gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improve ROCm support. (#780)

Browse Source 
- updates to support ROCm 5.2
- workarounds in tests where NV tools were used unconditionally
- implemented `get_num_blocks()` and `add_memfence()` for AMD GPU
- backported from history some atomics
- added bf16 support
- minor warnings cleanup
- added dockerfile to run on a ROCm enabled machine

Co-authored-by: B1tway <andrew.shukshov@gmail.com>
Co-authored-by: Andrey Shukshov <36711069+B1tway@users.noreply.github.com>
This commit is contained in:
Daniil Fukalov
2022-10-14 21:33:42 +03:00
committed by GitHub
parent 94d5c2e8b5
commit 406d03bfaf
17 changed files with 435 additions and 155 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
include/triton/codegen/analysis/layout.h
View File

@@ -137,7 +137,8 @@ private:
std::vector<int> rep_;
};
struct scanline_layout: public distributed_layout {
class scanline_layout: public distributed_layout {
public:
scanline_layout(size_t num_warps,
const std::vector<int>& axes,
const std::vector<unsigned>& shape,
@@ -149,7 +150,7 @@ struct scanline_layout: public distributed_layout {
int mts(size_t k) { return mts_.at(k); }
int nts(size_t k) { return nts_.at(k); }
public:
private:
// micro tile size. The size of a tile held by a thread block.
std::vector<int> mts_;
// nano tile size. The size of a tile held by a thread.

5
include/triton/driver/dispatch.h
View File

@@ -181,7 +181,8 @@ public:
static hipError_t hipEventElapsedTime(float *pMilliseconds, hipEvent_t hStart, hipEvent_t hEnd);
static hipError_t hipEventRecord(hipEvent_t hEvent, hipStream_t hStream);
static hipError_t hipEventDestroy(hipEvent_t hEvent);
// error handling
static hipError_t hipGetLastError(void);
private:
@@ -306,6 +307,8 @@ private:
static void* hipEventElapsedTime_;
static void* hipEventRecord_;
static void* hipEventDestroy_;
// error handling
static void* hipGetLastError_;
};
}

4
include/triton/driver/llvm.h
View File

@@ -17,3 +17,7 @@ hipModule_t amdgpu_to_hipmodule(const std::string& path);
}
}
#define STRINGIFY_HELPER(X) #X
#define STRINGIFY(X) STRINGIFY_HELPER(X)

