diff --git a/projects/rocdecode/samples/videoDecodeRGB/videodecrgb.cpp b/projects/rocdecode/samples/videoDecodeRGB/videodecrgb.cpp
index 11655c8760..c36b7b6d22 100644
--- a/projects/rocdecode/samples/videoDecodeRGB/videodecrgb.cpp
+++ b/projects/rocdecode/samples/videoDecodeRGB/videodecrgb.cpp
@@ -77,75 +77,75 @@ void DumpRGBImage(std::string outputfileName, void* pdevMem, OutputSurfaceInfo *
     }
 }
 
-void ColorConvertYUV2RGB(uint8_t *p_src, OutputSurfaceInfo *surf_info, uint8_t *rgb_dev_mem_ptr, OutputFormatEnum e_output_format) {
+void ColorConvertYUV2RGB(uint8_t *p_src, OutputSurfaceInfo *surf_info, uint8_t *rgb_dev_mem_ptr, OutputFormatEnum e_output_format, hipStream_t hip_stream) {
     
     int  rgb_width = (surf_info->output_width + 1) & ~1;    // has to be a multiple of 2 for hip colorconvert kernels
     // todo:: get color standard from the decoder
     if (surf_info->surface_format == rocDecVideoSurfaceFormat_YUV444) {
         if (e_output_format == bgr)
           YUV444ToColor24<BGR24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgra)
           YUV444ToColor32<BGRA32>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 4 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb)
           YUV444ToColor24<RGB24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgba)
           YUV444ToColor32<RGBA32>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 4 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
     } else if (surf_info->surface_format == rocDecVideoSurfaceFormat_NV12) {
         if (e_output_format == bgr)
           Nv12ToColor24<BGR24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgra)
           Nv12ToColor32<BGRA32>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 4 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb)
           Nv12ToColor24<RGB24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgba)
           Nv12ToColor32<RGBA32>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 4 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
     }
     if (surf_info->surface_format == rocDecVideoSurfaceFormat_YUV444_16Bit) {
         if (e_output_format == bgr)
           YUV444P16ToColor24<BGR24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb)
           YUV444P16ToColor24<RGB24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgr48)
           YUV444P16ToColor48<BGR48>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 6 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb48)
           YUV444P16ToColor48<RGB48>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 6 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgra64)
           YUV444P16ToColor64<BGRA64>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 8 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgba64)
           YUV444P16ToColor64<RGBA64>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 8 * rgb_width, surf_info->output_width, 
-                                surf_info->output_height, surf_info->output_vstride, 0);
+                                surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
     } else if (surf_info->surface_format == rocDecVideoSurfaceFormat_P016) {
         if (e_output_format == bgr)
           P016ToColor24<BGR24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb)
           P016ToColor24<RGB24>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 3 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgr48)
           P016ToColor48<BGR48>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 6 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgb48)
           P016ToColor48<RGB48>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 6 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == bgra64)
           P016ToColor64<BGRA64>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 8 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
         else if (e_output_format == rgba64)
           P016ToColor64<RGBA64>(p_src, surf_info->output_pitch, static_cast<uint8_t *>(rgb_dev_mem_ptr), 8 * rgb_width, surf_info->output_width, 
-                              surf_info->output_height, surf_info->output_vstride, 0);
+                              surf_info->output_height, surf_info->output_vstride, 0, hip_stream);
     }
 }
 
@@ -281,7 +281,7 @@ int main(int argc, char **argv) {
                             return -1;
                         }
                     }
-                    ColorConvertYUV2RGB(p_frame, surf_info, p_rgb_dev_mem, e_output_format);
+                    ColorConvertYUV2RGB(p_frame, surf_info, p_rgb_dev_mem, e_output_format, viddec.GetStream());
                 }
                 if (dump_output_frames) {
                     if (convert_to_rgb)
diff --git a/projects/rocdecode/utils/colorspace_kernels.cpp b/projects/rocdecode/utils/colorspace_kernels.cpp
index 49e35740fa..fbd1ad63bf 100644
--- a/projects/rocdecode/utils/colorspace_kernels.cpp
+++ b/projects/rocdecode/utils/colorspace_kernels.cpp
@@ -283,209 +283,209 @@ __global__ static void Yuv444ToRgbPlanarKernel(uint8_t *dp_yuv, int yuv_pitch, u
 }
 
