Data Structures | Macros | Typedefs | Functions | Variables
cuda_runtime.h File Reference

Go to the source code of this file.

Data Structures

struct  dim3


#define __global__   __attribute__((global))
#define __device__   __attribute__((device))
#define __device_builtin__   __attribute__((device_builtin))
#define __align__(N)   __attribute__((aligned(N)))
#define __inline__   __inline__ __attribute__((always_inline))
#define max(a, b)   ((a) > (b) ? (a) : (b))
#define min(a, b)   ((a) < (b) ? (a) : (b))
#define abs(x)   ((x) < 0 ? -(x) : (x))
#define atomicAdd(a, b)   (__atomic_fetch_add(a, b, __ATOMIC_SEQ_CST))
#define GETCOMP(reg, comp)
#define GET(name, reg)
#define blockIdx   (getBlockIdx())
#define blockDim   (getBlockDim())
#define threadIdx   (getThreadIdx())
#define make_uchar2(a, b)   ((uchar2){.x = a, .y = b})
#define make_ushort2(a, b)   ((ushort2){.x = a, .y = b})
#define make_uchar4(a, b, c, d)   ((uchar4){.x = a, .y = b, .z = c, .w = d})
#define make_ushort4(a, b, c, d)   ((ushort4){.x = a, .y = b, .z = c, .w = d})
#define TEX2D(type, ret)   static inline __device__ void conv(type* out, unsigned a, unsigned b, unsigned c, unsigned d) {*out = (ret);}


typedef __device_builtin__ unsigned long long cudaTextureObject_t


struct __device_builtin__ __align__ (2) uchar2
struct __device_builtin__ __align__ (4) ushort2
struct __device_builtin__ __align__ (8) int2
struct __device_builtin__ __align__ (16) int4
template<class T >
static __device__ T tex2D (cudaTextureObject_t texObject, float x, float y)



Macro Definition Documentation

#define __global__   __attribute__((global))

Definition at line 27 of file cuda_runtime.h.

#define __device__   __attribute__((device))

Definition at line 28 of file cuda_runtime.h.

#define __device_builtin__   __attribute__((device_builtin))

Definition at line 29 of file cuda_runtime.h.

#define __align__ (   N)    __attribute__((aligned(N)))

Definition at line 30 of file cuda_runtime.h.

#define __inline__   __inline__ __attribute__((always_inline))

Definition at line 31 of file cuda_runtime.h.

#define max (   a,
)    ((a) > (b) ? (a) : (b))

Definition at line 33 of file cuda_runtime.h.

Referenced by aac_encode_frame(), acb_search(), adx_encode(), av_inv_q(), av_max_alloc(), av_size_mult(), build_luma_lut(), calc_input_response(), cas_slice16(), categorize(), categorize_regions(), cbs_vp9_assemble_fragment(), check_diff(), check_threshold(), checkasm_check_audiodsp(), clean_index(), clip_with_log(), color_graticule16(), comp_adjust(), comp_harmonic_coeff(), config_input(), config_props(), count_bits(), dct_quantize_trellis_c(), decode_entropy_image(), decode_frame_header(), decode_rice(), decompress_p(), decompress_p3(), deflicker16(), dering_altivec(), dering_TMPL(), direct_search(), dnxhd_10bit_dct_quantize_444(), do_a_deblock_C(), do_plc(), draw_response(), dts_probe(), dv_set_class_number_hd(), dv_set_class_number_sd(), encode_cblk(), envelope_instant16(), envelope_peak16(), eval_expr(), ff_ac3_bit_alloc_calc_psd(), ff_convert_matrix(), ff_dcaadpcm_subband_analysis(), ff_dct_quantize_c(), ff_g723_1_scale_vector(), ff_h264_parse_ref_count(), ff_hevc_ref_idx_lx_decode(), ff_interleave_add_packet(), ff_intra_pred_8_16x16_msa(), ff_intra_pred_8_32x32_msa(), ff_nelly_get_sample_bits(), ff_sws_alphablendaway(), filter_frame(), find_first_break(), find_peak_magnitude(), generate_new_codebooks(), get_duration(), get_fcb_param(), get_metadata_duration(), get_new_centroids(), get_output(), get_palette_frame(), green_graticule16(), hdcd_scan(), huff_build(), init(), intlist_read(), intra_pred(), inv_log_scale(), invert_graticule16(), irdft_horizontal16(), last_significant_coeff_xy_prefix_decode(), log_scale(), lpc2lsp(), lsp_quantize(), magicyuv_median_pred16(), magy_decode_slice10(), makelayers(), match_framerate(), max_component_diff(), merge_superframe(), motion_search(), mov_prune_frag_info(), mpeg4_decode_studio_block(), normalize(), opengl_get_texture_size(), opt_max_alloc(), optimize_colors(), oscilloscope_filter_frame(), parse_cube(), pixscope_filter_frame(), postProcess_TMPL(), process_frame(), qdm2_decode_fft_packets(), read_code(), reverse_color16(), rpza_encode_stream(), run_psnr(), s337m_probe(), set_format(), set_string_fmt(), slice_header(), stats(), sws_printVec2(), take_samples(), true_peak_limiter(), vectorscope16(), vibrance_slice16(), vp6_coeff_order_table_init(), write_packet(), x8_loop_filter(), and xcorr_coeff().

#define min (   a,
)    ((a) < (b) ? (a) : (b))

Definition at line 34 of file cuda_runtime.h.

#define abs (   x)    ((x) < 0 ? -(x) : (x))

Definition at line 35 of file cuda_runtime.h.