319
include/triton/external/hip.h vendored
View File

@@ -1,13 +1,35 @@
/*
* @brief hipError_t
* @enum
* @ingroup Enumerations
*/
// Developer note - when updating these, update the hipErrorName and hipErrorString functions in
// NVCC and HCC paths Also update the hipCUDAErrorTohipError function in NVCC path.
Copyright (c) 2015 - 2022 Advanced Micro Devices, Inc. All rights reserved.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
*/
#ifndef HIP_H
#define HIP_H
// Ignoring error-code return values from hip APIs is discouraged. On C++17,
// we can make that yield a warning
#if __cplusplus >= 201703L
#define __HIP_NODISCARD [[nodiscard]]
#else
#define __HIP_NODISCARD
#endif
/*
* @brief hipError_t
@@ -17,9 +39,7 @@
// Developer note - when updating these, update the hipErrorName and hipErrorString functions in
// NVCC and HCC paths Also update the hipCUDAErrorTohipError function in NVCC path.
#include <cstddef>
typedef enum hipError_t {
typedef enum __HIP_NODISCARD hipError_t {
hipSuccess = 0, ///< Successful completion.
hipErrorInvalidValue = 1, ///< One or more of the parameters passed to the API call is NULL
///< or not in an acceptable range.
@@ -73,6 +93,7 @@ typedef enum hipError_t {
hipErrorInvalidHandle = 400,
// Deprecated
hipErrorInvalidResourceHandle = 400, ///< Resource handle (hipEvent_t or hipStream_t) invalid.
hipErrorIllegalState = 401, ///< Resource required is not in a valid state to perform operation.
hipErrorNotFound = 500,
hipErrorNotReady = 600, ///< Indicates that asynchronous operations enqueued earlier are not
///< ready. This is not actually an error, but is used to distinguish
@@ -86,6 +107,7 @@ typedef enum hipError_t {
hipErrorPeerAccessNotEnabled =
705, ///< Peer access was never enabled from the current device.
hipErrorSetOnActiveProcess = 708,
hipErrorContextIsDestroyed = 709,
hipErrorAssert = 710, ///< Produced when the kernel calls assert.
hipErrorHostMemoryAlreadyRegistered =
712, ///< Produced when trying to lock a page-locked memory.
@@ -98,6 +120,32 @@ typedef enum hipError_t {
///< that was launched via cooperative launch APIs exceeds the maximum number of
///< allowed blocks for the current device
hipErrorNotSupported = 801, ///< Produced when the hip API is not supported/implemented
hipErrorStreamCaptureUnsupported = 900, ///< The operation is not permitted when the stream
///< is capturing.
hipErrorStreamCaptureInvalidated = 901, ///< The current capture sequence on the stream
///< has been invalidated due to a previous error.
hipErrorStreamCaptureMerge = 902, ///< The operation would have resulted in a merge of
///< two independent capture sequences.
hipErrorStreamCaptureUnmatched = 903, ///< The capture was not initiated in this stream.
hipErrorStreamCaptureUnjoined = 904, ///< The capture sequence contains a fork that was not
///< joined to the primary stream.
hipErrorStreamCaptureIsolation = 905, ///< A dependency would have been created which crosses
///< the capture sequence boundary. Only implicit
///< in-stream ordering dependencies are allowed
///< to cross the boundary
hipErrorStreamCaptureImplicit = 906, ///< The operation would have resulted in a disallowed
///< implicit dependency on a current capture sequence
///< from hipStreamLegacy.
hipErrorCapturedEvent = 907, ///< The operation is not permitted on an event which was last
///< recorded in a capturing stream.
hipErrorStreamCaptureWrongThread = 908, ///< A stream capture sequence not initiated with
///< the hipStreamCaptureModeRelaxed argument to
///< hipStreamBeginCapture was passed to
///< hipStreamEndCapture in a different thread.
hipErrorGraphExecUpdateFailure = 910, ///< This error indicates that the graph update
///< not performed because it included changes which
///< violated constraintsspecific to instantiated graph
///< update.