 template <class COLOR32>
-void Nv12ToColor32(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void Nv12ToColor32(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbaKernel<uchar2, COLOR32, uint2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_nv12, nv12_pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR64>
-void Nv12ToColor64(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void Nv12ToColor64(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbaKernel<uchar2, COLOR64, ulonglong2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_nv12, nv12_pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void YUV444ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbaKernel<uchar2, COLOR32, uint2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR64>
-void YUV444ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbaKernel<uchar2, COLOR64, ulonglong2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void P016ToColor32(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void P016ToColor32(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbaKernel<ushort2, COLOR32, uint2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_p016, p016_pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR64>
-void P016ToColor64(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void P016ToColor64(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbaKernel<ushort2, COLOR64, ulonglong2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_p016, p016_pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void YUV444P16ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444P16ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbaKernel<ushort2, COLOR32, uint2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR64>
-void YUV444P16ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444P16ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbaKernel<ushort2, COLOR64, ulonglong2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void Nv12ToColorPlanar(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard) {
+void Nv12ToColorPlanar(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbPlanarKernel<uchar2, COLOR32, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_nv12, nv12_pitch, dp_bgrp, nBgrpPitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void P016ToColorPlanar(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard) {
+void P016ToColorPlanar(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbPlanarKernel<ushort2, COLOR32, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_p016, p016_pitch, dp_bgrp, nBgrpPitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void YUV444ToColorPlanar(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444ToColorPlanar(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbPlanarKernel<uchar2, COLOR32, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgrp, nBgrpPitch, width, height, v_pitch);
 }
 
 template <class COLOR32>
-void YUV444P16ToColorPlanar(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444P16ToColorPlanar(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbPlanarKernel<ushort2, COLOR32, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgrp, nBgrpPitch, width, height, v_pitch);
 }
 
 // Explicit Instantiation: for RGB32/BGR32 and RGB64/BGR64 formats
-template void Nv12ToColor32<BGRA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor32<RGBA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor64<BGRA64>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor64<RGBA64>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor32<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor32<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor64<BGRA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor64<RGBA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor32<BGRA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor32<RGBA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor64<BGRA64>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor64<RGBA64>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor32<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor32<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor64<BGRA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor64<RGBA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColorPlanar<BGRA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColorPlanar<RGBA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColorPlanar<BGRA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColorPlanar<RGBA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColorPlanar<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColorPlanar<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColorPlanar<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColorPlanar<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard);
+template void Nv12ToColor32<BGRA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor32<RGBA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor64<BGRA64>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor64<RGBA64>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor32<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor32<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor64<BGRA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor64<RGBA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor32<BGRA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor32<RGBA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor64<BGRA64>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor64<RGBA64>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor32<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor32<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor64<BGRA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor64<RGBA64>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColorPlanar<BGRA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColorPlanar<RGBA32>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColorPlanar<BGRA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColorPlanar<RGBA32>(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColorPlanar<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColorPlanar<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColorPlanar<BGRA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColorPlanar<RGBA32>(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgrp, int nBgrpPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 
 template <class COLOR24>
-void Nv12ToColor24(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void Nv12ToColor24(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbKernel<uchar2, COLOR24, uchar4, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_nv12, nv12_pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR48>
-void Nv12ToColor48(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void Nv12ToColor48(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbKernel<uchar2, COLOR48, ushort4, ushort2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_nv12, nv12_pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR24>
-void YUV444ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbKernel<uchar2, COLOR24, uchar4, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR48>
-void YUV444ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbKernel<uchar2, COLOR48, ushort4, ushort2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR24>
-void P016ToColor24(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void P016ToColor24(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbKernel<ushort2, COLOR24, uchar4, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_p016, p016_pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR48>
-void P016ToColor48(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void P016ToColor48(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     YuvToRgbKernel<ushort2, COLOR48, ushort4, ushort2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_p016, p016_pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 template <class COLOR24>
-void YUV444P16ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444P16ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbKernel<ushort2, COLOR24, uchar4, uchar2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgra, bgra_pitch, width, height, v_pitch);
 }
 
 template <class COLOR48>
-void YUV444P16ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard) {
+void YUV444P16ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream) {
     SetMatYuv2Rgb(col_standard);
     Yuv444ToRgbKernel<ushort2, COLOR48, ushort4, ushort2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2) >>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_yuv_444, pitch, dp_bgr, bgr_pitch, width, height, v_pitch);
 }
 
