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

nir,ac/llvm: add nir_load_smem_buffer_amd

Browse Source 
Used by radeonsi to load const buffer.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18010>
This commit is contained in:
Qiang Yu
2022-08-10 16:57:37 +08:00
committed by Marge Bot
parent 73ea7d651a
commit 8030fbcf16
3 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/amd/llvm/ac_nir_to_llvm.c
View File

@@ -4403,6 +4403,15 @@ static bool visit_intrinsic(struct ac_nir_context *ctx, nir_intrinsic_instr *ins
LLVMSetMetadata(result, ctx->ac.invariant_load_md_kind, ctx->ac.empty_md);
break;
}
case nir_intrinsic_load_smem_buffer_amd: {
LLVMValueRef descriptor = get_src(ctx, instr->src[0]);
LLVMValueRef offset = get_src(ctx, instr->src[1]);
unsigned num_components = instr->dest.ssa.num_components;
result = ac_build_buffer_load(&ctx->ac, descriptor, num_components, NULL, offset, NULL,
ctx->ac.i32, 0, true, true);
break;
}
case nir_intrinsic_ordered_xfb_counter_add_amd: {
/* must be called in a single lane of a workgroup. */
LLVMTypeRef gdsptr = LLVMPointerType(ctx->ac.i32, AC_ADDR_SPACE_GDS);

1
src/compiler/nir/nir_divergence_analysis.c
View File

@@ -185,6 +185,7 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
case nir_intrinsic_load_tess_level_outer_default:
case nir_intrinsic_load_scalar_arg_amd:
case nir_intrinsic_load_smem_amd:
case nir_intrinsic_load_smem_buffer_amd:
case nir_intrinsic_load_rt_dynamic_callable_stack_base_amd:
case nir_intrinsic_load_global_const_block_intel:
case nir_intrinsic_load_reloc_const_intel:

5
src/compiler/nir/nir_intrinsics.py
View File

@@ -1482,6 +1482,11 @@ intrinsic("load_smem_amd", src_comp=[1, 1], dest_comp=0, bit_sizes=[32],
indices=[ALIGN_MUL, ALIGN_OFFSET],
flags=[CAN_ELIMINATE, CAN_REORDER])
# src[] = { descriptor, offset }
intrinsic("load_smem_buffer_amd", src_comp=[4, 1], dest_comp=0, bit_sizes=[32],
indices=[ALIGN_MUL, ALIGN_OFFSET],
flags=[CAN_ELIMINATE, CAN_REORDER])
# src[] = { offset }.
intrinsic("load_shared2_amd", [1], dest_comp=2, indices=[OFFSET0, OFFSET1, ST64], flags=[CAN_ELIMINATE])