[Mesa-dev] [PATCH 05/20] radeonsi: add nir support for ls epilogue
Timothy Arceri
tarceri at itsqueeze.com
Fri Nov 10 03:13:39 UTC 2017
---
src/gallium/drivers/radeonsi/si_shader.c | 37 +++++++++++++++++++-------------
1 file changed, 22 insertions(+), 15 deletions(-)
diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 47ca64fdea..cc68d0ac6f 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -1106,27 +1106,25 @@ static LLVMValueRef lds_load(struct lp_build_tgsi_context *bld_base,
return bitcast(bld_base, type, value);
}
/**
* Store to LDS.
*
* \param swizzle offset (typically 0..3)
* \param dw_addr address in dwords
* \param value value to store
*/
-static void lds_store(struct lp_build_tgsi_context *bld_base,
+static void lds_store(struct si_shader_context *ctx,
unsigned dw_offset_imm, LLVMValueRef dw_addr,
LLVMValueRef value)
{
- struct si_shader_context *ctx = si_shader_context(bld_base);
-
- dw_addr = lp_build_add(&bld_base->uint_bld, dw_addr,
+ dw_addr = lp_build_add(&ctx->bld_base.uint_bld, dw_addr,
LLVMConstInt(ctx->i32, dw_offset_imm, 0));
ac_lds_store(&ctx->ac, dw_addr, value);
}
static LLVMValueRef desc_from_addr_base64k(struct si_shader_context *ctx,
unsigned param)
{
LLVMBuilderRef builder = ctx->ac.builder;
@@ -1258,21 +1256,21 @@ static void store_output_tcs(struct lp_build_tgsi_context *bld_base,
uint32_t writemask = reg->Register.WriteMask;
while (writemask) {
chan_index = u_bit_scan(&writemask);
LLVMValueRef value = dst[chan_index];
if (inst->Instruction.Saturate)
value = ac_build_clamp(&ctx->ac, value);
/* Skip LDS stores if there is no LDS read of this output. */
if (!skip_lds_store)
- lds_store(bld_base, chan_index, dw_addr, value);
+ lds_store(ctx, chan_index, dw_addr, value);
value = ac_to_integer(&ctx->ac, value);
values[chan_index] = value;
if (reg->Register.WriteMask != 0xF && !is_tess_factor) {
ac_build_buffer_store_dword(&ctx->ac, buffer, value, 1,
buf_addr, base,
4 * chan_index, 1, 0, true, false);
}
@@ -3126,36 +3124,37 @@ static void si_set_es_return_value_for_gs(struct si_shader_context *ctx)
8 + GFX9_SGPR_GS_SAMPLERS_AND_IMAGES);
unsigned vgpr = 8 + GFX9_GS_NUM_USER_SGPR;
for (unsigned i = 0; i < 5; i++) {
unsigned param = ctx->param_gs_vtx01_offset + i;
ret = si_insert_input_ret_float(ctx, ret, param, vgpr++);
}
ctx->return_value = ret;
}
-static void si_llvm_emit_ls_epilogue(struct lp_build_tgsi_context *bld_base)
+static void si_llvm_emit_ls_epilogue(struct ac_shader_abi *abi,
+ unsigned max_outputs,
+ LLVMValueRef *addrs)
{
- struct si_shader_context *ctx = si_shader_context(bld_base);
+ struct si_shader_context *ctx = si_shader_context_from_abi(abi);
struct si_shader *shader = ctx->shader;
struct tgsi_shader_info *info = &shader->selector->info;
unsigned i, chan;
LLVMValueRef vertex_id = LLVMGetParam(ctx->main_fn,
ctx->param_rel_auto_id);
LLVMValueRef vertex_dw_stride = get_tcs_in_vertex_dw_stride(ctx);
LLVMValueRef base_dw_addr = LLVMBuildMul(ctx->ac.builder, vertex_id,
vertex_dw_stride, "");
/* Write outputs to LDS. The next shader (TCS aka HS) will read
* its inputs from it. */
for (i = 0; i < info->num_outputs; i++) {
- LLVMValueRef *out_ptr = ctx->outputs[i];
unsigned name = info->output_semantic_name[i];
unsigned index = info->output_semantic_index[i];
/* The ARB_shader_viewport_layer_array spec contains the
* following issue:
*
* 2) What happens if gl_ViewportIndex or gl_Layer is
* written in the vertex shader and a geometry shader is
* present?
