snapdragon profiler realtime模式参数

Clocks / Second : Number of GPU clocks per second.
GPU % Bus Busy : Approximate Percentage of time the GPU's bus to system memory is busy.
% Vertex Fetch Stall : Percentage of clock cycles where the GPU cannot make any more requests for vertex data.

 A high value for this metric implies the GPU cannot get vertex data from memory fast enough, and rendering peformance may be negatively affected.   
% Texture Fetch Stall : Percentage of clock cycles where the shader processors cannot make any more requests for texture data.

 A high value for this metric implies the shaders cannot get texture data from the texture pipe (L1, L2 cache or memory) fast enough, and rendering peformance may be negatively affected.   
Clocks : Number of GPU clocks
L1 Texture Cache Miss Per Pixel : Average number of Texture L1 cache misses per pixel.

  Lower values for this metric imply better memory coherency.  If this value is high, consider using compressed textures, reducing texture usage, etc.
Power : Power event tracing.
% Texture L1 Miss : Number of L1 texture cache misses divided by L1 texure cache requests.

This metric does not consider how many texture requests are made per time period (like the '% GPU L1 Texture cache miss' metric), but is simple miss to request ratio.
Disk I/O : Disk I/O tracing.
OpenCL Trace : Gathers all information related to OpenCL including programs, kernels, buffers, devices, etc.
Temperature : Die temperature in degrees Celsius.
% Vertex Fetch Stall : Percentage of clock cycles where the GPU cannot make any more requests for vertex data.

 A high value for this metric implies the GPU cannot get vertex data from memory fast enough, and rendering peformance may be negatively affected.   
% Texture L2 Miss : Number of L2 texture cache misses divided by L2 texure cache requests.

This metric does not consider how many texture requests are made per time period, but is simple miss to request ratio.
CPU Idle : CPU idle event tracing.
% Texture Fetch Stall : Percentage of clock cycles where the shader processors cannot make any more requests for texture data.

 A high value for this metric implies the shaders cannot get texture data from the texture pipe (L1, L2 cache or memory) fast enough, and rendering peformance may be negatively affected.   
% Stalled on System Memory : Percentage of cycles the L2 cache is stalled waiting for data from system memory 
CPU Scheduling : CPU scheduling event tracing.
L1 Texture Cache Miss Per Pixel : Average number of Texture L1 cache misses per pixel.

  Lower values for this metric imply better memory coherency.  If this value is high, consider using compressed textures, reducing texture usage, etc.
RenderScript : RenderScript event tracing.
% Texture L1 Miss : Number of L1 texture cache misses divided by L1 texure cache requests.

This metric does not consider how many texture requests are made per time period (like the '% GPU L1 Texture cache miss' metric), but is simple miss to request ratio.
Pre-clipped Polygons/Second : Number of polygons submitted to the GPU, per second, before any hardware clipping.
Dalvik VM : Dalvik VM event tracing.
% Texture L2 Miss : Number of L2 texture cache misses divided by L2 texure cache requests.

This metric does not consider how many texture requests are made per time period, but is simple miss to request ratio.
% Prims Trivially Rejected : Percentage of primitives that are trivially rejected.

A primitive can be trivially rejected if it outside the visible region of the render surface.  These primitives are ignored by the rasterizer.
CPU Frequency : CPU frequency tracing.
% Stalled on System Memory : Percentage of cycles the L2 cache is stalled waiting for data from system memory 
% Prims Clipped : Percentage of primitives clipped by the GPU (where new primitives are generated).

For a primitive to be clipped, it has to have a visible portion inside the viewport but extend outside the 'guardband' - an area that surrounds the viewport and significantly reduces the number of primitives the hardware has to clip.
Resource Loading : Resource load event tracing.
Average Vertices / Polygon : Average number of vertices per polygon.  This will be around 3 for triangles, and close to 1 for triangle strips.
Input : Input event tracing.
Pre-clipped Polygon : Number of polygons submitted to the GPU before any hardware clipping.
Reused Vertices / Second : Number of vertices used from the post-tranform vertex buffer cache.  A vertex may be used in multiple primitives; a high value for this metric (compared to number of vertices shaded) indicates good re-use of transformed vertices, reducing vertex shader workload.
Audio : Audio event tracing.
% Prims Trivially Rejected : Percentage of primitives that are trivially rejected.

