[Mesa-dev] [PATCH 6/6] radv: add sample mask output support

[Dave Airlie]

From: Dave Airlie <airlied at redhat.com>

This adds support to write to sample mask from the fragment shader.

We can optimise this later like radeonsi.

Signed-off-by: Dave Airlie <airlied at redhat.com>
---
 src/amd/common/ac_nir_to_llvm.c  | 8 ++++++--
 src/amd/common/ac_nir_to_llvm.h  | 1 +
 src/amd/vulkan/radv_cmd_buffer.c | 2 ++
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index 6021647..9778581 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -4753,13 +4753,17 @@ handle_fs_outputs_post(struct nir_to_llvm_context *ctx)
 			ctx->shader_info->fs.writes_stencil = true;
 			stencil = to_float(ctx, LLVMBuildLoad(ctx->builder,
 							      ctx->outputs[radeon_llvm_reg_index_soa(i, 0)], ""));
+		} else if (i == FRAG_RESULT_SAMPLE_MASK) {
+			ctx->shader_info->fs.writes_sample_mask = true;
+			samplemask = to_float(ctx, LLVMBuildLoad(ctx->builder,
+								  ctx->outputs[radeon_llvm_reg_index_soa(i, 0)], ""));
 		} else {
 			bool last = false;
 			for (unsigned j = 0; j < 4; j++)
 				values[j] = to_float(ctx, LLVMBuildLoad(ctx->builder,
 									ctx->outputs[radeon_llvm_reg_index_soa(i, j)], ""));
 
-			if (!ctx->shader_info->fs.writes_z && !ctx->shader_info->fs.writes_stencil)
+			if (!ctx->shader_info->fs.writes_z && !ctx->shader_info->fs.writes_stencil && !ctx->shader_info->fs.writes_sample_mask)
 				last = ctx->output_mask <= ((1ull << (i + 1)) - 1);
 
 			si_export_mrt_color(ctx, values, V_008DFC_SQ_EXP_MRT + index, last);
@@ -4767,7 +4771,7 @@ handle_fs_outputs_post(struct nir_to_llvm_context *ctx)
 		}
 	}
 
-	if (depth || stencil)
+	if (depth || stencil || samplemask)
 		si_export_mrt_z(ctx, depth, stencil, samplemask);
 	else if (!index)
 		si_export_mrt_color(ctx, NULL, V_008DFC_SQ_EXP_NULL, true);
diff --git a/src/amd/common/ac_nir_to_llvm.h b/src/amd/common/ac_nir_to_llvm.h
index c2662e2..6c2b78b 100644
--- a/src/amd/common/ac_nir_to_llvm.h
+++ b/src/amd/common/ac_nir_to_llvm.h
@@ -118,6 +118,7 @@ struct ac_shader_variant_info {
 			bool can_discard;
 			bool writes_z;
 			bool writes_stencil;
+			bool writes_sample_mask;
 			bool early_fragment_test;
 			bool writes_memory;
 			bool force_persample;
diff --git a/src/amd/vulkan/radv_cmd_buffer.c b/src/amd/vulkan/radv_cmd_buffer.c
index 5b7564c..1e38cbe 100644
--- a/src/amd/vulkan/radv_cmd_buffer.c
+++ b/src/amd/vulkan/radv_cmd_buffer.c
@@ -674,6 +674,7 @@ radv_emit_fragment_shader(struct radv_cmd_buffer *cmd_buffer,
 			       S_02880C_Z_EXPORT_ENABLE(ps->info.fs.writes_z) |
 			       S_02880C_STENCIL_TEST_VAL_EXPORT_ENABLE(ps->info.fs.writes_stencil) |
 			       S_02880C_KILL_ENABLE(!!ps->info.fs.can_discard) |
+			       S_02880C_MASK_EXPORT_ENABLE(ps->info.fs.writes_sample_mask) |
 			       S_02880C_Z_ORDER(z_order) |
 			       S_02880C_DEPTH_BEFORE_SHADER(ps->info.fs.early_fragment_test) |
 			       S_02880C_EXEC_ON_HIER_FAIL(ps->info.fs.writes_memory) |
@@ -694,6 +695,7 @@ radv_emit_fragment_shader(struct radv_cmd_buffer *cmd_buffer,
 	radeon_set_context_reg(cmd_buffer->cs, R_0286E0_SPI_BARYC_CNTL, spi_baryc_cntl);
 
 	radeon_set_context_reg(cmd_buffer->cs, R_028710_SPI_SHADER_Z_FORMAT,
+			       ps->info.fs.writes_sample_mask ? V_028710_SPI_SHADER_32_ABGR :
 			       ps->info.fs.writes_stencil ? V_028710_SPI_SHADER_32_GR :
 			       ps->info.fs.writes_z ? V_028710_SPI_SHADER_32_R :
 			       V_028710_SPI_SHADER_ZERO);
-- 
2.9.3