_llvm.c | 20 +++++++++------
src/amd/common/ac_shader_abi.h | 4 +++
src/gallium/drivers/radeonsi/si_shader.c | 42 +++++++++++++++++++-------------
3 files changed, 42 insertions(+), 24 deletions(-)
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index ce91d403884..d2a8691b11b 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -4017,37 +4017,38 @@ visit_emit_vertex(struct ac_shader_abi *abi, unsigned
stream, LLVMValueRef *addr
}
static void
visit_end_primitive(struct nir_to_llvm_context *ctx,
const nir_intrinsic_instr *instr)
{
ac_build_sendmsg(&ctx->ac, AC_SENDMSG_GS_OP_CUT | AC_SENDMSG_GS | (0 <<
8), ctx->gs_wave_id);
}
static LLVMValueRef
-visit_load_tess_coord(struct nir_to_llvm_context *ctx,
- const nir_intrinsic_instr *instr)
+load_tess_coord(struct ac_shader_abi *abi, LLVMTypeRef type,
+ unsigned num_components)
{
+ struct nir_to_llvm_context *ctx = nir_to_llvm_context_from_abi(abi);
+
LLVMValueRef coord[4] = {
ctx->tes_u,
ctx->tes_v,
ctx->ac.f32_0,
ctx->ac.f32_0,
};
if (ctx->tes_primitive_mode == GL_TRIANGLES)
coord[2] = LLVMBuildFSub(ctx->builder, ctx->ac.f32_1,
LLVMBuildFAdd(ctx->builder, coord[0],
coord[1], ""), "");
- LLVMValueRef result = ac_build_gather_values(&ctx->ac, coord,
instr->num_components);
- return LLVMBuildBitCast(ctx->builder, result,
- get_def_type(ctx->nir, &instr->dest.ssa), "");
+ LLVMValueRef result = ac_build_gather_values(&ctx->ac, coord,
num_components);
+ return LLVMBuildBitCast(ctx->builder, result, type, "");
}
static void visit_intrinsic(struct ac_nir_context *ctx,
nir_intrinsic_instr *instr)
{
LLVMValueRef result = NULL;
switch (instr->intrinsic) {
case nir_intrinsic_load_work_group_id: {
result = ctx->nctx->workgroup_ids;
@@ -4218,23 +4219,27 @@ static void visit_intrinsic(struct ac_nir_context *ctx,
case nir_intrinsic_interp_var_at_offset:
result = visit_interp(ctx->nctx, instr);
break;
case nir_intrinsic_emit_vertex:
assert(instr->const_index[0] == 0);
ctx->abi->emit_vertex(ctx->abi, 0, ctx->outputs);
break;
case nir_intrinsic_end_primitive:
visit_end_primitive(ctx->nctx, instr);
break;
- case nir_intrinsic_load_tess_coord:
- result = visit_load_tess_coord(ctx->nctx, instr);
+ case nir_intrinsic_load_tess_coord: {
+ LLVMTypeRef type = ctx->nctx ?
+ get_def_type(ctx->nctx->nir, &instr->dest.ssa) :
+ NULL;
+ result = ctx->abi->load_tess_coord(ctx->abi, type,
instr->num_components);
break;
+ }
case nir_intrinsic_load_patch_vertices_in:
result = LLVMConstInt(ctx->ac.i32,
ctx->nctx->options->key.tcs.input_vertices, false);
break;
default:
fprintf(stderr, "Unknown intrinsic: ");
nir_print_instr(&instr->instr, stderr);
fprintf(stderr, "\n");
break;
}
if (result) {
@@ -6574,20 +6579,21 @@ LLVMModuleRef
ac_translate_nir_to_llvm(LLVMTargetMachineRef tm,
ctx.gs_max_out_vertices =
shaders[i]->info.gs.vertices_out;
ctx.abi.load_inputs = load_gs_input;
} else if (shaders[i]->info.stage == MESA_SHADER_TESS_CTRL) {
ctx.tcs_outputs_read = shaders[i]->info.outputs_read;
ctx.tcs_patch_outputs_read =
shaders[i]->info.patch_outputs_read;
ctx.abi.load_tess_inputs = load_tcs_input;
ctx.abi.store_tcs_outputs = store_tcs_output;
} else if (shaders[i]->info.stage == MESA_SHADER_TESS_EVAL) {
ctx.tes_primitive_mode =
shaders[i]->info.tess.primitive_mode;
ctx.abi.load_tess_inputs = load_tes_input;
+ ctx.abi.load_tess_coord = load_tess_coord;
} else if (shaders[i]->info.stage == MESA_SHADER_VERTEX) {
if (shader_info->info.vs.needs_instance_id) {
ctx.shader_info->vs.vgpr_comp_cnt =
MAX2(3,
ctx.shader_info->vs.vgpr_comp_cnt);
}
} else if (shaders[i]->info.stage == MESA_SHADER_FRAGMENT) {
shader_info->fs.can_discard =
shaders[i]->info.fs.uses_discard;
}
if (i)
diff --git a/src/amd/common/ac_shader_abi.h b/src/amd/common/ac_shader_abi.h
index 827617c8e97..2278f37c7cd 100644
--- a/src/amd/common/ac_shader_abi.h
+++ b/src/amd/common/ac_shader_abi.h
@@ -93,20 +93,24 @@ struct ac_shader_abi {
LLVMValueRef param_index,
unsigned const_index,
unsigned location,
unsigned driver_location,
LLVMValueRef src,
unsigned component,
bool is_patch,
bool is_compact,
unsigned writemask);
+ LLVMValueRef (*load_tess_coord)(struct ac_shader_abi *abi,
+ LLVMTypeRef type,
+ unsigned num_components);
+
LLVMValueRef (*load_ubo)(struct ac_shader_abi *abi, LLVMValueRef index);
/**
* Load the descriptor for the given buffer.