A primitive can be trivially rejected if it outside the visible region of the render surface.  These primitives are ignored by the rasterizer.
Average Polygon Area : Average number of pixels per polygon. Adreno's binning architecture will count a primitive for each 'bin' it covers, so this metric may not exactly match expectations.
Video : Video event tracing.
% Prims Clipped : Percentage of primitives clipped by the GPU (where new primitives are generated).

For a primitive to be clipped, it has to have a visible portion inside the viewport but extend outside the 'guardband' - an area that surrounds the viewport and significantly reduces the number of primitives the hardware has to clip.
Hardware Modules : Hardware module event tracing.
Average Vertices / Polygon : Average number of vertices per polygon.  This will be around 3 for triangles, and close to 1 for triangle strips.
% Shaders Busy : Percentage of time that all Shader cores are busy.
Camera : Camera event tracing.
Reused Vertices / Second : Number of vertices used from the post-tranform vertex buffer cache.  A vertex may be used in multiple primitives; a high value for this metric (compared to number of vertices shaded) indicates good re-use of transformed vertices, reducing vertex shader workload.
Vertices Shaded / Second : Number of vertices submitted to the shader engine, per second.
Activity Manager : Activity manager event tracing.
Average Polygon Area : Average number of pixels per polygon. Adreno's binning architecture will count a primitive for each 'bin' it covers, so this metric may not exactly match expectations.
Fragments Shaded / Second : Number of fragments submitted to the shader engine, per second.
View : View event tracing.
Vertex Instructions / Second : Total number of scalar vertex shader instructions issued, per second.

Includes full precision ALU vertex instructions and EFU vertex instructions.  Does not include medium precision instructions (since they are not used for vertex shaders). Does not include vertex fetch or texture fetch instructions.
Graphics : Graphics buffer allocation tracing.
% Shaders Busy : Percentage of time that all Shader cores are busy.
Fragment Instructions / Second : Total number of fragment shader instructions issued, per second.

Reported as full precision scalar ALU instructions - 2 medium precision instructions equal 1 full precision instruction. Also includes interpolation instructions (which are executed on the ALU hardware) and EFU (Elementary Function Unit) instructions. Does not include texture fetch instructions.
Window Manager : Window manager event tracing.
Vertices Shaded : Number of vertices submitted to the shader engine.
Fragment ALU Instructions / Sec (Full) : Total number of full precision fragment shader instructions issued, per second.

. Does not include medium precision instructions or texture fetch instructions.
WebView : WebView event tracing.
Fragments Shaded : Number of fragments submitted to the shader engine.
Fragment ALU Instructions / Sec (Half) : Total number of half precision Scalar fragment shader instructions issued, per second.

. Does not include full precision instructions or texture fetch instructions.
Vertex Instructions : Total number of scalar vertex shader instructions issued.

Includes full precision ALU vertex instructions and EFU vertex instructions.  Does not include medium precision instructions (since they are not used for vertex shaders). Does not include vertex fetch or texture fetch instructions.
Fragment EFU Instructions / Second : Total number of Scalar fragment shader Elementary Function Unit (EFU) instructions issued, per second.

.  These include math functions like sin, cos, pow, etc.
Fragment Instructions : Total number of fragment shader instructions issued.

Reported as full precision scalar ALU instructions - 2 medium precision instructions equal 1 full precision instruction. Also includes interpolation instructions (which are executed on the ALU hardware) and EFU (Elementary Function Unit) instructions. Does not include texture fetch instructions.
Textures / Vertex : Average number of textures referenced per vertex.
Fragment ALU Instructions(Full) : Total number of full precision fragment shader instructions issued.

. Does not include medium precision instructions or texture fetch instructions.
Textures / Fragment : Average number of textures referenced per fragment.
Fragment ALU Instructions(Half) : Total number of half precision Scalar fragment shader instructions issued.

. Does not include full precision instructions or texture fetch instructions.
ALU / Vertex : Average number of vertex scalar shader ALU instructions issued per shaded vertex. Does not include fragment shader instructions.
Fragment EFU Instructions : Total number of Scalar fragment shader Elementary Function Unit (EFU) instructions issued.

