gpu_blocks         30 apps/cuda_mat_mul/mat_mul_generator.cpp             .gpu_blocks(x, y).gpu_threads(xii);
gpu_blocks         36 python_bindings/python/Func_gpu.h     return that.gpu_blocks(block_x, device_api);
gpu_blocks         41 python_bindings/python/Func_gpu.h     return that.gpu_blocks(block_x, block_y, device_api);
gpu_blocks         46 python_bindings/python/Func_gpu.h     return that.gpu_blocks(block_x, block_y, block_z, device_api);
gpu_blocks        108 python_bindings/python/Var.cpp                          .def("gpu_blocks", &Var::gpu_blocks,  // no args
gpu_blocks       1574 src/Func.cpp       return gpu_blocks(bx).gpu_threads(tx);
gpu_blocks       1579 src/Func.cpp       return gpu_blocks(bx, by).gpu_threads(tx, ty);
gpu_blocks       1585 src/Func.cpp       return gpu_blocks(bx, by, bz).gpu_threads(tx, ty, tz);
gpu_blocks       2044 src/Func.cpp       Stage(func.definition(), name(), args(), func.schedule().storage_dims()).gpu_blocks(bx, device_api);
gpu_blocks       2050 src/Func.cpp       Stage(func.definition(), name(), args(), func.schedule().storage_dims()).gpu_blocks(bx, by, device_api);
gpu_blocks       2056 src/Func.cpp       Stage(func.definition(), name(), args(), func.schedule().storage_dims()).gpu_blocks(bx, by, bz, device_api);
gpu_blocks       2192 src/Func.cpp       Stage(func.definition(), name(), args(), func.schedule().storage_dims()).gpu_blocks(x, y, device_api);
gpu_blocks        211 src/Func.h         EXPORT Stage &gpu_blocks(VarOrRVar block_x, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks        212 src/Func.h         EXPORT Stage &gpu_blocks(VarOrRVar block_x, VarOrRVar block_y, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks        213 src/Func.h         EXPORT Stage &gpu_blocks(VarOrRVar block_x, VarOrRVar block_y, VarOrRVar block_z, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks       1455 src/Func.h         EXPORT Func &gpu_blocks(VarOrRVar block_x, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks       1456 src/Func.h         EXPORT Func &gpu_blocks(VarOrRVar block_x, VarOrRVar block_y, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks       1457 src/Func.h         EXPORT Func &gpu_blocks(VarOrRVar block_x, VarOrRVar block_y, VarOrRVar block_z, DeviceAPI device_api = DeviceAPI::Default_GPU);
gpu_blocks       1623 src/Generator.h     HALIDE_OUTPUT_FORWARD(gpu_blocks)
gpu_blocks        155 src/Var.h          static Var gpu_blocks() {
gpu_blocks        102 test/correctness/gpu_reuse_shared_memory.cpp         .gpu_blocks(x, y)
gpu_blocks         86 test/correctness/gpu_specialize.cpp         g.tile(x, y, xi, yi, 2, 2).gpu_blocks(x, y);
gpu_blocks         23 test/correctness/gpu_sum_scan.cpp     f.compute_root().gpu_blocks(y).gpu_threads(x);
gpu_blocks         28 test/correctness/gpu_sum_scan.cpp     f.update(0).gpu_blocks(y);
gpu_blocks         38 test/correctness/gpu_sum_scan.cpp     f.update(2).gpu_blocks(y).gpu_threads(r3);
gpu_blocks         32 test/correctness/gpu_transpose.cpp         .gpu_blocks(subtile_idx, tile_idx)
gpu_blocks         22 test/correctness/gpu_vectorized_shared_memory.cpp         h.split(x, xo, xi, 16).vectorize(xi, 4).gpu_threads(xi).gpu_blocks(xo);
gpu_blocks         23 test/error/five_d_gpu_buffer.cpp     f.compute_root().gpu_blocks(v3, v4).gpu_threads(v1, v2);
gpu_blocks        127 tutorial/lesson_12_using_the_gpu.cpp         lut.gpu_blocks(block)