static const enum AVPixelFormat supported_formats[] = {
AV_PIX_FMT_NV12,
AV_PIX_FMT_YUV420P,
+ AV_PIX_FMT_YUVA420P,
AV_PIX_FMT_YUV444P,
AV_PIX_FMT_P010,
AV_PIX_FMT_P016,
return 0;
}
-static int cuda_transfer_data_from(AVHWFramesContext *ctx, AVFrame *dst,
- const AVFrame *src)
+static int cuda_transfer_data(AVHWFramesContext *ctx, AVFrame *dst,
+ const AVFrame *src)
{
CUDAFramesContext *priv = ctx->internal->priv;
AVHWDeviceContext *device_ctx = ctx->device_ctx;
CUcontext dummy;
int i, ret;
- /* We don't support transfers to HW devices. */
- if (dst->hw_frames_ctx)
+ if ((src->hw_frames_ctx && ((AVHWFramesContext*)src->hw_frames_ctx->data)->format != AV_PIX_FMT_CUDA) ||
+ (dst->hw_frames_ctx && ((AVHWFramesContext*)dst->hw_frames_ctx->data)->format != AV_PIX_FMT_CUDA))
return AVERROR(ENOSYS);
ret = CHECK_CU(cu->cuCtxPushCurrent(hwctx->cuda_ctx));
for (i = 0; i < FF_ARRAY_ELEMS(src->data) && src->data[i]; i++) {
CUDA_MEMCPY2D cpy = {
- .srcMemoryType = CU_MEMORYTYPE_DEVICE,
- .dstMemoryType = CU_MEMORYTYPE_HOST,
- .srcDevice = (CUdeviceptr)src->data[i],
- .dstHost = dst->data[i],
.srcPitch = src->linesize[i],
.dstPitch = dst->linesize[i],
.WidthInBytes = FFMIN(src->linesize[i], dst->linesize[i]),
- .Height = src->height >> (i ? priv->shift_height : 0),
+ .Height = src->height >> ((i == 0 || i == 3) ? 0 : priv->shift_height),
};
+ if (src->hw_frames_ctx) {
+ cpy.srcMemoryType = CU_MEMORYTYPE_DEVICE;
+ cpy.srcDevice = (CUdeviceptr)src->data[i];
+ } else {
+ cpy.srcMemoryType = CU_MEMORYTYPE_HOST;
+ cpy.srcHost = src->data[i];
+ }
+
+ if (dst->hw_frames_ctx) {
+ cpy.dstMemoryType = CU_MEMORYTYPE_DEVICE;
+ cpy.dstDevice = (CUdeviceptr)dst->data[i];
+ } else {
+ cpy.dstMemoryType = CU_MEMORYTYPE_HOST;
+ cpy.dstHost = dst->data[i];
+ }
+
ret = CHECK_CU(cu->cuMemcpy2DAsync(&cpy, hwctx->stream));
if (ret < 0)
goto exit;
}
- ret = CHECK_CU(cu->cuStreamSynchronize(hwctx->stream));
- if (ret < 0)
- goto exit;
-
-exit:
- CHECK_CU(cu->cuCtxPopCurrent(&dummy));
-
- return 0;
-}
-
-static int cuda_transfer_data_to(AVHWFramesContext *ctx, AVFrame *dst,
- const AVFrame *src)
-{
- CUDAFramesContext *priv = ctx->internal->priv;
- AVHWDeviceContext *device_ctx = ctx->device_ctx;
- AVCUDADeviceContext *hwctx = device_ctx->hwctx;
- CudaFunctions *cu = hwctx->internal->cuda_dl;
-
- CUcontext dummy;
- int i, ret;
-
- /* We don't support transfers from HW devices. */
- if (src->hw_frames_ctx)
- return AVERROR(ENOSYS);
-
- ret = CHECK_CU(cu->cuCtxPushCurrent(hwctx->cuda_ctx));
- if (ret < 0)
- return ret;
-
- for (i = 0; i < FF_ARRAY_ELEMS(src->data) && src->data[i]; i++) {
- CUDA_MEMCPY2D cpy = {
