OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

radv,aco: adjust the sample mask only if per-sample shading is enabled

Browse Source 
When per-sample shading isn't enabled, we can just load the
samplemask from the hardware which is always the coverage of
the entire pixel/fragment.

fossilds-db (VEGA10):
Totals from 131 (0.10% of 136546) affected shaders:
SGPRs: 5056 -> 5048 (-0.16%)
VGPRs: 2600 -> 2372 (-8.77%)
CodeSize: 115788 -> 112560 (-2.79%)
MaxWaves: 1266 -> 1274 (+0.63%)
Instrs: 20620 -> 20071 (-2.66%)
Cycles: 82416 -> 80220 (-2.66%)
VMEM: 51567 -> 35532 (-31.10%); split: +0.24%, -31.34%
SMEM: 8952 -> 8258 (-7.75%); split: +0.11%, -7.86%
SClause: 1223 -> 1199 (-1.96%); split: -2.62%, +0.65%
Copies: 1247 -> 1124 (-9.86%); split: -10.18%, +0.32%
PreVGPRs: 2112 -> 1981 (-6.20%)

Helps Britannia, Shadow of the Tomb Raider, Warhammer II and Control.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7377>
This commit is contained in:
Samuel Pitoiset
2020-10-29 16:39:28 +01:00
parent ea83fd9124
commit c63bcda22c
2 changed files with 19 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/amd/compiler/aco_instruction_selection.cpp
View File

@@ -6810,12 +6810,17 @@ void visit_load_sample_mask_in(isel_context *ctx, nir_intrinsic_instr *instr) {
Builder bld(ctx->program, ctx->block);
Temp dst = get_ssa_temp(ctx, &instr->dest.ssa);
if (log2_ps_iter_samples) {
Temp sample_id = bld.vop3(aco_opcode::v_bfe_u32, bld.def(v1),
get_arg(ctx, ctx->args->ac.ancillary), Operand(8u), Operand(4u));
Temp ps_iter_mask = bld.copy(bld.def(v1), Operand(ps_iter_masks[log2_ps_iter_samples]));
Temp mask = bld.vop2(aco_opcode::v_lshlrev_b32, bld.def(v1), sample_id, ps_iter_mask);
Temp dst = get_ssa_temp(ctx, &instr->dest.ssa);
bld.vop2(aco_opcode::v_and_b32, Definition(dst), mask, get_arg(ctx, ctx->args->ac.sample_coverage));
} else {
bld.copy(Definition(dst), get_arg(ctx, ctx->args->ac.sample_coverage));
}
}
unsigned gs_outprim_vertices(unsigned outprim)

5
src/amd/vulkan/radv_nir_to_llvm.c
View File

@@ -758,10 +758,15 @@ static LLVMValueRef load_sample_mask_in(struct ac_shader_abi *abi)
uint32_t ps_iter_mask = ps_iter_masks[log2_ps_iter_samples];
LLVMValueRef result, sample_id;
if (log2_ps_iter_samples) {
sample_id = ac_unpack_param(&ctx->ac, ac_get_arg(&ctx->ac, ctx->args->ac.ancillary), 8, 4);
sample_id = LLVMBuildShl(ctx->ac.builder, LLVMConstInt(ctx->ac.i32, ps_iter_mask, false), sample_id, "");
result = LLVMBuildAnd(ctx->ac.builder, sample_id,
ac_get_arg(&ctx->ac, ctx->args->ac.sample_coverage), "");
} else {
result = ac_get_arg(&ctx->ac, ctx->args->ac.sample_coverage);
}
return result;
}