hipErrorUnknown = 999, //< Unknown error.
// HSA Runtime Error Codes start here.
hipErrorRuntimeMemory = 1052, ///< HSA runtime memory call returned error. Typically not seen
@@ -107,35 +155,154 @@ typedef enum hipError_t {
hipErrorTbd ///< Marker that more error codes are needed.
} hipError_t;
#undef __HIP_NODISCARD
/*
* @brief hipDeviceAttribute_t
* @enum
* @ingroup Enumerations
*/
typedef enum hipDeviceAttribute_t {
hipDeviceAttributeCudaCompatibleBegin = 0,
hipDeviceAttributeEccEnabled = hipDeviceAttributeCudaCompatibleBegin, ///< Whether ECC support is enabled.
hipDeviceAttributeAccessPolicyMaxWindowSize, ///< Cuda only. The maximum size of the window policy in bytes.
hipDeviceAttributeAsyncEngineCount, ///< Cuda only. Asynchronous engines number.
hipDeviceAttributeCanMapHostMemory, ///< Whether host memory can be mapped into device address space
hipDeviceAttributeCanUseHostPointerForRegisteredMem,///< Cuda only. Device can access host registered memory
///< at the same virtual address as the CPU
hipDeviceAttributeClockRate, ///< Peak clock frequency in kilohertz.
hipDeviceAttributeComputeMode, ///< Compute mode that device is currently in.
hipDeviceAttributeComputePreemptionSupported, ///< Cuda only. Device supports Compute Preemption.
hipDeviceAttributeConcurrentKernels, ///< Device can possibly execute multiple kernels concurrently.
hipDeviceAttributeConcurrentManagedAccess, ///< Device can coherently access managed memory concurrently with the CPU
hipDeviceAttributeCooperativeLaunch, ///< Support cooperative launch
hipDeviceAttributeCooperativeMultiDeviceLaunch, ///< Support cooperative launch on multiple devices
hipDeviceAttributeDeviceOverlap, ///< Cuda only. Device can concurrently copy memory and execute a kernel.
///< Deprecated. Use instead asyncEngineCount.
hipDeviceAttributeDirectManagedMemAccessFromHost, ///< Host can directly access managed memory on
///< the device without migration
hipDeviceAttributeGlobalL1CacheSupported, ///< Cuda only. Device supports caching globals in L1
hipDeviceAttributeHostNativeAtomicSupported, ///< Cuda only. Link between the device and the host supports native atomic operations
hipDeviceAttributeIntegrated, ///< Device is integrated GPU
hipDeviceAttributeIsMultiGpuBoard, ///< Multiple GPU devices.
hipDeviceAttributeKernelExecTimeout, ///< Run time limit for kernels executed on the device
hipDeviceAttributeL2CacheSize, ///< Size of L2 cache in bytes. 0 if the device doesn't have L2 cache.
hipDeviceAttributeLocalL1CacheSupported, ///< caching locals in L1 is supported
hipDeviceAttributeLuid, ///< Cuda only. 8-byte locally unique identifier in 8 bytes. Undefined on TCC and non-Windows platforms
hipDeviceAttributeLuidDeviceNodeMask, ///< Cuda only. Luid device node mask. Undefined on TCC and non-Windows platforms
hipDeviceAttributeComputeCapabilityMajor, ///< Major compute capability version number.
hipDeviceAttributeManagedMemory, ///< Device supports allocating managed memory on this system
hipDeviceAttributeMaxBlocksPerMultiProcessor, ///< Cuda only. Max block size per multiprocessor
hipDeviceAttributeMaxBlockDimX, ///< Max block size in width.
hipDeviceAttributeMaxBlockDimY, ///< Max block size in height.
hipDeviceAttributeMaxBlockDimZ, ///< Max block size in depth.
hipDeviceAttributeMaxGridDimX, ///< Max grid size in width.
hipDeviceAttributeMaxGridDimY, ///< Max grid size in height.
hipDeviceAttributeMaxGridDimZ, ///< Max grid size in depth.
hipDeviceAttributeMaxSurface1D, ///< Maximum size of 1D surface.
hipDeviceAttributeMaxSurface1DLayered, ///< Cuda only. Maximum dimensions of 1D layered surface.
hipDeviceAttributeMaxSurface2D, ///< Maximum dimension (width, height) of 2D surface.
hipDeviceAttributeMaxSurface2DLayered, ///< Cuda only. Maximum dimensions of 2D layered surface.
hipDeviceAttributeMaxSurface3D, ///< Maximum dimension (width, height, depth) of 3D surface.