- .srcMemoryType = CU_MEMORYTYPE_HOST,
- .dstMemoryType = CU_MEMORYTYPE_DEVICE,
- .srcHost = src->data[i],
- .dstDevice = (CUdeviceptr)dst->data[i],
- .srcPitch = src->linesize[i],
- .dstPitch = dst->linesize[i],
- .WidthInBytes = FFMIN(src->linesize[i], dst->linesize[i]),
- .Height = src->height >> (i ? priv->shift_height : 0),
- };
-
- ret = CHECK_CU(cu->cuMemcpy2DAsync(&cpy, hwctx->stream));
+ if (!dst->hw_frames_ctx) {
+ ret = CHECK_CU(cu->cuStreamSynchronize(hwctx->stream));
if (ret < 0)
goto exit;
}
return ret;
}
-static int cuda_device_create(AVHWDeviceContext *device_ctx,
- const char *device,
- AVDictionary *opts, int flags)
-{
+static int cuda_context_init(AVHWDeviceContext *device_ctx, int flags) {
AVCUDADeviceContext *hwctx = device_ctx->hwctx;
CudaFunctions *cu;
CUcontext dummy;
- int ret, dev_active = 0, device_idx = 0;
+ int ret, dev_active = 0;
unsigned int dev_flags = 0;
const unsigned int desired_flags = CU_CTX_SCHED_BLOCKING_SYNC;
- if (device)
- device_idx = strtol(device, NULL, 0);
-
- if (cuda_device_init(device_ctx) < 0)
- goto error;
-
cu = hwctx->internal->cuda_dl;
- ret = CHECK_CU(cu->cuInit(0));
- if (ret < 0)
- goto error;
-
- ret = CHECK_CU(cu->cuDeviceGet(&hwctx->internal->cuda_device, device_idx));
- if (ret < 0)
- goto error;
-
hwctx->internal->flags = flags;
if (flags & AV_CUDA_USE_PRIMARY_CONTEXT) {
- ret = CHECK_CU(cu->cuDevicePrimaryCtxGetState(hwctx->internal->cuda_device, &dev_flags, &dev_active));
+ ret = CHECK_CU(cu->cuDevicePrimaryCtxGetState(hwctx->internal->cuda_device,
+ &dev_flags, &dev_active));
if (ret < 0)
- goto error;
+ return ret;
if (dev_active && dev_flags != desired_flags) {
av_log(device_ctx, AV_LOG_ERROR, "Primary context already active with incompatible flags.\n");
- goto error;
+ return AVERROR(ENOTSUP);
} else if (dev_flags != desired_flags) {
- ret = CHECK_CU(cu->cuDevicePrimaryCtxSetFlags(hwctx->internal->cuda_device, desired_flags));
+ ret = CHECK_CU(cu->cuDevicePrimaryCtxSetFlags(hwctx->internal->cuda_device,
+ desired_flags));
if (ret < 0)
- goto error;
+ return ret;
}
- ret = CHECK_CU(cu->cuDevicePrimaryCtxRetain(&hwctx->cuda_ctx, hwctx->internal->cuda_device));
+ ret = CHECK_CU(cu->cuDevicePrimaryCtxRetain(&hwctx->cuda_ctx,
+ hwctx->internal->cuda_device));
if (ret < 0)
- goto error;
+ return ret;
} else {
- ret = CHECK_CU(cu->cuCtxCreate(&hwctx->cuda_ctx, desired_flags, hwctx->internal->cuda_device));
+ ret = CHECK_CU(cu->cuCtxCreate(&hwctx->cuda_ctx, desired_flags,
+ hwctx->internal->cuda_device));
if (ret < 0)
- goto error;
+ return ret;
CHECK_CU(cu->cuCtxPopCurrent(&dummy));
}
hwctx->stream = NULL;
return 0;
+}
+