.  These include math functions like sin, cos, pow, etc.
ALU / Fragment : Average number of scalar fragment shader ALU instructions issued per shaded fragment, expressed as full precision ALUs (2 mediump = 1 fullp).  Includes interpolation instruction.

Does not include vertex shader instructions.
Textures / Vertex : Average number of textures referenced per vertex.
EFU / Fragment : Average number of scalar fragment shader EFU instructions issued per shaded fragment.  Does not include Vertex EFU instructions
Textures / Fragment : Average number of textures referenced per fragment.
EFU / Vertex : Average number of scalar vertex shader EFU instructions issued per shaded vertex.  Does not include fragment EFU instructions
Rx Bytes (Total) : Total bytes received by this process.
ALU / Vertex : Average number of vertex scalar shader ALU instructions issued per shaded vertex. Does not include fragment shader instructions.
% Time Shading Fragments : Amount of time spent shading fragments compared to the total time spent shading everything.
Upload Mbps (WiFi) : Throughput (Mbps) sent through the WiFi interface.
ALU / Fragment : Average number of scalar fragment shader ALU instructions issued per shaded fragment, expressed as full precision ALUs (2 mediump = 1 fullp).  Includes interpolation instruction.

Does not include vertex shader instructions.
% Time Shading Vertices : Amount of time spent shading vertices compared to the total time spent shading everything.
Tx Bytes (TCP) : TCP bytes sent by this process.
EFU / Fragment : Average number of scalar fragment shader EFU instructions issued per shaded fragment.  Does not include Vertex EFU instructions
% Time Compute : Amount of time spent in compute work compared to the total time spent shading everything.
Rx Packets (WiFi) : Total packets received through the WiFi interface.
EFU / Vertex : Average number of scalar vertex shader EFU instructions issued per shaded vertex.  Does not include fragment EFU instructions
% Shader ALU Capacity Utilized : Percent of maximum shader capacity (ALU operations) utilized. For each cycle that the shaders are working, the average percentage of the total shader ALU capacity that is utilized for that cycle.
Tx Packets (WiFi) : Total packets sent through the WiFi interface.
% Time Shading Fragments : Amount of time spent shading fragments compared to the total time spent shading everything.
% Time ALUs Working : Percentage of time the ALUs are working while the Shaders are busy.
Tx Bytes (WiFi) : Total bytes sent through the WiFi interface.
% Time Shading Vertices : Amount of time spent shading vertices compared to the total time spent shading everything.
% Time EFUs Working : Percentage of time the EFUs are working while the Shaders are busy.
Rx Bytes (WiFi) : Total bytes received through the WiFi interface.
% Time Compute : Amount of time spent in compute work compared to the total time spent shading everything.
% Nearest Filtered : Percent of texels filtered using the 'Nearest' sampling method.
Download Mbps (WiFi) : Throughput (Mbps) received through the WiFi interface.
% Shader ALU Capacity Utilized : Percent of maximum shader capacity (ALU operations) utilized. For each cycle that the shaders are working, the average percentage of the total shader ALU capacity that is utilized for that cycle.
% Linear Filtered : Percent of texels filtered using the 'Linear' sampling method.
Rx Bytes (UDP) : UDP bytes received by this process.
% Time ALUs Working : Percentage of time the ALUs are working while the Shaders are busy.
CPU 6 % Utilization : 
% Anisotropic Filtered : Percent of texels filtered using the 'Anisotropic' sampling method.
Rx Bytes (TCP) : TCP bytes received by this process.
% Time EFUs Working : Percentage of time the EFUs are working while the Shaders are busy.
CPU 6 Frequency : 
% Non-Base Level Textures : Percent of texels coming from a non-base MIP level.
Tx Bytes (Total) : Total bytes sent by this process.
% Nearest Filtered : Percent of texels filtered using the 'Nearest' sampling method.
CPU 5 % Utilization : 
Tx Bytes (UDP) : UDP bytes sent by this process.
% Linear Filtered : Percent of texels filtered using the 'Linear' sampling method.
CPU 5 Frequency : 
Read Total (Bytes/sec) : Total number of bytes read by the GPU from memory, per second.
% Anisotropic Filtered : Percent of texels filtered using the 'Anisotropic' sampling method.
CPU 4 % Utilization : 
Write Total (Bytes/sec) : Total number of bytes written by  the GPU to memory, per second.
System Memory Usage : The total memory in use across the system in bytes.
% Non-Base Level Textures : Percent of texels coming from a non-base MIP level.
Texture Memory Read BW (Bytes/Second) : Bytes of texture data read from memory per second; includes bytes of platform compressed texture data read from memory.
CPU Cycles : CPU cycles per second.
Vertex Memory Read (Bytes/Second) : Bytes of vertex data read from memory per second.
CPU 6 Load : 
Read Total (Bytes) : Total number of bytes read by the GPU from memory.
SP Memory Read (Bytes/Second) : Bytes of data read from memory by the Shader Processors, per second.
CPU 4 Frequency : 
Write Total (Bytes) : Total number of bytes written by  the GPU to memory.
Avg Bytes / Fragment : Average number of bytes transferred from main memory for each fragment.
CPU 7 Frequency : 
Texture Memory Read BW (Bytes) : Bytes of texture data read from memory.
Avg Bytes / Vertex : Average number of bytes transferred from main memory for each vertex.
CPU 5 Load : 
Vertex Memory Read (Bytes) : Bytes of vertex data read from memory.
CPU 3 Load : 
SP Memory Read (Bytes) : Bytes of data read from memory by the Shader Processors.
Preemptions / second : The number of GPU preemptions that occurred, per second.
CPU 7 % Utilization : 
Avg Bytes / Fragment : Average number of bytes transferred from main memory for each fragment.
GPU Temperature : GPU temperature in degrees Celsius.
CPU 3 % Utilization : 
Avg Bytes / Vertex : Average number of bytes transferred from main memory for each vertex.
CPU 1 Load : 
Avg Preemption Delay : Average time (us) from the preemption request to preemption start.
CPU 0 Load : 
CPU Utilization % : % of CPU time the process is active.
Rendering stages : Information about the stages of rendering executed on a surface.
CPU 7 Load : 
Memory Usage : Memory (RAM) used by the process in bytes.
Clocks : Number of GPU clocks
CPU 1 % Utilization : 
CPU 4 Load : 
% Vertex Fetch Stall : Percentage of clock cycles where the GPU cannot make any more requests for vertex data.

