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

radv/llvm: use ac_build_gep0_type to get args types

Browse Source 
Reviewed-by: Mihai Preda <mhpreda@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19035>
This commit is contained in:
Pierre-Eric Pelloux-Prayer
2022-10-10 12:30:26 +02:00
committed by Marge Bot
parent f12adf2cc9
commit cb117cdc96
1 changed files with 13 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/amd/vulkan/radv_nir_to_llvm.c
View File

@@ -108,12 +108,13 @@ load_descriptor_sets(struct radv_shader_context *ctx)
uint32_t mask = ctx->shader_info->desc_set_used_mask; uint32_t mask = ctx->shader_info->desc_set_used_mask;
if (user_sgprs_locs->shader_data[AC_UD_INDIRECT_DESCRIPTOR_SETS].sgpr_idx != -1) { if (user_sgprs_locs->shader_data[AC_UD_INDIRECT_DESCRIPTOR_SETS].sgpr_idx != -1) {
LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args->ac, ctx->args->descriptor_sets[0]);
LLVMValueRef desc_sets = ac_get_arg(&ctx->ac, ctx->args->descriptor_sets[0]); LLVMValueRef desc_sets = ac_get_arg(&ctx->ac, ctx->args->descriptor_sets[0]);
while (mask) { while (mask) {
int i = u_bit_scan(&mask); int i = u_bit_scan(&mask);
ctx->descriptor_sets[i] = ctx->descriptor_sets[i] =
ac_build_load_to_sgpr(&ctx->ac, desc_sets, LLVMConstInt(ctx->ac.i32, i, false)); ac_build_load_to_sgpr2(&ctx->ac, type, desc_sets, LLVMConstInt(ctx->ac.i32, i, false));
LLVMSetAlignment(ctx->descriptor_sets[i], 4); LLVMSetAlignment(ctx->descriptor_sets[i], 4);
} }
} else { } else {
@@ -347,6 +348,7 @@ static void
load_vs_input(struct radv_shader_context *ctx, unsigned driver_location, LLVMTypeRef dest_type, load_vs_input(struct radv_shader_context *ctx, unsigned driver_location, LLVMTypeRef dest_type,
LLVMValueRef out[4]) LLVMValueRef out[4])
{ {
LLVMTypeRef t_list_type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args->ac, ctx->args->ac.vertex_buffers);
LLVMValueRef t_list_ptr = ac_get_arg(&ctx->ac, ctx->args->ac.vertex_buffers); LLVMValueRef t_list_ptr = ac_get_arg(&ctx->ac, ctx->args->ac.vertex_buffers);
LLVMValueRef t_offset; LLVMValueRef t_offset;
LLVMValueRef t_list; LLVMValueRef t_list;
@@ -398,7 +400,7 @@ load_vs_input(struct radv_shader_context *ctx, unsigned driver_location, LLVMTyp
desc_index = util_bitcount(ctx->shader_info->vs.vb_desc_usage_mask & desc_index = util_bitcount(ctx->shader_info->vs.vb_desc_usage_mask &
u_bit_consecutive(0, desc_index)); u_bit_consecutive(0, desc_index));
t_offset = LLVMConstInt(ctx->ac.i32, desc_index, false); t_offset = LLVMConstInt(ctx->ac.i32, desc_index, false);
t_list = ac_build_load_to_sgpr(&ctx->ac, t_list_ptr, t_offset); t_list = ac_build_load_to_sgpr2(&ctx->ac, t_list_type, t_list_ptr, t_offset);
/* Always split typed vertex buffer loads on GFX6 and GFX10+ to avoid any alignment issues that /* Always split typed vertex buffer loads on GFX6 and GFX10+ to avoid any alignment issues that
* triggers memory violations and eventually a GPU hang. This can happen if the stride (static or * triggers memory violations and eventually a GPU hang. This can happen if the stride (static or
@@ -794,6 +796,7 @@ radv_emit_streamout(struct radv_shader_context *ctx, unsigned stream)
*/ */
LLVMValueRef so_write_offset[4] = {0}; LLVMValueRef so_write_offset[4] = {0};
LLVMValueRef so_buffers[4] = {0}; LLVMValueRef so_buffers[4] = {0};
LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args->ac, ctx->args->streamout_buffers);
LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->args->streamout_buffers); LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->args->streamout_buffers);
for (i = 0; i < 4; i++) { for (i = 0; i < 4; i++) {
@@ -804,7 +807,7 @@ radv_emit_streamout(struct radv_shader_context *ctx, unsigned stream)
LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, i, false); LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, i, false);
so_buffers[i] = ac_build_load_to_sgpr(&ctx->ac, buf_ptr, offset); so_buffers[i] = ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr, offset);
LLVMValueRef so_offset = ac_get_arg(&ctx->ac, ctx->args->ac.streamout_offset[i]); LLVMValueRef so_offset = ac_get_arg(&ctx->ac, ctx->args->ac.streamout_offset[i]);
@@ -1178,11 +1181,11 @@ ac_setup_rings(struct radv_shader_context *ctx)
unsigned ring = ctx->stage == MESA_SHADER_GEOMETRY ? RING_ESGS_GS : RING_ESGS_VS; unsigned ring = ctx->stage == MESA_SHADER_GEOMETRY ? RING_ESGS_GS : RING_ESGS_VS;
LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, ring, false); LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, ring, false);
ctx->esgs_ring = ac_build_load_to_sgpr(&ctx->ac, ctx->ring_offsets, offset); ctx->esgs_ring = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets, offset);
} }
if (ctx->args->is_gs_copy_shader) { if (ctx->args->is_gs_copy_shader) {
ctx->gsvs_ring[0] = ac_build_load_to_sgpr(&ctx->ac, ctx->ring_offsets, ctx->gsvs_ring[0] = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
LLVMConstInt(ctx->ac.i32, RING_GSVS_VS, false)); LLVMConstInt(ctx->ac.i32, RING_GSVS_VS, false));
} }
@@ -1200,7 +1203,7 @@ ac_setup_rings(struct radv_shader_context *ctx)
unsigned num_records = ctx->ac.wave_size; unsigned num_records = ctx->ac.wave_size;
LLVMValueRef base_ring; LLVMValueRef base_ring;
base_ring = ac_build_load_to_sgpr(&ctx->ac, ctx->ring_offsets, base_ring = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
LLVMConstInt(ctx->ac.i32, RING_GSVS_GS, false)); LLVMConstInt(ctx->ac.i32, RING_GSVS_GS, false));
for (unsigned stream = 0; stream < 4; stream++) { for (unsigned stream = 0; stream < 4; stream++) {
@@ -1240,10 +1243,10 @@ ac_setup_rings(struct radv_shader_context *ctx)
} }
if (ctx->stage == MESA_SHADER_TESS_CTRL || ctx->stage == MESA_SHADER_TESS_EVAL) { if (ctx->stage == MESA_SHADER_TESS_CTRL || ctx->stage == MESA_SHADER_TESS_EVAL) {
ctx->hs_ring_tess_offchip = ac_build_load_to_sgpr( ctx->hs_ring_tess_offchip = ac_build_load_to_sgpr2(
&ctx->ac, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_OFFCHIP, false)); &ctx->ac, ctx->ac.i8, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_OFFCHIP, false));
ctx->hs_ring_tess_factor = ac_build_load_to_sgpr( ctx->hs_ring_tess_factor = ac_build_load_to_sgpr2(
&ctx->ac, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_FACTOR, false)); &ctx->ac, ctx->ac.i8, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_FACTOR, false));
} }
} }