Question

我有Metal计算内核，该内核采用两个纹理作为参数。但是，我遇到了内核无法运行的问题。我将问题简化为这个简单的内核。

#include <metal_stdlib>
using namespace metal;

kernel void test_texture(       texture2d<float, access::sample>  tex1 [[texture(0)]],
                                texture2d<float, access::sample>  tex2 [[texture(1)]],
                         device float                            *buf  [[buffer(0)]],
                                uint                              idx  [[thread_position_in_grid]]) {
    buf[idx] = 100;
}

以及以下主机代码。

#import <Metal/Metal.h>

int main(int argc, const char * argv[]) {
    @autoreleasepool {
        const size_t max_buffer = 128000000;
        const size_t max_texture = 16384;

        id<MTLDevice> device = MTLCreateSystemDefaultDevice();
        id<MTLLibrary> library = [device newDefaultLibrary];
        id<MTLCommandQueue> queue = [device newCommandQueue];

        id<MTLBuffer> buffer = [device newBufferWithLength:sizeof(float)*max_buffer
                                                   options:MTLResourceCPUCacheModeDefaultCache |
                                                           MTLResourceStorageModeManaged];

        MTLTextureDescriptor *textureDescriptor = [[MTLTextureDescriptor alloc] init];
        textureDescriptor.textureType = MTLTextureType2D;
        textureDescriptor.pixelFormat = MTLPixelFormatR32Float;
        textureDescriptor.width = max_texture;
        textureDescriptor.height = max_texture;
        textureDescriptor.depth = 1;
        textureDescriptor.mipmapLevelCount = 1;
        textureDescriptor.sampleCount = 1;
        textureDescriptor.arrayLength = 1;
        textureDescriptor.resourceOptions = MTLResourceStorageModePrivate |
        MTLResourceCPUCacheModeDefaultCache;
        textureDescriptor.cpuCacheMode = MTLCPUCacheModeDefaultCache;
        textureDescriptor.storageMode = MTLStorageModePrivate;
        textureDescriptor.usage = MTLTextureUsageShaderRead;
        id<MTLTexture> texture1 = [device newTextureWithDescriptor:textureDescriptor];
        id<MTLTexture> texture2 = [device newTextureWithDescriptor:textureDescriptor];

        MTLComputePipelineDescriptor *discriptor = [[MTLComputePipelineDescriptor alloc] init];
        discriptor.computeFunction = [library newFunctionWithName:@"test_texture"];
        discriptor.threadGroupSizeIsMultipleOfThreadExecutionWidth = YES;

        id<MTLComputePipelineState> pipeline = [device newComputePipelineStateWithDescriptor:discriptor
                                                                                     options:MTLPipelineOptionNone
                                                                                  reflection:NULL
                                                                                       error:NULL];

        id<MTLCommandBuffer> command_buffer = queue.commandBuffer;
        id<MTLComputeCommandEncoder> compute_encoder = [command_buffer computeCommandEncoder];
        [compute_encoder setComputePipelineState:pipeline];
        [compute_encoder setTexture:texture1 atIndex:0];
        [compute_encoder setTexture:texture2 atIndex:1];
        [compute_encoder setBuffer:buffer offset:0 atIndex:0];
        [compute_encoder dispatchThreads:MTLSizeMake(max_buffer, 1, 1) threadsPerThreadgroup:MTLSizeMake(1024, 1, 1)];
        [compute_encoder endEncoding];

        id<MTLBlitCommandEncoder> blit_encoder = [command_buffer blitCommandEncoder];
        [blit_encoder synchronizeResource:buffer];
        [blit_encoder endEncoding];

        [command_buffer commit];
        [command_buffer waitUntilCompleted];

        float *result = (float *)buffer.contents;
        NSLog(@"%f",result[0]);
    }
    return 0;
}

如果我注释掉第二个纹理参数，则在读取结果缓冲区时会得到期望值。但是，当我完整保留第二个纹理参数时，它看起来好像内核没有运行，并且结果的值显示为零。在MacOS上的计算内核中可以采样的纹理数量是否有限制？还是由于我在两个纹理中都使用了最大纹理尺寸（我的纹理内存用完了）引起的问题？ strong text

Answer 1

在您的情况下，错误很可能是由于纹理占用了整个视频内存预算造成的。 16384 x 16384 * sizeof（float）=每个纹理1024mb的内存因为您使用的是MTLStorageModePrivate，所以资源仅存储在视频内存中。

金属计算内核因两个纹理参数而失败

1 个答案: