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>
---
src/amd/common/ac_nir_to_llvm.c | 98 ++++++++++++++++++++++-------------------
1 file changed, 52 insertions(+), 46 deletions(-)
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index ea51c3a54a..c370c80ec7 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -6484,67 +6484,73 @@ handle_tcs_outputs_post(struct radv_shader_context *ctx)
write_tess_factors(ctx);
}
-static bool
-si_export_mrt_color(struct radv_shader_context *ctx,
- LLVMValueRef *color, unsigned index, bool is_last,
- 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)
- return false; /* unnecessary NULL export */
-
- return true;
-}
+struct radv_ps_exports {
+ unsigned num;
+ struct ac_export_args args[10];
+};
static void
radv_export_mrt_z(struct radv_shader_context *ctx,
LLVMValueRef depth, LLVMValueRef stencil,
- LLVMValueRef samplemask)
+ LLVMValueRef samplemask, struct radv_ps_exports *exp)
{
struct ac_export_args args;
ac_export_mrt_z(&ctx->ac, depth, stencil, samplemask, &args);
- ac_build_export(&ctx->ac, &args);
+ memcpy(&exp->args[exp->num++], &args, sizeof(args));
}
static void
handle_fs_outputs_post(struct radv_shader_context *ctx)
{
- unsigned index = 0;
LLVMValueRef depth = NULL, stencil = NULL, samplemask = NULL;
- struct ac_export_args color_args[8];
+ struct radv_ps_exports exp = {};
+ struct ac_export_args args[8];
+ int last_color_export = -1;
+ int last_non_null = -1;
+ unsigned colors_written;
+
+ /* Find the last written color export. */
+ colors_written = ctx->output_mask >> FRAG_RESULT_DATA0;
+ if (!ctx->shader_info->info.ps.writes_z &&
+ !ctx->shader_info->info.ps.writes_stencil &&
+ !ctx->shader_info->info.ps.writes_sample_mask) {
+ last_color_export = util_last_bit(colors_written) - 1;
+ }
+
+ /* Get the export arguments, and find the last non-null color export. */
+ for (unsigned mrt = 0; mrt < 8; mrt++) {
+ unsigned index = mrt + FRAG_RESULT_DATA0;
+ LLVMValueRef color[4];
+
+ if (!(colors_written & (1 << mrt)))
+ continue;
- for (unsigned i = 0; i < AC_LLVM_MAX_OUTPUTS; ++i) {
- LLVMValueRef values[4];
- bool last = false;
+ for (unsigned chan = 0; chan < 4; chan++) {
+ color[chan] =
+ ac_to_float(&ctx->ac,
+ radv_load_output(ctx, index, chan));
+ }
- if (!(ctx->output_mask & (1ull << i)))
- continue;
+ si_llvm_init_export_args(ctx, color, 0xf,
+ V_008DFC_SQ_EXP_MRT + mrt, &args[mrt]);
+ if (args[mrt].enabled_channels)
+ last_non_null = mrt;
+ }
- if (i < FRAG_RESULT_DATA0)
+ /* Emit all exports. */
+ for (unsigned mrt = 0; mrt < 8; mrt++) {
+ if (!(colors_written & (1 << mrt)))
continue;
- for (unsigned j = 0; j < 4; j++)
- values[j] = ac_to_float(&ctx->ac,
- radv_load_output(ctx, i, j));
+ if (last_color_export != -1 && last_non_null == mrt) {
+ args[mrt].valid_mask = 1; /* whether the EXEC mask is valid */
+ args[mrt].done = 1; /* DONE bit */
+ } else if (!args[mrt].enabled_channels)
+ continue; /* unnecessary NULL export */
- 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]);
- if (ret)
- index++;
+ memcpy(&exp.args[exp.num++], &args[mrt], sizeof(args[mrt]));
}
/* Process depth, stencil, samplemask. */
@@ -6561,14 +6567,14 @@ handle_fs_outputs_post(struct radv_shader_context *ctx)
radv_load_output(ctx, FRAG_RESULT_SAMPLE_MASK, 0));
}
- /* Export PS outputs. */
- for (unsigned i = 0; i < index; i++)
- ac_build_export(&ctx->ac, &color_args[i]);
-
if (depth || stencil || samplemask)
- radv_export_mrt_z(ctx, depth, stencil, samplemask);
- else if (!index)
+ radv_export_mrt_z(ctx, depth, stencil, samplemask, &exp);
+ else if (last_color_export == -1 || last_non_null == -1)
ac_build_export_null(&ctx->ac);
+
+ /* Export PS outputs. */
+ for (unsigned i = 0; i < exp.num; i++)
+ ac_build_export(&ctx->ac, &exp.args[i]);
}
static void
--
2.16.2