 A high value for this metric implies the GPU cannot get vertex data from memory fast enough, and rendering peformance may be negatively affected.   
CPU 1 Frequency : 
% Texture Fetch Stall : Percentage of clock cycles where the shader processors cannot make any more requests for texture data.

 A high value for this metric implies the shaders cannot get texture data from the texture pipe (L1, L2 cache or memory) fast enough, and rendering peformance may be negatively affected.   
CPU 2 % Utilization : 
L1 Texture Cache Miss Per Pixel : Average number of Texture L1 cache misses per pixel.

  Lower values for this metric imply better memory coherency.  If this value is high, consider using compressed textures, reducing texture usage, etc.
CPU 0 % Utilization : 
% Texture L1 Miss : Number of L1 texture cache misses divided by L1 texure cache requests.

This metric does not consider how many texture requests are made per time period (like the '% GPU L1 Texture cache miss' metric), but is simple miss to request ratio.
CPU 2 Frequency : 
% Texture L2 Miss : Number of L2 texture cache misses divided by L2 texure cache requests.

This metric does not consider how many texture requests are made per time period, but is simple miss to request ratio.
CPU 0 Frequency : 
% Stalled on System Memory : Percentage of cycles the L2 cache is stalled waiting for data from system memory 
CPU 3 Frequency : 
CPU 2 Load : 
Pre-clipped Polygon : Number of polygons submitted to the GPU before any hardware clipping.
Native Tracing API : Enable display of Native Tracing API markers in trace output
% Prims Trivially Rejected : Percentage of primitives that are trivially rejected.

A primitive can be trivially rejected if it outside the visible region of the render surface.  These primitives are ignored by the rasterizer.
% Prims Clipped : Percentage of primitives clipped by the GPU (where new primitives are generated).

