diff --git a/src/amd/vulkan/radv_pipeline.c b/src/amd/vulkan/radv_pipeline.c index 728cd8df753..35f99172ca9 100644 --- a/src/amd/vulkan/radv_pipeline.c +++ b/src/amd/vulkan/radv_pipeline.c @@ -4507,14 +4507,21 @@ radv_create_shaders(struct radv_pipeline *pipeline, struct radv_pipeline_layout } if (((stages[i].nir->info.bit_sizes_int | stages[i].nir->info.bit_sizes_float) & 16) && device->physical_device->rad_info.chip_class >= GFX9) { + bool copy_prop = false; uint32_t sampler_dims = UINT32_MAX; /* Skip because AMD doesn't support 16-bit types with these. */ sampler_dims &= ~BITFIELD_BIT(GLSL_SAMPLER_DIM_CUBE); // TODO: also optimize the tex srcs. see radeonSI for reference */ /* Skip if there are potentially conflicting rounding modes */ if (!nir_has_any_rounding_mode_enabled(stages[i].nir->info.float_controls_execution_mode)) - NIR_PASS_V(stages[i].nir, nir_fold_16bit_sampler_conversions, 0, sampler_dims); - NIR_PASS_V(stages[i].nir, nir_fold_16bit_image_load_store_conversions); + NIR_PASS(copy_prop, stages[i].nir, nir_fold_16bit_sampler_conversions, 0, sampler_dims); + NIR_PASS(copy_prop, stages[i].nir, nir_fold_16bit_image_load_store_conversions); + + if (copy_prop) { + NIR_PASS_V(stages[i].nir, nir_copy_prop); + NIR_PASS_V(stages[i].nir, nir_opt_dce); + } + NIR_PASS_V(stages[i].nir, nir_opt_vectorize, opt_vectorize_callback, NULL); }