Mesa (master): ac/nir: do not emit unnecessary null exports in fragment shaders

[Samuel Pitoiset]

Module: Mesa
Branch: master
Commit: 4e3c1ace659c7325bd8d54b66370c3755e40a266
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=4e3c1ace659c7325bd8d54b66370c3755e40a266

Author: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Date:   Thu Mar  8 09:53:14 2018 +0100

ac/nir: do not emit unnecessary null exports in fragment shaders

Null exports should only be needed when no other exports are
emitted. This removes a bunch of 'exp null off, off, off, off done vm'.

Affected games are Dota 2 and Wolfenstein 2, not sure if that
really helps, but code size is decreasing there.

Polaris10:
Totals from affected shaders:
SGPRS: 8216 -> 8216 (0.00 %)
VGPRS: 7072 -> 7072 (0.00 %)
Spilled SGPRs: 0 -> 0 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Code Size: 454968 -> 453896 (-0.24 %) bytes
Max Waves: 772 -> 772 (0.00 %)

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>

---

 src/amd/common/ac_nir_to_llvm.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index c785244dcc..9b85069860 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -6539,17 +6539,13 @@ handle_tcs_outputs_post(struct radv_shader_context *ctx)
 
 static bool
 si_export_mrt_color(struct radv_shader_context *ctx,
-		    LLVMValueRef *color, unsigned index, bool is_last,
+		    LLVMValueRef *color, unsigned index,
 		    struct ac_export_args *args)
 {
 	/* Export */
 	si_llvm_init_export_args(ctx, color, 0xf,
 				 V_008DFC_SQ_EXP_MRT + index, args);
-
-	if (is_last) {
-		args->valid_mask = 1; /* whether the EXEC mask is valid */
-		args->done = 1; /* DONE bit */
-	} else if (!args->enabled_channels)
+	if (!args->enabled_channels)
 		return false; /* unnecessary NULL export */
 
 	return true;
@@ -6576,7 +6572,6 @@ handle_fs_outputs_post(struct radv_shader_context *ctx)
 
 	for (unsigned i = 0; i < AC_LLVM_MAX_OUTPUTS; ++i) {
 		LLVMValueRef values[4];
-		bool last = false;
 
 		if (!(ctx->output_mask & (1ull << i)))
 			continue;
@@ -6588,14 +6583,9 @@ handle_fs_outputs_post(struct radv_shader_context *ctx)
 			values[j] = ac_to_float(&ctx->ac,
 						radv_load_output(ctx, i, j));
 
-		if (!ctx->shader_info->info.ps.writes_z &&
-		    !ctx->shader_info->info.ps.writes_stencil &&
-		    !ctx->shader_info->info.ps.writes_sample_mask)
-			last = ctx->output_mask <= ((1ull << (i + 1)) - 1);
-
 		bool ret = si_export_mrt_color(ctx, values,
 					       i - FRAG_RESULT_DATA0,
-					       last, &color_args[index]);
+					       &color_args[index]);
 		if (ret)
 			index++;
 	}
@@ -6614,6 +6604,19 @@ handle_fs_outputs_post(struct radv_shader_context *ctx)
 					 radv_load_output(ctx, FRAG_RESULT_SAMPLE_MASK, 0));
 	}
 
+	/* Set the DONE bit on last non-null color export only if Z isn't
+	 * exported.
+	 */
+	if (index > 0 &&
+	    !ctx->shader_info->info.ps.writes_z &&
+	    !ctx->shader_info->info.ps.writes_stencil &&
+	    !ctx->shader_info->info.ps.writes_sample_mask) {
+		unsigned last = index - 1;
+
+               color_args[last].valid_mask = 1; /* whether the EXEC mask is valid */
+               color_args[last].done = 1; /* DONE bit */
+	}
+
 	/* Export PS outputs. */
 	for (unsigned i = 0; i < index; i++)
 		ac_build_export(&ctx->ac, &color_args[i]);