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

ac/llvm: don't use tbuffer_store as a fallback for swizzled stores

Browse Source 
This depends on the offset computation fix from:
   "ac/llvm: remove inst_offset parameter from ac_build_buffer_store_dword"

v2: The instruction type is changed to MUBUF, which requires us to clear
    DATA_FORMAT with ADD_TID_ENABLE.

Reviewed-by: Mihai Preda <mhpreda@gmail.com> (v1)
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> (v1)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15966>
This commit is contained in:
Marek Olšák
2022-04-15 02:00:55 -04:00
committed by Marge Bot
parent 4b63b5caa2
commit 6698753cdb
2 changed files with 14 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
src/amd/llvm/ac_llvm_build.c
View File

@@ -51,11 +51,6 @@ struct ac_llvm_flow {
LLVMBasicBlockRef loop_entry_block;
};
static void ac_build_tbuffer_store(struct ac_llvm_context *ctx, LLVMValueRef rsrc,
LLVMValueRef vdata, LLVMValueRef vindex, LLVMValueRef voffset,
LLVMValueRef soffset, unsigned num_channels, unsigned dfmt,
unsigned nfmt, unsigned cache_policy);
/* Initialize module-independent parts of the context.
*
* The caller is responsible for initializing ctx::module and ctx::builder.
@@ -1174,24 +1169,8 @@ void ac_build_buffer_store_dword(struct ac_llvm_context *ctx, LLVMValueRef rsrc,
return;
}
/* SWIZZLE_ENABLE requires that soffset isn't folded into voffset
* (voffset is swizzled, but soffset isn't swizzled).
* llvm.amdgcn.buffer.store doesn't have a separate soffset parameter.
*/
if (!(cache_policy & ac_swizzled)) {
ac_build_buffer_store_common(ctx, rsrc, ac_to_float(ctx, vdata), vindex, voffset, soffset,
cache_policy, false);
return;
}
static const unsigned dfmts[] = {V_008F0C_BUF_DATA_FORMAT_32, V_008F0C_BUF_DATA_FORMAT_32_32,
V_008F0C_BUF_DATA_FORMAT_32_32_32,
V_008F0C_BUF_DATA_FORMAT_32_32_32_32};
unsigned dfmt = dfmts[num_channels - 1];
unsigned nfmt = V_008F0C_BUF_NUM_FORMAT_UINT;
ac_build_tbuffer_store(ctx, rsrc, vdata, vindex, voffset, soffset, num_channels, dfmt,
nfmt, cache_policy);
ac_build_buffer_store_common(ctx, rsrc, ac_to_float(ctx, vdata), vindex, voffset, soffset,
cache_policy, false);
}
static LLVMValueRef ac_build_buffer_load_common(struct ac_llvm_context *ctx, LLVMValueRef rsrc,
@@ -1659,34 +1638,6 @@ LLVMValueRef ac_build_opencoded_load_format(struct ac_llvm_context *ctx, unsigne
return ac_build_gather_values(ctx, loads, 4);
}
static void ac_build_tbuffer_store(struct ac_llvm_context *ctx, LLVMValueRef rsrc,
LLVMValueRef vdata, LLVMValueRef vindex, LLVMValueRef voffset,
LLVMValueRef soffset, unsigned num_channels, unsigned dfmt,
unsigned nfmt, unsigned cache_policy)
{
LLVMValueRef args[7];
int idx = 0;
args[idx++] = vdata;
args[idx++] = LLVMBuildBitCast(ctx->builder, rsrc, ctx->v4i32, "");
if (vindex)
args[idx++] = vindex ? vindex : ctx->i32_0;
args[idx++] = voffset ? voffset : ctx->i32_0;
args[idx++] = soffset ? soffset : ctx->i32_0;
args[idx++] = LLVMConstInt(ctx->i32, ac_get_tbuffer_format(ctx->chip_class, dfmt, nfmt), 0);
args[idx++] = LLVMConstInt(ctx->i32, cache_policy, 0);
unsigned func =
!ac_has_vec3_support(ctx->chip_class, true) && num_channels == 3 ? 4 : num_channels;
const char *indexing_kind = vindex ? "struct" : "raw";
char name[256], type_name[8];
LLVMTypeRef type = func > 1 ? LLVMVectorType(ctx->i32, func) : ctx->i32;
ac_build_type_name_for_intr(type, type_name, sizeof(type_name));
snprintf(name, sizeof(name), "llvm.amdgcn.%s.tbuffer.store.%s", indexing_kind, type_name);
ac_build_intrinsic(ctx, name, ctx->voidt, args, idx, AC_FUNC_ATTR_INACCESSIBLE_MEM_ONLY);
}
void ac_build_tbuffer_store_short(struct ac_llvm_context *ctx, LLVMValueRef rsrc,
LLVMValueRef vdata, LLVMValueRef voffset, LLVMValueRef soffset,
unsigned cache_policy)

13
src/gallium/drivers/radeonsi/si_shader_llvm_gs.c
View File

@@ -332,6 +332,13 @@ void si_preload_esgs_ring(struct si_shader_context *ctx)
S_008F0C_ELEMENT_SIZE(1) |
S_008F0C_INDEX_STRIDE(3) |
S_008F0C_ADD_TID_ENABLE(1), 0), "");
/* If MUBUF && ADD_TID_ENABLE, DATA_FORMAT means STRIDE[14:17] on gfx8-9, so set 0. */
if (ctx->screen->info.chip_class == GFX8) {
desc3 = LLVMBuildAnd(builder, desc3,
LLVMConstInt(ctx->ac.i32, C_008F0C_DATA_FORMAT, 0), "");
}
ctx->esgs_ring = LLVMBuildInsertElement(builder, ctx->esgs_ring, desc1, ctx->ac.i32_1, "");
ctx->esgs_ring = LLVMBuildInsertElement(builder, ctx->esgs_ring, desc3,
LLVMConstInt(ctx->ac.i32, 3, 0), "");
@@ -408,8 +415,12 @@ void si_preload_gs_rings(struct si_shader_context *ctx)
rsrc3 |= S_008F0C_FORMAT(V_008F0C_GFX10_FORMAT_32_FLOAT) |
S_008F0C_OOB_SELECT(V_008F0C_OOB_SELECT_DISABLED) | S_008F0C_RESOURCE_LEVEL(1);
} else {
/* If MUBUF && ADD_TID_ENABLE, DATA_FORMAT means STRIDE[14:17] on gfx8-9, so set 0. */
unsigned data_format = ctx->ac.chip_class == GFX8 || ctx->ac.chip_class == GFX9 ?
0 : V_008F0C_BUF_DATA_FORMAT_32;
rsrc3 |= S_008F0C_NUM_FORMAT(V_008F0C_BUF_NUM_FORMAT_FLOAT) |
S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32) |
S_008F0C_DATA_FORMAT(data_format) |
S_008F0C_ELEMENT_SIZE(1); /* element_size = 4 (bytes) */
}