#include "brw_defines.h"
-static void
-prepare_indirect_gpgpu_walker(struct brw_context *brw)
-{
- const struct gen_device_info *devinfo = &brw->screen->devinfo;
- GLintptr indirect_offset = brw->compute.num_work_groups_offset;
- struct brw_bo *bo = brw->compute.num_work_groups_bo;
-
- brw_load_register_mem(brw, GEN7_GPGPU_DISPATCHDIMX, bo, indirect_offset + 0);
- brw_load_register_mem(brw, GEN7_GPGPU_DISPATCHDIMY, bo, indirect_offset + 4);
- brw_load_register_mem(brw, GEN7_GPGPU_DISPATCHDIMZ, bo, indirect_offset + 8);
-
- if (devinfo->gen > 7)
- return;
-
- /* Clear upper 32-bits of SRC0 and all 64-bits of SRC1 */
- BEGIN_BATCH(7);
- OUT_BATCH(MI_LOAD_REGISTER_IMM | (7 - 2));
- OUT_BATCH(MI_PREDICATE_SRC0 + 4);
- OUT_BATCH(0u);
- OUT_BATCH(MI_PREDICATE_SRC1 + 0);
- OUT_BATCH(0u);
- OUT_BATCH(MI_PREDICATE_SRC1 + 4);
- OUT_BATCH(0u);
- ADVANCE_BATCH();
-
- /* Load compute_dispatch_indirect_x_size into SRC0 */
- brw_load_register_mem(brw, MI_PREDICATE_SRC0, bo, indirect_offset + 0);
-
- /* predicate = (compute_dispatch_indirect_x_size == 0); */
- BEGIN_BATCH(1);
- OUT_BATCH(GEN7_MI_PREDICATE |
- MI_PREDICATE_LOADOP_LOAD |
- MI_PREDICATE_COMBINEOP_SET |
- MI_PREDICATE_COMPAREOP_SRCS_EQUAL);
- ADVANCE_BATCH();
-
- /* Load compute_dispatch_indirect_y_size into SRC0 */
- brw_load_register_mem(brw, MI_PREDICATE_SRC0, bo, indirect_offset + 4);
-
- /* predicate |= (compute_dispatch_indirect_y_size == 0); */
- BEGIN_BATCH(1);
- OUT_BATCH(GEN7_MI_PREDICATE |
- MI_PREDICATE_LOADOP_LOAD |
- MI_PREDICATE_COMBINEOP_OR |
- MI_PREDICATE_COMPAREOP_SRCS_EQUAL);
- ADVANCE_BATCH();
-
- /* Load compute_dispatch_indirect_z_size into SRC0 */
- brw_load_register_mem(brw, MI_PREDICATE_SRC0, bo, indirect_offset + 8);
-
- /* predicate |= (compute_dispatch_indirect_z_size == 0); */
- BEGIN_BATCH(1);
- OUT_BATCH(GEN7_MI_PREDICATE |
- MI_PREDICATE_LOADOP_LOAD |
- MI_PREDICATE_COMBINEOP_OR |
- MI_PREDICATE_COMPAREOP_SRCS_EQUAL);
- ADVANCE_BATCH();
-
- /* predicate = !predicate; */
- BEGIN_BATCH(1);
- OUT_BATCH(GEN7_MI_PREDICATE |
- MI_PREDICATE_LOADOP_LOADINV |
- MI_PREDICATE_COMBINEOP_OR |
- MI_PREDICATE_COMPAREOP_FALSE);
- ADVANCE_BATCH();
-}
-
-static void
-brw_emit_gpgpu_walker(struct brw_context *brw)
-{
- const struct gen_device_info *devinfo = &brw->screen->devinfo;
- const struct brw_cs_prog_data *prog_data =
- brw_cs_prog_data(brw->cs.base.prog_data);
-
- const GLuint *num_groups = brw->compute.num_work_groups;
- uint32_t indirect_flag;
-
- if (brw->compute.num_work_groups_bo == NULL) {
- indirect_flag = 0;
- } else {
- indirect_flag =
- GEN7_GPGPU_INDIRECT_PARAMETER_ENABLE |
- (devinfo->gen == 7 ? GEN7_GPGPU_PREDICATE_ENABLE : 0);
- prepare_indirect_gpgpu_walker(brw);
- }
-
- const unsigned simd_size = prog_data->simd_size;
- unsigned group_size = prog_data->local_size[0] *
- prog_data->local_size[1] * prog_data->local_size[2];
- unsigned thread_width_max =
- (group_size + simd_size - 1) / simd_size;
-
- uint32_t right_mask = 0xffffffffu >> (32 - simd_size);
- const unsigned right_non_aligned = group_size & (simd_size - 1);
- if (right_non_aligned != 0)
- right_mask >>= (simd_size - right_non_aligned);
-
- uint32_t dwords = devinfo->gen < 8 ? 11 : 15;
- BEGIN_BATCH(dwords);
- OUT_BATCH(GPGPU_WALKER << 16 | (dwords - 2) | indirect_flag);
- OUT_BATCH(0);
- if (devinfo->gen >= 8) {
- OUT_BATCH(0); /* Indirect Data Length */
- OUT_BATCH(0); /* Indirect Data Start Address */
- }
- assert(thread_width_max <= brw->screen->devinfo.max_cs_threads);
- OUT_BATCH(SET_FIELD(simd_size / 16, GPGPU_WALKER_SIMD_SIZE) |
- SET_FIELD(thread_width_max - 1, GPGPU_WALKER_THREAD_WIDTH_MAX));
- OUT_BATCH(0); /* Thread Group ID Starting X */
- if (devinfo->gen >= 8)
- OUT_BATCH(0); /* MBZ */
- OUT_BATCH(num_groups[0]); /* Thread Group ID X Dimension */
- OUT_BATCH(0); /* Thread Group ID Starting Y */
- if (devinfo->gen >= 8)
- OUT_BATCH(0); /* MBZ */
- OUT_BATCH(num_groups[1]); /* Thread Group ID Y Dimension */
- OUT_BATCH(0); /* Thread Group ID Starting/Resume Z */
- OUT_BATCH(num_groups[2]); /* Thread Group ID Z Dimension */
- OUT_BATCH(right_mask); /* Right Execution Mask */
- OUT_BATCH(0xffffffff); /* Bottom Execution Mask */
- ADVANCE_BATCH();
-
- BEGIN_BATCH(2);
- OUT_BATCH(MEDIA_STATE_FLUSH << 16 | (2 - 2));
- OUT_BATCH(0);
- ADVANCE_BATCH();
-}
-
-
static void
brw_dispatch_compute_common(struct gl_context *ctx)
{
struct brw_context *brw = brw_context(ctx);
- bool fail_next = false;
+ bool fail_next;
if (!_mesa_check_conditional_render(ctx))
return;
intel_batchbuffer_require_space(brw, 600);
brw_require_statebuffer_space(brw, 2500);
intel_batchbuffer_save_state(brw);
+ fail_next = intel_batchbuffer_saved_state_is_empty(brw);
retry:
brw->batch.no_wrap = true;
brw_upload_compute_state(brw);
- brw_emit_gpgpu_walker(brw);
+ brw->vtbl.emit_compute_walker(brw);
brw->batch.no_wrap = false;