hipDeviceAttributeMaxSurfaceCubemap, ///< Cuda only. Maximum dimensions of Cubemap surface.
hipDeviceAttributeMaxSurfaceCubemapLayered, ///< Cuda only. Maximum dimension of Cubemap layered surface.
hipDeviceAttributeMaxTexture1DWidth, ///< Maximum size of 1D texture.
hipDeviceAttributeMaxTexture1DLayered, ///< Cuda only. Maximum dimensions of 1D layered texture.
hipDeviceAttributeMaxTexture1DLinear, ///< Maximum number of elements allocatable in a 1D linear texture.
///< Use cudaDeviceGetTexture1DLinearMaxWidth() instead on Cuda.
hipDeviceAttributeMaxTexture1DMipmap, ///< Cuda only. Maximum size of 1D mipmapped texture.
hipDeviceAttributeMaxTexture2DWidth, ///< Maximum dimension width of 2D texture.
hipDeviceAttributeMaxTexture2DHeight, ///< Maximum dimension hight of 2D texture.
hipDeviceAttributeMaxTexture2DGather, ///< Cuda only. Maximum dimensions of 2D texture if gather operations performed.
hipDeviceAttributeMaxTexture2DLayered, ///< Cuda only. Maximum dimensions of 2D layered texture.
hipDeviceAttributeMaxTexture2DLinear, ///< Cuda only. Maximum dimensions (width, height, pitch) of 2D textures bound to pitched memory.
hipDeviceAttributeMaxTexture2DMipmap, ///< Cuda only. Maximum dimensions of 2D mipmapped texture.
hipDeviceAttributeMaxTexture3DWidth, ///< Maximum dimension width of 3D texture.
hipDeviceAttributeMaxTexture3DHeight, ///< Maximum dimension height of 3D texture.
hipDeviceAttributeMaxTexture3DDepth, ///< Maximum dimension depth of 3D texture.
hipDeviceAttributeMaxTexture3DAlt, ///< Cuda only. Maximum dimensions of alternate 3D texture.
hipDeviceAttributeMaxTextureCubemap, ///< Cuda only. Maximum dimensions of Cubemap texture
hipDeviceAttributeMaxTextureCubemapLayered, ///< Cuda only. Maximum dimensions of Cubemap layered texture.
hipDeviceAttributeMaxThreadsDim, ///< Maximum dimension of a block
hipDeviceAttributeMaxThreadsPerBlock, ///< Maximum number of threads per block.
hipDeviceAttributeMaxThreadsPerMultiProcessor, ///< Maximum resident threads per multiprocessor.
hipDeviceAttributeMaxPitch, ///< Maximum pitch in bytes allowed by memory copies
hipDeviceAttributeMemoryBusWidth, ///< Global memory bus width in bits.
hipDeviceAttributeMemoryClockRate, ///< Peak memory clock frequency in kilohertz.
hipDeviceAttributeComputeCapabilityMinor, ///< Minor compute capability version number.
hipDeviceAttributeMultiGpuBoardGroupID, ///< Cuda only. Unique ID of device group on the same multi-GPU board
hipDeviceAttributeMultiprocessorCount, ///< Number of multiprocessors on the device.
hipDeviceAttributeName, ///< Device name.
hipDeviceAttributePageableMemoryAccess, ///< Device supports coherently accessing pageable memory
///< without calling hipHostRegister on it
hipDeviceAttributePageableMemoryAccessUsesHostPageTables, ///< Device accesses pageable memory via the host's page tables
hipDeviceAttributePciBusId, ///< PCI Bus ID.
hipDeviceAttributePciDeviceId, ///< PCI Device ID.
hipDeviceAttributePciDomainID, ///< PCI Domain ID.
hipDeviceAttributePersistingL2CacheMaxSize, ///< Cuda11 only. Maximum l2 persisting lines capacity in bytes
hipDeviceAttributeMaxRegistersPerBlock, ///< 32-bit registers available to a thread block. This number is shared
///< by all thread blocks simultaneously resident on a multiprocessor.
hipDeviceAttributeMaxRegistersPerMultiprocessor, ///< 32-bit registers available per block.
hipDeviceAttributeReservedSharedMemPerBlock, ///< Cuda11 only. Shared memory reserved by CUDA driver per block.
hipDeviceAttributeMaxSharedMemoryPerBlock, ///< Maximum shared memory available per block in bytes.
hipDeviceAttributeSharedMemPerBlockOptin, ///< Cuda only. Maximum shared memory per block usable by special opt in.
hipDeviceAttributeSharedMemPerMultiprocessor, ///< Cuda only. Shared memory available per multiprocessor.
