P4 to Git Change 1177220 by emankov@em-hsa-amd on 2015/08/05 06:08:39

ECR #333753 - ORCA RT/Compiler Lib/aoc2: AMD HSA Code Object Import feature (part II) - arbitrary hidden (extra) kernargs support

	Only HSAIL path is affected. It doesn't affect blit kernels.

	To use offline by aoc2:
	aoc2 -hsacodeobject=<importing_code_object_filename> -numhiddenkernargs=<num> -cl-std=CL2.0 -march=hsail(-64) -mdevice=Bonaire <source_cl_filename>

	To use online by setting env:
	AMD_DEBUG_HSA_NUM_HIDDEN_KERNARGS=<num>

	where num >= 0. If num == 0, then no additional arguments will be added on RT for every kernel. The default value is unchanged and equal to 6 for now.

	Misc:
	+ get rid of PRE & POST defines in Compiler Lib, as they started to conflict with ugl\gl\gs\hwl\ headers with the same defines.
	+ minor copy/paste eliminations & typo fixes
	+ ocltst complib tests update

	Testing: pre check-in, manually based on ocl sdk MatrixMultiplication

	Reviewers: Brian Sumner, German Andryeyev, Nikolay Haustov, Artem Tamazov

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#72 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/hsail_be.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/metadata.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclDefs.h#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclEnums.h#19 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclStructs.h#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/bif_section_labels.hpp#21 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/libUtils.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/libUtils.h#20 edit
... //depot/stg/opencl/drivers/opencl/compiler/tools/aoc2/aoc2.cpp#74 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#181 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#249 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#291 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#113 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#199 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#369 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsaprogram.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsakernel.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsakernel.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsaprogram.cpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsavirtual.cpp#43 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/CLAssumptionCheck.cpp#43 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/CLEnumCheck.cpp#44 edit

rocclr/compiler/lib/include/v0_8/aclDefs.h

@@ -28,4 +28,10 @@
 #define BIF_API_3_0
 #endif
 
+#ifndef MAX_HIDDEN_KERNARGS_NUM
+#define MAX_HIDDEN_KERNARGS_NUM 6
+#else
+#error "MAX_HIDDEN_KERNARGS_NUM is already defined"
+#endif
+
 #endif // _ACL_DEFS_0_8_H_

rocclr/compiler/lib/include/v0_8/aclEnums.h

@@ -188,29 +188,30 @@ typedef enum _bif_sections_enum_0_8 {
 
 //! An enumeration that defines what are valid queries for aclQueryInfo.
 typedef enum _rt_query_types_enum_0_8 {
-  RT_ABI_VERSION         = 0,
-  RT_DEVICE_NAME         = 1,
-  RT_MEM_SIZES           = 2,
-  RT_GPU_FUNC_CAPS       = 3,
-  RT_GPU_FUNC_ID         = 4,
-  RT_GPU_DEFAULT_ID      = 5,
-  RT_WORK_GROUP_SIZE     = 6,
-  RT_WORK_REGION_SIZE    = 7,
-  RT_ARGUMENT_ARRAY      = 8,
-  RT_GPU_PRINTF_ARRAY    = 9,
-  RT_CPU_BARRIER_NAMES   = 10,
-  RT_DEVICE_ENQUEUE      = 11,
-  RT_KERNEL_INDEX        = 12,
-  RT_KERNEL_NAME         = 13,
-  RT_KERNEL_NAMES        = 14,
-  RT_CONTAINS_LLVMIR     = 15,
-  RT_CONTAINS_OPTIONS    = 16,
-  RT_CONTAINS_BRIG       = 17,
-  RT_CONTAINS_HSAIL      = 18,
-  RT_CONTAINS_ISA        = 19,
-  RT_CONTAINS_LOADER_MAP = 20,
-  RT_CONTAINS_SPIR       = 21,
-  RT_LAST_TYPE           = 22
+  RT_ABI_VERSION            = 0,
+  RT_DEVICE_NAME            = 1,
+  RT_MEM_SIZES              = 2,
+  RT_GPU_FUNC_CAPS          = 3,
+  RT_GPU_FUNC_ID            = 4,
+  RT_GPU_DEFAULT_ID         = 5,
+  RT_WORK_GROUP_SIZE        = 6,
+  RT_WORK_REGION_SIZE       = 7,
+  RT_ARGUMENT_ARRAY         = 8,
+  RT_GPU_PRINTF_ARRAY       = 9,
+  RT_CPU_BARRIER_NAMES      = 10,
+  RT_DEVICE_ENQUEUE         = 11,
+  RT_KERNEL_INDEX           = 12,
+  RT_KERNEL_NAME            = 13,
+  RT_KERNEL_NAMES           = 14,
+  RT_CONTAINS_LLVMIR        = 15,
+  RT_CONTAINS_OPTIONS       = 16,
+  RT_CONTAINS_BRIG          = 17,
+  RT_CONTAINS_HSAIL         = 18,
+  RT_CONTAINS_ISA           = 19,
+  RT_CONTAINS_LOADER_MAP    = 20,
+  RT_CONTAINS_SPIR          = 21,
+  RT_NUM_KERNEL_HIDDEN_ARGS = 22,
+  RT_LAST_TYPE              = 23
 } aclQueryType_0_8;
 
 //! An enumeration for the various GPU capabilities

rocclr/compiler/lib/include/v0_8/aclStructs.h

@@ -119,6 +119,7 @@ typedef struct _acl_metadata_0_8 {
   const char *deviceName; // RT_DEVICE_NAME
   bool enqueue_kernel; // RT_DEVICE_ENQUEUE
   uint32_t kernel_index; // RT_KERNEL_INDEX
+  uint32_t numHiddenKernelArgs; // RT_NUM_KERNEL_HIDDEN_ARGS
 } aclMetadata_0_8;
 
 //! An structure that holds information on the capabilities of the bif device.