Referenced by ac3_extract_exponents_c(), ac3_max_msb_abs_int16_c(), adpcm_argo_compress_block(), adpcm_ima_compress_sample(), adpcm_ima_cunning_expand_nibble(), adpcm_ima_qt_compress_sample(), adpcm_yamaha_compress_sample(), calc_combed_score(), cfhd_decode(), checkmm(), compare_fields(), compute_scale_factors(), dct_error(), decode_cce(), dequant_and_decompand(), draw_mandelbrot(), ff_add_png_paeth_prediction(), ff_gradfun_filter_line_c(), ff_mpeg4_pred_dc(), ff_msmpeg4_pred_dc(), ff_nelly_get_sample_bits(), ff_vc1_pred_dc(), ff_vp9_fill_mv(), filter16_vrep(), filter8_vrep(), filter_frame(), filter_frame16(), filter_frame8(), filter_tout_outlier(), find_peak(), fits_read_header(), g726_decode(), get_badness(), get_bs(), get_rrp(), get_wb_bitrate_mode(), hadamard_intra_8x8_msa(), hdcd_analyze_prepare(), hdcd_envelope(), hevc_loop_filter_luma(), hevc_loopfilter_luma_hor_msa(), hevc_loopfilter_luma_ver_msa(), idct248_error(), if(), image_sad(), imdct_half_32(), imdct_half_64(), init_h263_dc_for_msmpeg4(), init_uni_dc_tab(), interpolation(), intlist_read(), is_image(), log2mono(), log2stereo(), loop_filter_c1(), loop_filter_c2(), loop_filter_l1(), loop_filter_l2(), luma_abs_diff(), main(), mpeg1_encode_block(), mv_pred_median(), mv_scale(), on2avc_scale(), parse_timestamp(), parse_value(), peak_table(), pix_abs16_c(), pix_abs16_x2_c(), pix_abs16_xy2_c(), pix_abs16_y2_c(), pix_abs8_c(), pix_abs8_x2_c(), pix_abs8_xy2_c(), pix_abs8_y2_c(), pix_median_abs16_c(), pix_median_abs8_c(), png_choose_filter(), push_single_pic(), ratecontrol_1pass(), read_diff_float_data(), run_psnr(), select_sample_rate(), spatial_compensation_0(), sub_png_paeth_prediction(), swap_sample_fmts_on_filter(), swap_samplerates_on_filter(), synth_frame(), and vc1_i_pred_dc().

#define atomicAdd (   a,
)    (__atomic_fetch_add(a, b, __ATOMIC_SEQ_CST))

Definition at line 37 of file cuda_runtime.h.

#define GETCOMP (   reg,
asm("mov.u32 %0, %%" #reg "." #comp ";" : "=r"(tmp)); \
ret.comp = tmp;
static void comp(unsigned char *dst, ptrdiff_t dst_stride, unsigned char *src, ptrdiff_t src_stride, int add)
Definition: eamad.c:83
static uint8_t tmp[11]
Definition: aes_ctr.c:26

Definition at line 80 of file cuda_runtime.h.

#define GET (   name,
static inline __device__ uint3 name() {\
uint3 ret; \
unsigned tmp; \
GETCOMP(reg, x) \
GETCOMP(reg, y) \
GETCOMP(reg, z) \
#define __device__
Definition: cuda_runtime.h:28
#define GETCOMP(reg, comp)
Definition: cuda_runtime.h:80
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a it should return
const char * name
Definition: opengl_enc.c:102
static uint8_t tmp[11]
Definition: aes_ctr.c:26

Definition at line 84 of file cuda_runtime.h.

#define blockIdx   (getBlockIdx())

Definition at line 98 of file cuda_runtime.h.

#define blockDim   (getBlockDim())

Definition at line 99 of file cuda_runtime.h.

#define threadIdx   (getThreadIdx())

Definition at line 100 of file cuda_runtime.h.

#define make_uchar2 (   a,
)    ((uchar2){.x = a, .y = b})

Definition at line 103 of file cuda_runtime.h.

#define make_ushort2 (   a,
)    ((ushort2){.x = a, .y = b})

Definition at line 104 of file cuda_runtime.h.

#define make_uchar4 (   a,
)    ((uchar4){.x = a, .y = b, .z = c, .w = d})

Definition at line 105 of file cuda_runtime.h.

#define make_ushort4 (   a,
)    ((ushort4){.x = a, .y = b, .z = c, .w = d})

Definition at line 106 of file cuda_runtime.h.

#define TEX2D (   type,
)    static inline __device__ void conv(type* out, unsigned a, unsigned b, unsigned c, unsigned d) {*out = (ret);}

Definition at line 109 of file cuda_runtime.h.

Typedef Documentation

typedef __device_builtin__ unsigned long long cudaTextureObject_t

Definition at line 40 of file cuda_runtime.h.

Function Documentation

struct __device_builtin__ __align__ ( )

Definition at line 42 of file cuda_runtime.h.

struct __device_builtin__ __align__ ( )

Definition at line 47 of file cuda_runtime.h.

struct __device_builtin__ __align__ ( )

Definition at line 59 of file cuda_runtime.h.

struct __device_builtin__ __align__ ( 16  )

Definition at line 74 of file cuda_runtime.h.

template<class T >
static __device__ T tex2D ( cudaTextureObject_t  texObject,
float  x,
float  y 

Definition at line 120 of file cuda_runtime.h.

Variable Documentation


Definition at line 45 of file cuda_runtime.h.


Definition at line 50 of file cuda_runtime.h.


Definition at line 62 of file cuda_runtime.h.


Definition at line 67 of file cuda_runtime.h.


Definition at line 72 of file cuda_runtime.h.


Definition at line 77 of file cuda_runtime.h.