*
@@ -3169,29 +3168,37 @@ static void si_llvm_emit_ls_epilogue(struct lp_build_tgsi_context *bld_base)
*/
if (name == TGSI_SEMANTIC_LAYER ||
name == TGSI_SEMANTIC_VIEWPORT_INDEX)
continue;
int param = si_shader_io_get_unique_index(name, index);
LLVMValueRef dw_addr = LLVMBuildAdd(ctx->ac.builder, base_dw_addr,
LLVMConstInt(ctx->i32, param * 4, 0), "");
for (chan = 0; chan < 4; chan++) {
- lds_store(bld_base, chan, dw_addr,
- LLVMBuildLoad(ctx->ac.builder, out_ptr[chan], ""));
+ lds_store(ctx, chan, dw_addr,
+ LLVMBuildLoad(ctx->ac.builder, addrs[4 * i + chan], ""));
}
}
if (ctx->screen->b.chip_class >= GFX9)
si_set_ls_return_value_for_tcs(ctx);
}
+static void si_tgsi_emit_ls_epilogue(struct lp_build_tgsi_context *bld_base)
+{
+ struct si_shader_context *ctx = si_shader_context(bld_base);
+
+ ctx->abi.emit_outputs(&ctx->abi, RADEON_LLVM_MAX_OUTPUTS,
+ ctx->outputs[0]);
+}
+
static void si_llvm_emit_es_epilogue(struct lp_build_tgsi_context *bld_base)
{
struct si_shader_context *ctx = si_shader_context(bld_base);
struct si_shader *es = ctx->shader;
struct tgsi_shader_info *info = &es->selector->info;
LLVMValueRef soffset = LLVMGetParam(ctx->main_fn,
ctx->param_es2gs_offset);
LLVMValueRef lds_base = NULL;
unsigned chan;
int i;
@@ -3217,21 +3224,21 @@ static void si_llvm_emit_es_epilogue(struct lp_build_tgsi_context *bld_base)
param = si_shader_io_get_unique_index(info->output_semantic_name[i],
info->output_semantic_index[i]);
for (chan = 0; chan < 4; chan++) {
LLVMValueRef out_val = LLVMBuildLoad(ctx->ac.builder, out_ptr[chan], "");
out_val = ac_to_integer(&ctx->ac, out_val);
/* GFX9 has the ESGS ring in LDS. */
if (ctx->screen->b.chip_class >= GFX9) {
- lds_store(bld_base, param * 4 + chan, lds_base, out_val);
+ lds_store(ctx, param * 4 + chan, lds_base, out_val);
continue;
}
ac_build_buffer_store_dword(&ctx->ac,
ctx->esgs_ring,
out_val, 1, NULL, soffset,
(4 * param + chan) * 4,
1, 1, true, true);
}
}
@@ -4426,21 +4433,20 @@ static void create_function(struct si_shader_context *ctx)
break;
}
declare_per_stage_desc_pointers(ctx, &fninfo, true);
declare_vs_specific_input_sgprs(ctx, &fninfo);
if (shader->key.as_es) {
assert(!shader->selector->nir);
ctx->param_es2gs_offset = add_arg(&fninfo, ARG_SGPR, ctx->i32);
} else if (shader->key.as_ls) {
- assert(!shader->selector->nir);
/* no extra parameters */
} else {
if (shader->is_gs_copy_shader) {
fninfo.num_params = ctx->param_rw_buffers + 1;
fninfo.num_sgpr_params = fninfo.num_params;
}
/* The locations of the other parameters are assigned dynamically. */
declare_streamout_params(ctx, &shader->selector->so,
&fninfo);
@@ -5728,23 +5734,24 @@ static bool si_compile_tgsi_main(struct si_shader_context *ctx,
bool is_monolithic)
{
struct si_shader *shader = ctx->shader;
struct si_shader_selector *sel = shader->selector;
struct lp_build_tgsi_context *bld_base = &ctx->bld_base;
// TODO clean all this up!
switch (ctx->type) {
case PIPE_SHADER_VERTEX:
ctx->load_input = declare_input_vs;
- if (shader->key.as_ls)
- bld_base->emit_epilogue = si_llvm_emit_ls_epilogue;
- else if (shader->key.as_es)
+ if (shader->key.as_ls) {
+ ctx->abi.emit_outputs = si_llvm_emit_ls_epilogue;
+ bld_base->emit_epilogue = si_tgsi_emit_ls_epilogue;
+ } else if (shader->key.as_es)
bld_base->emit_epilogue = 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_TESS_CTRL:
bld_base->emit_fetch_funcs[TGSI_FILE_INPUT] = fetch_input_tcs;
bld_base->emit_fetch_funcs[TGSI_FILE_OUTPUT] = fetch_output_tcs;
bld_base->emit_store = store_output_tcs;
--
2.14.3
More information about the mesa-dev
mailing list