For a primitive to be clipped, it has to have a visible portion inside the viewport but extend outside the 'guardband' - an area that surrounds the viewport and significantly reduces the number of primitives the hardware has to clip.
Average Vertices / Polygon : Average number of vertices per polygon.  This will be around 3 for triangles, and close to 1 for triangle strips.
Reused Vertices / Second : Number of vertices used from the post-tranform vertex buffer cache.  A vertex may be used in multiple primitives; a high value for this metric (compared to number of vertices shaded) indicates good re-use of transformed vertices, reducing vertex shader workload.
Average Polygon Area : Average number of pixels per polygon. Adreno's binning architecture will count a primitive for each 'bin' it covers, so this metric may not exactly match expectations.
% Shaders Busy : Percentage of time that all Shader cores are busy.
Vertices Shaded : Number of vertices submitted to the shader engine.
Fragments Shaded : Number of fragments submitted to the shader engine.
Vertex Instructions : Total number of scalar vertex shader instructions issued.

Includes full precision ALU vertex instructions and EFU vertex instructions.  Does not include medium precision instructions (since they are not used for vertex shaders). Does not include vertex fetch or texture fetch instructions.
Fragment Instructions : Total number of fragment shader instructions issued.

Reported as full precision scalar ALU instructions - 2 medium precision instructions equal 1 full precision instruction. Also includes interpolation instructions (which are executed on the ALU hardware) and EFU (Elementary Function Unit) instructions. Does not include texture fetch instructions.
Fragment ALU Instructions(Full) : Total number of full precision fragment shader instructions issued.

. Does not include medium precision instructions or texture fetch instructions.
Fragment ALU Instructions(Half) : Total number of half precision Scalar fragment shader instructions issued.

. Does not include full precision instructions or texture fetch instructions.
Fragment EFU Instructions : Total number of Scalar fragment shader Elementary Function Unit (EFU) instructions issued.

.  These include math functions like sin, cos, pow, etc.
Textures / Vertex : Average number of textures referenced per vertex.
Textures / Fragment : Average number of textures referenced per fragment.
ALU / Vertex : Average number of vertex scalar shader ALU instructions issued per shaded vertex. Does not include fragment shader instructions.
ALU / Fragment : Average number of scalar fragment shader ALU instructions issued per shaded fragment, expressed as full precision ALUs (2 mediump = 1 fullp).  Includes interpolation instruction.

Does not include vertex shader instructions.
EFU / Fragment : Average number of scalar fragment shader EFU instructions issued per shaded fragment.  Does not include Vertex EFU instructions
EFU / Vertex : Average number of scalar vertex shader EFU instructions issued per shaded vertex.  Does not include fragment EFU instructions
% Time Shading Fragments : Amount of time spent shading fragments compared to the total time spent shading everything.
% Time Shading Vertices : Amount of time spent shading vertices compared to the total time spent shading everything.
% Time Compute : Amount of time spent in compute work compared to the total time spent shading everything.
% Shader ALU Capacity Utilized : Percent of maximum shader capacity (ALU operations) utilized. For each cycle that the shaders are working, the average percentage of the total shader ALU capacity that is utilized for that cycle.
% Time ALUs Working : Percentage of time the ALUs are working while the Shaders are busy.
% Time EFUs Working : Percentage of time the EFUs are working while the Shaders are busy.
% Nearest Filtered : Percent of texels filtered using the 'Nearest' sampling method.
% Linear Filtered : Percent of texels filtered using the 'Linear' sampling method.
% Anisotropic Filtered : Percent of texels filtered using the 'Anisotropic' sampling method.
% Non-Base Level Textures : Percent of texels coming from a non-base MIP level.
Read Total (Bytes) : Total number of bytes read by the GPU from memory.
Write Total (Bytes) : Total number of bytes written by  the GPU to memory.
Texture Memory Read BW (Bytes) : Bytes of texture data read from memory.
Vertex Memory Read (Bytes) : Bytes of vertex data read from memory.
SP Memory Read (Bytes) : Bytes of data read from memory by the Shader Processors.
Avg Bytes / Fragment : Average number of bytes transferred from main memory for each fragment.
Avg Bytes / Vertex : Average number of bytes transferred from main memory for each vertex.
OpenGL Snapshot : Display all OpenGL ES API calls