summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSamuel Pitoiset <samuel.pitoiset@gmail.com>2018-01-10 20:12:11 +0100
committerSamuel Pitoiset <samuel.pitoiset@gmail.com>2018-01-26 12:14:27 +0100
commit310d17fcf17bdeb897f12b4577f8faf3abba9e77 (patch)
treecba4d8ac08e31f18ffd4cb90a30fca209cde0434
parent51e14bc3c00c3fe0511eae7eddc8d89365e964a2 (diff)
ac: only load used channels when sampling buffer views
This allows to reduce the number of dwords that are loaded with buffer_load_format_xyzw. For example, when the only used channel is 1, the driver will emit buffer_load_format_x instead. Shader stats for DOW3 (with some local hacky scripts for SPIRV): 143 shaders in 143 tests Totals: SGPRS: 5344 -> 5352 (0.15 %) VGPRS: 3476 -> 3452 (-0.69 %) Spilled SGPRs: 30 -> 29 (-3.33 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 0 -> 0 (0.00 %) Scratch size: 0 -> 0 (0.00 %) dwords per thread Code Size: 269860 -> 269808 (-0.02 %) bytes LDS: 0 -> 0 (0.00 %) blocks Max Waves: 1267 -> 1272 (0.39 %) Wait states: 0 -> 0 (0.00 %) Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
-rw-r--r--src/amd/common/ac_nir_to_llvm.c5
1 files changed, 4 insertions, 1 deletions
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index b40769fe5a0..5b8c346d005 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -2315,11 +2315,14 @@ static LLVMValueRef build_tex_intrinsic(struct ac_nir_context *ctx,
struct ac_image_args *args)
{
if (instr->sampler_dim == GLSL_SAMPLER_DIM_BUF) {
+ unsigned mask = nir_ssa_def_components_read(&instr->dest.ssa);
+
return ac_build_buffer_load_format(&ctx->ac,
args->resource,
args->addr,
ctx->ac.i32_0,
- 4, true);
+ util_last_bit(mask),
+ true);
}
args->opcode = ac_image_sample;