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

ac: unify build_sendmsg_gs_alloc_req

Browse Source 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
This commit is contained in:
Marek Olšák
2020-01-03 15:56:18 -05:00
parent fd84e422b6
commit 1c77a18cc2
4 changed files with 31 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/amd/llvm/ac_llvm_build.c
View File

@@ -4728,6 +4728,26 @@ ac_export_mrt_z(struct ac_llvm_context *ctx, LLVMValueRef depth,
args->enabled_channels = mask;
}
/* Send GS Alloc Req message from the first wave of the group to SPI.
* Message payload is:
* - bits 0..10: vertices in group
* - bits 12..22: primitives in group
*/
void ac_build_sendmsg_gs_alloc_req(struct ac_llvm_context *ctx, LLVMValueRef wave_id,
LLVMValueRef vtx_cnt, LLVMValueRef prim_cnt)
{
LLVMBuilderRef builder = ctx->builder;
LLVMValueRef tmp;
ac_build_ifcc(ctx, LLVMBuildICmp(builder, LLVMIntEQ, wave_id, ctx->i32_0, ""), 5020);
tmp = LLVMBuildShl(builder, prim_cnt, LLVMConstInt(ctx->i32, 12, false),"");
tmp = LLVMBuildOr(builder, tmp, vtx_cnt, "");
ac_build_sendmsg(ctx, AC_SENDMSG_GS_ALLOC_REQ, tmp);
ac_build_endif(ctx, 5020);
}
static LLVMTypeRef
arg_llvm_type(enum ac_arg_type type, unsigned size, struct ac_llvm_context *ctx)
{

3
src/amd/llvm/ac_llvm_build.h
View File

@@ -747,6 +747,9 @@ ac_export_mrt_z(struct ac_llvm_context *ctx, LLVMValueRef depth,
LLVMValueRef stencil, LLVMValueRef samplemask,
struct ac_export_args *args);
void ac_build_sendmsg_gs_alloc_req(struct ac_llvm_context *ctx, LLVMValueRef wave_id,
LLVMValueRef vtx_cnt, LLVMValueRef prim_cnt);
static inline LLVMValueRef
ac_get_arg(struct ac_llvm_context *ctx, struct ac_arg arg)
{

28
src/amd/vulkan/radv_nir_to_llvm.c
View File

@@ -2371,28 +2371,6 @@ ngg_gs_emit_vertex_ptr(struct radv_shader_context *ctx, LLVMValueRef gsthread,
return ngg_gs_vertex_ptr(ctx, vertexidx);
}
/* Send GS Alloc Req message from the first wave of the group to SPI.
* Message payload is:
* - bits 0..10: vertices in group
* - bits 12..22: primitives in group
*/
static void build_sendmsg_gs_alloc_req(struct radv_shader_context *ctx,
LLVMValueRef vtx_cnt,
LLVMValueRef prim_cnt)
{
LLVMBuilderRef builder = ctx->ac.builder;
LLVMValueRef tmp;
tmp = LLVMBuildICmp(builder, LLVMIntEQ, get_wave_id_in_tg(ctx), ctx->ac.i32_0, "");
ac_build_ifcc(&ctx->ac, tmp, 5020);
tmp = LLVMBuildShl(builder, prim_cnt, LLVMConstInt(ctx->ac.i32, 12, false),"");
tmp = LLVMBuildOr(builder, tmp, vtx_cnt, "");
ac_build_sendmsg(&ctx->ac, AC_SENDMSG_GS_ALLOC_REQ, tmp);
ac_build_endif(&ctx->ac, 5020);
}
struct ngg_prim {
unsigned num_vertices;
LLVMValueRef isnull;
@@ -3020,7 +2998,8 @@ handle_ngg_outputs_post_2(struct radv_shader_context *ctx)
/* TODO: primitive culling */
build_sendmsg_gs_alloc_req(ctx, ngg_get_vtx_cnt(ctx), ngg_get_prim_cnt(ctx));
ac_build_sendmsg_gs_alloc_req(&ctx->ac, get_wave_id_in_tg(ctx),
ngg_get_vtx_cnt(ctx), ngg_get_prim_cnt(ctx));
/* TODO: streamout queries */
/* Export primitive data to the index buffer. Format is:
@@ -3317,7 +3296,8 @@ static void gfx10_ngg_gs_emit_epilogue_2(struct radv_shader_context *ctx)
* there are 4 or more contiguous null primitives in the export
* (in the common case of single-dword prim exports).
*/
build_sendmsg_gs_alloc_req(ctx, vertlive_scan.result_reduce, num_emit_threads);
ac_build_sendmsg_gs_alloc_req(&ctx->ac, get_wave_id_in_tg(ctx),
vertlive_scan.result_reduce, num_emit_threads);
/* Setup the reverse vertex compaction permutation. We re-use stream 1
* of the primitive liveness flags, relying on the fact that each

28
src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
View File

@@ -71,28 +71,6 @@ static LLVMValueRef ngg_get_query_buf(struct si_shader_context *ctx)
LLVMConstInt(ctx->i32, GFX10_GS_QUERY_BUF, false));
}
/* Send GS Alloc Req message from the first wave of the group to SPI.
* Message payload is:
* - bits 0..10: vertices in group
* - bits 12..22: primitives in group
*/
static void build_sendmsg_gs_alloc_req(struct si_shader_context *ctx,
LLVMValueRef vtx_cnt,
LLVMValueRef prim_cnt)
{
LLVMBuilderRef builder = ctx->ac.builder;
LLVMValueRef tmp;
tmp = LLVMBuildICmp(builder, LLVMIntEQ, get_wave_id_in_tg(ctx), ctx->ac.i32_0, "");
ac_build_ifcc(&ctx->ac, tmp, 5020);
tmp = LLVMBuildShl(builder, prim_cnt, LLVMConstInt(ctx->ac.i32, 12, false),"");
tmp = LLVMBuildOr(builder, tmp, vtx_cnt, "");
ac_build_sendmsg(&ctx->ac, AC_SENDMSG_GS_ALLOC_REQ, tmp);
ac_build_endif(&ctx->ac, 5020);
}
struct ngg_prim {
unsigned num_vertices;
LLVMValueRef isnull;
@@ -676,7 +654,8 @@ void gfx10_emit_ngg_epilogue(struct ac_shader_abi *abi,
ac_build_endif(&ctx->ac, 5400);
}
build_sendmsg_gs_alloc_req(ctx, ngg_get_vtx_cnt(ctx), ngg_get_prim_cnt(ctx));
ac_build_sendmsg_gs_alloc_req(&ctx->ac, get_wave_id_in_tg(ctx),
ngg_get_vtx_cnt(ctx), ngg_get_prim_cnt(ctx));
/* Update query buffer */
/* TODO: this won't catch 96-bit clear_buffer via transform feedback. */
@@ -1213,7 +1192,8 @@ void gfx10_ngg_gs_emit_epilogue(struct si_shader_context *ctx)
* there are 4 or more contiguous null primitives in the export
* (in the common case of single-dword prim exports).
*/
build_sendmsg_gs_alloc_req(ctx, vertlive_scan.result_reduce, num_emit_threads);
ac_build_sendmsg_gs_alloc_req(&ctx->ac, get_wave_id_in_tg(ctx),
vertlive_scan.result_reduce, num_emit_threads);
/* Setup the reverse vertex compaction permutation. We re-use stream 1
* of the primitive liveness flags, relying on the fact that each