/external/llvm-project/polly/test/ScopInfo/ |
D | invariant_load_complex_condition.ll | 26 ; CHECK-NEXT: [block_y, block_x] -> { Stmt_entry_split[] }; 28 ; CHECK-NEXT: [block_y, block_x] -> { Stmt_entry_split[] -> [] }; 30 …block_y, block_x] -> { Stmt_entry_split[] -> MemRef4[o0] : (-3 <= block_y < 0 and block_x <= -4 an… 32 ; CHECK-NEXT: [block_y, block_x] -> { Stmt_entry_split[] -> MemRef0[] }; 38 define void @dct_luma(i32 %block_x, i32 %block_y) #0 { 44 %div1 = sdiv i32 %block_y, 4
|
/external/tensorflow/tensorflow/lite/delegates/gpu/common/tasks/ |
D | fully_connected.h | 69 for (int block_y = 0; 4 * block_y < padded_dst_channels; block_y++) { in RearrangeFCWeightsToIOO4I4() local 73 int y = 4 * block_y + y_in_block; in RearrangeFCWeightsToIOO4I4() 77 int dst_index = block_x * padded_dst_channels * 4 + block_y * 16 + in RearrangeFCWeightsToIOO4I4()
|
/external/tensorflow/tensorflow/lite/delegates/gpu/common/tasks/special/ |
D | fc_fc_add.h | 47 for (int block_y = 0; 4 * block_y < padded_dst_channels; block_y++) { in RearrangeFCWeightsToIOO4I4() local 51 int y = 4 * block_y + y_in_block; in RearrangeFCWeightsToIOO4I4() 53 int dst_index = block_x * padded_dst_channels * 4 + block_y * 16 + in RearrangeFCWeightsToIOO4I4()
|
/external/llvm-project/mlir/test/Dialect/GPU/ |
D | outlining.mlir | 28 threads(%tx, %ty, %tz) in (%block_x = %bDimX, %block_y = %bDimY, 70 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, 101 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, 125 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, 153 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, 180 threads(%tx, %ty, %tz) in (%block_x = %c1, %block_y = %c1, 206 threads(%tx, %ty, %tz) in (%block_x = %c1, %block_y = %c1, 225 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst,
|
D | multiple-all-reduce.mlir | 11 threads(%tx, %ty, %tz) in (%block_x = %c1, %block_y = %c1, %block_z = %c1) {
|
D | ops.mlir | 9 threads(%tx, %ty, %tz) in (%block_x = %sz, %block_y = %sz, %block_z = %sz) { 20 threads(%tx, %ty, %tz) in (%block_x = %thrd, %block_y = %thrd, %block_z = %thrd) {
|
/external/pdfium/third_party/libopenjpeg20/ |
D | sparse_array.c | 117 OPJ_UINT32 y, block_y; in opj_sparse_array_int32_read_or_write() local 125 block_y = y0 / sa->block_height; in opj_sparse_array_int32_read_or_write() 126 for (y = y0; y < y1; block_y ++, y += y_incr) { in opj_sparse_array_int32_read_or_write() 142 src_block = sa->data_blocks[block_y * sa->block_count_hor + block_x]; in opj_sparse_array_int32_read_or_write() 242 sa->data_blocks[block_y * sa->block_count_hor + block_x] = src_block; in opj_sparse_array_int32_read_or_write()
|
/external/llvm-project/mlir/test/mlir-cuda-runner/ |
D | two-modules.mlir | 13 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %one, %block_z = %one) { 19 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %one, %block_z = %one) {
|
D | all-reduce-op.mlir | 16 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %sy, %block_z = %sz) { 17 %t0 = muli %tz, %block_y : index
|
D | gpu-to-cubin.mlir | 8 threads(%tx, %ty, %tz) in (%block_x = %cst2, %block_y = %cst, %block_z = %cst) {
|
D | all-reduce-region.mlir | 13 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %one, %block_z = %one) {
|
D | shuffle.mlir | 13 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %one, %block_z = %one) {
|
D | all-reduce-max.mlir | 48 threads(%tx, %ty, %tz) in (%block_x = %c6, %block_y = %c1, %block_z = %c1) {
|
D | all-reduce-or.mlir | 48 threads(%tx, %ty, %tz) in (%block_x = %c6, %block_y = %c1, %block_z = %c1) {
|
D | all-reduce-min.mlir | 48 threads(%tx, %ty, %tz) in (%block_x = %c6, %block_y = %c1, %block_z = %c1) {
|
D | all-reduce-xor.mlir | 48 threads(%tx, %ty, %tz) in (%block_x = %c6, %block_y = %c1, %block_z = %c1) {
|
/external/llvm-project/mlir/test/mlir-rocm-runner/ |
D | two-modules.mlir | 14 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %c1, %block_z = %c1) { 20 threads(%tx, %ty, %tz) in (%block_x = %sx, %block_y = %c1, %block_z = %c1) {
|
D | vector-transferops.mlir | 6 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) { 28 threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) {
|
D | gpu-to-hsaco.mlir | 8 threads(%tx, %ty, %tz) in (%block_x = %block_dim, %block_y = %c1, %block_z = %c1) {
|
D | vecadd.mlir | 8 threads(%tx, %ty, %tz) in (%block_x = %block_dim, %block_y = %c1, %block_z = %c1) {
|
/external/mesa3d/src/panfrost/shared/ |
D | pan_tiling.c | 194 uint16_t block_y = y & ~0x0f; \ 195 uint8_t *dest = (uint8_t *) (dest_start + (block_y * dst_stride)); \ 220 unsigned block_y = y & ~mask; \ 221 unsigned block_start_s = block_y * dst_stride; \
|
/external/llvm/test/Transforms/LoopSimplify/ |
D | notify-scev.ll | 49 …%block_y.09.us = phi i32 [ 0, %for.cond135.preheader.lr.ph.split.us ], [ %add184.us, %for.cond132.… 53 %add184.us = add nsw i32 %block_y.09.us, 4 67 %j.04.us = phi i32 [ %block_y.09.us, %for.cond138.preheader.us ], [ undef, %for.inc172.us ]
|
/external/llvm-project/llvm/test/Transforms/LoopSimplify/ |
D | notify-scev.ll | 49 …%block_y.09.us = phi i32 [ 0, %for.cond135.preheader.lr.ph.split.us ], [ %add184.us, %for.cond132.… 53 %add184.us = add nsw i32 %block_y.09.us, 4 67 %j.04.us = phi i32 [ %block_y.09.us, %for.cond138.preheader.us ], [ undef, %for.inc172.us ]
|
/external/tensorflow/tensorflow/core/profiler/internal/gpu/ |
D | cupti_collector.h | 87 uint32 block_y; member 106 kernel_info.block_y, ",", kernel_info.block_z, in ToXStat()
|
/external/tensorflow/tensorflow/core/profiler/utils/ |
D | kernel_stats_utils_test.cc | 76 kernel_info.block_y = 8; in TEST()
|