Split env.hpp header from the ck.hpp header. (#2049)

* split env.hpp out of main headers

* fix namespace logic

[ROCm/composable_kernel commit: 572cd820ce]

include/ck/ck.hpp

@@ -6,15 +6,10 @@
 #include "ck/config.h"
 
 #if !defined(__HIPCC_RTC__) || !defined(CK_CODE_GEN_RTC)
-#include "ck/utility/env.hpp"
 #ifndef CK_DONT_USE_HIP_RUNTIME_HEADERS
 #include "hip/hip_runtime.h"
 #include "hip/hip_fp16.h"
 #endif
-
-// environment variable to enable logging:
-// export CK_LOGGING=ON or CK_LOGGING=1 or CK_LOGGING=ENABLED
-CK_DECLARE_ENV_VAR_BOOL(CK_LOGGING)
 #endif
 // to do: add various levels of logging with CK_LOG_LEVEL
 

include/ck/host_utility/flush_cache.hpp

@@ -8,6 +8,7 @@
 #include <vector>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/stream_config.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 #include "ck/utility/flush_icache.hpp"

include/ck/host_utility/kernel_launch.hpp

@@ -6,6 +6,7 @@
 #include <hip/hip_runtime.h>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/stream_config.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp

@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -8,6 +8,7 @@
 #include <vector>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #ifndef DEVICE_CONV3D_FWD_XDL_HPP
 #define DEVICE_CONV3D_FWD_XDL_HPP
@@ -10,6 +10,7 @@
 #include "device.hpp"
 #include "device_conv_fwd.hpp"
 #include "common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "tensor_layout.hpp"
 #include "convolution_forward_specialization.hpp"
 #include "tensor_descriptor.hpp"

include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp

@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp

@@ -8,6 +8,7 @@
 
 #include "ck/library/utility/numeric.hpp"
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_two_stage_xdl_cshuffle.hpp

@@ -8,7 +8,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
-
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_xdl_cshuffle.hpp

@@ -8,6 +8,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp

@@ -11,6 +11,7 @@
 
 #include "ck/library/utility/numeric.hpp"
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle_v3.hpp

@@ -11,6 +11,7 @@
 
 #include "ck/library/utility/numeric.hpp"
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_dl.hpp

@@ -8,6 +8,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multiple_d_splitk_xdl_cshuffle_two_stage.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -8,6 +8,7 @@
 #include <tuple>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"
 #include "ck/host_utility/hip_check_error.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp

@@ -8,6 +8,7 @@
 #include <sstream>
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp

@@ -7,6 +7,7 @@
 #include <sstream>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"
 #include "ck/host_utility/hip_check_error.hpp"

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_streamk_v3.hpp

@@ -4,6 +4,7 @@
 #pragma once
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/multi_index_transform_helper.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp

@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/multi_index_transform_helper.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_b_preshuffle.hpp

@@ -4,6 +4,7 @@
 #pragma once
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/multi_index_transform_helper.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_b_scale.hpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -13,6 +13,7 @@
 #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
 #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_abd.hpp

@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/multi_index_transform_helper.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx.hpp

@@ -13,6 +13,7 @@
 #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
 #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp

@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
 #include "ck/utility/common_header.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_description/multi_index_transform_helper.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"

include/ck/utility/env.hpp

@@ -184,4 +184,9 @@ void UpdateEnvVar(EnvVar, const std::string_view& val)
 }
 
 } // namespace ck
+
+// environment variable to enable logging:
+// export CK_LOGGING=ON or CK_LOGGING=1 or CK_LOGGING=ENABLED
+CK_DECLARE_ENV_VAR_BOOL(CK_LOGGING)
+
 #endif

include/ck_tile/core.hpp

@@ -59,7 +59,6 @@
 #include "ck_tile/core/tensor/transpose_tile.hpp"
 #include "ck_tile/core/tensor/update_tile.hpp"
 #include "ck_tile/core/utility/bit_cast.hpp"
-#include "ck_tile/core/utility/env.hpp"
 #include "ck_tile/core/utility/functional.hpp"
 #include "ck_tile/core/utility/functional_with_tuple.hpp"
 #include "ck_tile/core/utility/ignore.hpp"

include/ck_tile/core/config.hpp

@@ -28,12 +28,6 @@
 #include "hip/hip_fp16.h"
 #endif
 
-#include "ck_tile/core/utility/env.hpp"
-
-// environment variable to enable logging:
-// export CK_TILE_LOGGING=ON or CK_TILE_LOGGING=1 or CK_TILE_LOGGING=ENABLED
-CK_TILE_DECLARE_ENV_VAR_BOOL(CK_TILE_LOGGING)
-
 #ifdef __HIPCC__
 #define CK_TILE_HOST inline __host__
 #define CK_TILE_DEVICE inline __device__

include/ck_tile/core/utility/env.hpp

@@ -202,3 +202,7 @@ void UpdateEnvVar(EnvVar, const std::string_view& val)
 }
 
 } // namespace ck_tile
+
+// environment variable to enable logging:
+// export CK_TILE_LOGGING=ON or CK_TILE_LOGGING=1 or CK_TILE_LOGGING=ENABLED
+CK_TILE_DECLARE_ENV_VAR_BOOL(CK_TILE_LOGGING)

include/ck_tile/ops/gemm/kernel/gemm_kernel.hpp

@@ -9,6 +9,7 @@
 #include "ck_tile/core.hpp"
 #include "ck_tile/ops/common.hpp"
 #include "ck_tile/host/concat.hpp"
+#include "ck_tile/core/utility/env.hpp"
 
 namespace ck_tile {
 

profiler/include/profiler/profile_grouped_gemm_fixed_nk_impl.hpp

@@ -6,6 +6,7 @@
 #include <iomanip>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"

profiler/include/profiler/profile_grouped_gemm_impl.hpp

@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
 #include <iomanip>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm.hpp"
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp"

profiler/include/profiler/profile_grouped_gemm_multiply_tile_loop_impl.hpp

@@ -6,6 +6,7 @@
 #include <iomanip>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_tile_loop.hpp"

profiler/include/profiler/profile_grouped_gemm_tile_loop_impl.hpp

@@ -6,6 +6,7 @@
 #include <iomanip>
 
 #include "ck/ck.hpp"
+#include "ck/utility/env.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_tile_loop.hpp"