*
* \param buffer the buffer as presented in NIR: this is the descriptor
* in Vulkan, and the buffer index in OpenGL/Gallium
* \param write whether buffer contents will be written
*/
LLVMValueRef (*load_ssbo)(struct ac_shader_abi *abi,
diff --git a/src/gallium/drivers/radeonsi/si_shader.c
b/src/gallium/drivers/radeonsi/si_shader.c
index 41698720df1..a823d49982f 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -1895,25 +1895,47 @@ static LLVMValueRef load_sample_position(struct
si_shader_context *ctx, LLVMValu
LLVMValueRef pos[4] = {
buffer_load_const(ctx, resource, offset0),
buffer_load_const(ctx, resource, offset1),
LLVMConstReal(ctx->f32, 0),
LLVMConstReal(ctx->f32, 0)
};
return lp_build_gather_values(&ctx->gallivm, pos, 4);
}
+static LLVMValueRef si_load_tess_coord(struct ac_shader_abi *abi,
+ LLVMTypeRef type,
+ unsigned num_components)
+{
+ struct si_shader_context *ctx = si_shader_context_from_abi(abi);
+ struct lp_build_context *bld = &ctx->bld_base.base;
+
+ LLVMValueRef coord[4] = {
+ LLVMGetParam(ctx->main_fn, ctx->param_tes_u),
+ LLVMGetParam(ctx->main_fn, ctx->param_tes_v),
+ ctx->ac.f32_0,
+ ctx->ac.f32_0
+ };
+
+ /* For triangles, the vector should be (u, v, 1-u-v). */
+ if (ctx->shader->selector->info.properties[TGSI_PROPERTY_TES_PRIM_MODE]
==
+ PIPE_PRIM_TRIANGLES)
+ coord[2] = lp_build_sub(bld, ctx->ac.f32_1,
+ lp_build_add(bld, coord[0], coord[1]));
+
+ return lp_build_gather_values(&ctx->gallivm, coord, 4);
+}
+
void si_load_system_value(struct si_shader_context *ctx,
unsigned index,
const struct tgsi_full_declaration *decl)
{
- struct lp_build_context *bld = &ctx->bld_base.base;
LLVMValueRef value = 0;
assert(index < RADEON_LLVM_MAX_SYSTEM_VALUES);
switch (decl->Semantic.Name) {
case TGSI_SEMANTIC_INSTANCEID:
value = ctx->abi.instance_id;
break;
case TGSI_SEMANTIC_VERTEXID:
@@ -2000,37 +2022,22 @@ void si_load_system_value(struct si_shader_context *ctx,
}
case TGSI_SEMANTIC_SAMPLEMASK:
/* This can only occur with the OpenGL Core profile, which
* doesn't support smoothing.
*/
value = LLVMGetParam(ctx->main_fn, SI_PARAM_SAMPLE_COVERAGE);
break;
case TGSI_SEMANTIC_TESSCOORD:
- {
- LLVMValueRef coord[4] = {
- LLVMGetParam(ctx->main_fn, ctx->param_tes_u),
- LLVMGetParam(ctx->main_fn, ctx->param_tes_v),
- ctx->ac.f32_0,
- ctx->ac.f32_0
- };
-
- /* For triangles, the vector should be (u, v, 1-u-v). */
- if
(ctx->shader->selector->info.properties[TGSI_PROPERTY_TES_PRIM_MODE] ==
- PIPE_PRIM_TRIANGLES)
- coord[2] = lp_build_sub(bld, ctx->ac.f32_1,
- lp_build_add(bld, coord[0],
coord[1]));
-
- value = lp_build_gather_values(&ctx->gallivm, coord, 4);
+ value = si_load_tess_coord(&ctx->abi, NULL, 4);
break;
- }
case TGSI_SEMANTIC_VERTICESIN:
if (ctx->type == PIPE_SHADER_TESS_CTRL)
value = unpack_param(ctx,
ctx->param_tcs_out_lds_layout, 26, 6);
else if (ctx->type == PIPE_SHADER_TESS_EVAL)
value = get_num_tcs_out_vertices(ctx);
else
assert(!"invalid shader stage for
TGSI_SEMANTIC_VERTICESIN");
break;
@@ -6055,20 +6062,21 @@ static bool si_compile_tgsi_main(struct
si_shader_context *ctx,
ctx->abi.load_tess_inputs = si_nir_load_input_tcs;
bld_base->emit_fetch_funcs[TGSI_FILE_OUTPUT] = fetch_output_tcs;
bld_base->emit_store = store_output_tcs;
ctx->abi.store_tcs_outputs = si_nir_store_output_tcs;
ctx->abi.emit_outputs = si_llvm_emit_tcs_epilogue;
bld_base->emit_epilogue = si_tgsi_emit_epilogue;
break;
case PIPE_SHADER_TESS_EVAL:
bld_base->emit_fetch_funcs[TGSI_FILE_INPUT] = fetch_input_tes;
ctx->abi.load_tess_inputs = si_nir_load_input_tes;
+ ctx->abi.load_tess_coord = si_load_tess_coord;
if (shader->key.as_es)
ctx->abi.emit_outputs = si_llvm_emit_es_epilogue;
else
ctx->abi.emit_outputs = si_llvm_emit_vs_epilogue;
bld_base->emit_epilogue = si_tgsi_emit_epilogue;
break;
case PIPE_SHADER_GEOMETRY:
bld_base->emit_fetch_funcs[TGSI_FILE_INPUT] = fetch_input_gs;
ctx->abi.load_inputs = si_nir_load_input_gs;
ctx->abi.emit_vertex = si_llvm_emit_vertex;
--
2.14.3
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