 
 // Explicit Instantiation: for RGB24/BGR24 and RGB48/BGR48 formats
-template void Nv12ToColor24<BGR24>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor24<RGB24>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor48<BGR48>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void Nv12ToColor48<RGB48>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor24<BGR24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor24<RGB24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor48<BGR48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444ToColor48<RGB48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor24<BGR24>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor24<RGB24>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor48<BGR48>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void P016ToColor48<RGB48>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor24<BGR24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor24<RGB24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor48<BGR48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
-template void YUV444P16ToColor48<RGB48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard);
+template void Nv12ToColor24<BGR24>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor24<RGB24>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor48<BGR48>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void Nv12ToColor48<RGB48>(uint8_t *dp_nv12, int nv12_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor24<BGR24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor24<RGB24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor48<BGR48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444ToColor48<RGB48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor24<BGR24>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor24<RGB24>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor48<BGR48>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void P016ToColor48<RGB48>(uint8_t *dp_p016, int p016_pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor24<BGR24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor24<RGB24>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor48<BGR48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
+template void YUV444P16ToColor48<RGB48>(uint8_t *dp_yuv_444, int pitch, uint8_t *p_bgr, int p_bgrPitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 
 
 template<class YuvUnit, class RgbUnit>
@@ -539,10 +539,10 @@ __global__ static void RgbaToYuvKernel(uint8_t *dp_rgb, int rgba_pitch, uint8_t
     };
 }
 
-void Bgra64ToP016(uint8_t *dp_bgra, int bgra_pitch, uint8_t *dp_p016, int p016_pitch, int width, int height, int col_standard) {
+void Bgra64ToP016(uint8_t *dp_bgra, int bgra_pitch, uint8_t *dp_p016, int p016_pitch, int width, int height, int col_standard, hipStream_t hip_stream) {
     SetMatRgb2Yuv(col_standard);
     RgbaToYuvKernel<ushort2, BGRA64, ulonglong2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (dp_bgra, bgra_pitch, dp_p016, p016_pitch, width, height);
 }
 
@@ -585,9 +585,9 @@ __global__ static void RgbToYuvKernel(uint8_t *dp_rgb, int rgb_pitch, uint8_t *d
     };
 }
 
-void Bgr48ToP016(uint8_t *p_bgr, int bgr_pitch, uint8_t *dp_p016, int p016_pitch, int width, int height, int col_standard) {
+void Bgr48ToP016(uint8_t *p_bgr, int bgr_pitch, uint8_t *dp_p016, int p016_pitch, int width, int height, int col_standard, hipStream_t hip_stream) {
     SetMatRgb2Yuv(col_standard);
     RgbToYuvKernel<ushort2, BGR48, ushort4, ushort2>
-        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2)>>>
+        <<<dim3((width + 63) / 32 / 2, (height + 3) / 2 / 2), dim3(32, 2), 0, hip_stream>>>
         (p_bgr, bgr_pitch, dp_p016, p016_pitch, width, height);
 }
diff --git a/projects/rocdecode/utils/colorspace_kernels.h b/projects/rocdecode/utils/colorspace_kernels.h
index c600de8582..49ad9cdfb5 100644
--- a/projects/rocdecode/utils/colorspace_kernels.h
+++ b/projects/rocdecode/utils/colorspace_kernels.h
@@ -108,36 +108,36 @@ union RGBA64 {
 
 // color-convert hip kernel function definitions
 template <class COLOR32>
-void YUV444ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR64>
-void YUV444ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR24>
-void YUV444ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR48>
-void YUV444ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 
 template <class COLOR24>
-void Nv12ToColor24(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void Nv12ToColor24(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR32>
-void Nv12ToColor32(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void Nv12ToColor32(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR48>
-void Nv12ToColor48(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void Nv12ToColor48(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR64>
-void Nv12ToColor64(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void Nv12ToColor64(uint8_t *dp_nv12, int nv12_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR24>
-void YUV444P16ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444P16ToColor24(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR48>
-void YUV444P16ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444P16ToColor48(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR32>
-void YUV444P16ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444P16ToColor32(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR64>
-void YUV444P16ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void YUV444P16ToColor64(uint8_t *dp_yuv_444, int pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR32>
-void P016ToColor32(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void P016ToColor32(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR64>
-void P016ToColor64(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard);
+void P016ToColor64(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgra, int bgra_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR24>
-void P016ToColor24(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void P016ToColor24(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);
 template <class COLOR48>
-void P016ToColor48(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard);
+void P016ToColor48(uint8_t *dp_p016, int p016_pitch, uint8_t *dp_bgr, int bgr_pitch, int width, int height, int v_pitch, int col_standard, hipStream_t hip_stream);