+static int cuda_device_create(AVHWDeviceContext *device_ctx,
+ const char *device,
+ AVDictionary *opts, int flags)
+{
+ AVCUDADeviceContext *hwctx = device_ctx->hwctx;
+ CudaFunctions *cu;
+ int ret, device_idx = 0;
+
+ if (device)
+ device_idx = strtol(device, NULL, 0);
+
+ if (cuda_device_init(device_ctx) < 0)
+ goto error;
+
+ cu = hwctx->internal->cuda_dl;
+
+ ret = CHECK_CU(cu->cuInit(0));
+ if (ret < 0)
+ goto error;
+
+ ret = CHECK_CU(cu->cuDeviceGet(&hwctx->internal->cuda_device, device_idx));
+ if (ret < 0)
+ goto error;
+
+ ret = cuda_context_init(device_ctx, flags);
+ if (ret < 0)
+ goto error;
+
+ return 0;
error:
cuda_device_uninit(device_ctx);
}
static int cuda_device_derive(AVHWDeviceContext *device_ctx,
- AVHWDeviceContext *src_ctx,
+ AVHWDeviceContext *src_ctx, AVDictionary *opts,
int flags) {
AVCUDADeviceContext *hwctx = device_ctx->hwctx;
CudaFunctions *cu;
const char *src_uuid = NULL;
- CUcontext dummy;
- int ret, i, device_count, dev_active = 0;
- unsigned int dev_flags = 0;
-
- const unsigned int desired_flags = CU_CTX_SCHED_BLOCKING_SYNC;
+ int ret, i, device_count;
#if CONFIG_VULKAN
VkPhysicalDeviceIDProperties vk_idp = {
goto error;
}
- hwctx->internal->flags = flags;
-
- if (flags & AV_CUDA_USE_PRIMARY_CONTEXT) {
- ret = CHECK_CU(cu->cuDevicePrimaryCtxGetState(hwctx->internal->cuda_device, &dev_flags, &dev_active));
- if (ret < 0)
- goto error;
-
- if (dev_active && dev_flags != desired_flags) {
- av_log(device_ctx, AV_LOG_ERROR, "Primary context already active with incompatible flags.\n");
- goto error;
- } else if (dev_flags != desired_flags) {
- ret = CHECK_CU(cu->cuDevicePrimaryCtxSetFlags(hwctx->internal->cuda_device, desired_flags));
- if (ret < 0)
- goto error;
- }
-
- ret = CHECK_CU(cu->cuDevicePrimaryCtxRetain(&hwctx->cuda_ctx, hwctx->internal->cuda_device));
- if (ret < 0)
- goto error;
- } else {
- ret = CHECK_CU(cu->cuCtxCreate(&hwctx->cuda_ctx, desired_flags, hwctx->internal->cuda_device));
- if (ret < 0)
- goto error;
-
- CHECK_CU(cu->cuCtxPopCurrent(&dummy));
- }
-
- hwctx->internal->is_allocated = 1;
-
- // Setting stream to NULL will make functions automatically use the default CUstream
- hwctx->stream = NULL;
+ ret = cuda_context_init(device_ctx, flags);
+ if (ret < 0)
+ goto error;
return 0;
.frames_init = cuda_frames_init,
.frames_get_buffer = cuda_get_buffer,
.transfer_get_formats = cuda_transfer_get_formats,
- .transfer_data_to = cuda_transfer_data_to,
- .transfer_data_from = cuda_transfer_data_from,
+ .transfer_data_to = cuda_transfer_data,
+ .transfer_data_from = cuda_transfer_data,
.pix_fmts = (const enum AVPixelFormat[]){ AV_PIX_FMT_CUDA, AV_PIX_FMT_NONE },
};