hipDeviceAttributeSingleToDoublePrecisionPerfRatio, ///< Cuda only. Performance ratio of single precision to double precision.
hipDeviceAttributeStreamPrioritiesSupported, ///< Cuda only. Whether to support stream priorities.
hipDeviceAttributeSurfaceAlignment, ///< Cuda only. Alignment requirement for surfaces
hipDeviceAttributeTccDriver, ///< Cuda only. Whether device is a Tesla device using TCC driver
hipDeviceAttributeTextureAlignment, ///< Alignment requirement for textures
hipDeviceAttributeTexturePitchAlignment, ///< Pitch alignment requirement for 2D texture references bound to pitched memory;
hipDeviceAttributeTotalConstantMemory, ///< Constant memory size in bytes.
hipDeviceAttributeTotalGlobalMem, ///< Global memory available on devicice.
hipDeviceAttributeUnifiedAddressing, ///< Cuda only. An unified address space shared with the host.
hipDeviceAttributeUuid, ///< Cuda only. Unique ID in 16 byte.
hipDeviceAttributeWarpSize, ///< Warp size in threads.
hipDeviceAttributeMemoryPoolsSupported, ///< Device supports HIP Stream Ordered Memory Allocator
hipDeviceAttributeCudaCompatibleEnd = 9999,
hipDeviceAttributeAmdSpecificBegin = 10000,
hipDeviceAttributeClockInstructionRate = hipDeviceAttributeAmdSpecificBegin, ///< Frequency in khz of the timer used by the device-side "clock*"
hipDeviceAttributeArch, ///< Device architecture
hipDeviceAttributeMaxSharedMemoryPerMultiprocessor, ///< Maximum Shared Memory PerMultiprocessor.
hipDeviceAttributeGcnArch, ///< Device gcn architecture
hipDeviceAttributeGcnArchName, ///< Device gcnArch name in 256 bytes
hipDeviceAttributeHdpMemFlushCntl, ///< Address of the HDP_MEM_COHERENCY_FLUSH_CNTL register
hipDeviceAttributeHdpRegFlushCntl, ///< Address of the HDP_REG_COHERENCY_FLUSH_CNTL register
hipDeviceAttributeCooperativeMultiDeviceUnmatchedFunc, ///< Supports cooperative launch on multiple
///< devices with unmatched functions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedGridDim, ///< Supports cooperative launch on multiple
///< devices with unmatched grid dimensions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedBlockDim, ///< Supports cooperative launch on multiple
///< devices with unmatched block dimensions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedSharedMem, ///< Supports cooperative launch on multiple
///< devices with unmatched shared memories
hipDeviceAttributeIsLargeBar, ///< Whether it is LargeBar
hipDeviceAttributeAsicRevision, ///< Revision of the GPU in this device
hipDeviceAttributeCanUseStreamWaitValue, ///< '1' if Device supports hipStreamWaitValue32() and
///< hipStreamWaitValue64(), '0' otherwise.
hipDeviceAttributeImageSupport, ///< '1' if Device supports image, '0' otherwise.
hipDeviceAttributePhysicalMultiProcessorCount, ///< All available physical compute
///< units for the device
hipDeviceAttributeFineGrainSupport, ///< '1' if Device supports fine grain, '0' otherwise
hipDeviceAttributeAmdSpecificEnd = 19999,
hipDeviceAttributeVendorSpecificBegin = 20000,
// Extended attributes for vendors
} hipDeviceAttribute_t;
#define HIP_LAUNCH_PARAM_BUFFER_POINTER ((void*)0x01)
#define HIP_LAUNCH_PARAM_BUFFER_SIZE ((void*)0x02)
#define HIP_LAUNCH_PARAM_END ((void*)0x03)
// API-visible structures
typedef struct ihipCtx_t* hipCtx_t;
// Note many APIs also use integer deviceIds as an alternative to the device pointer:
typedef int hipDevice_t;
typedef enum hipDeviceP2PAttr {
hipDevP2PAttrPerformanceRank = 0,
hipDevP2PAttrAccessSupported,
hipDevP2PAttrNativeAtomicSupported,
hipDevP2PAttrHipArrayAccessSupported
} hipDeviceP2PAttr;
typedef struct ihipStream_t* hipStream_t;
#define hipIpcMemLazyEnablePeerAccess 0
#define HIP_IPC_HANDLE_SIZE 64
typedef struct hipIpcMemHandle_st {
char reserved[HIP_IPC_HANDLE_SIZE];
} hipIpcMemHandle_t;
typedef struct hipIpcEventHandle_st {
char reserved[HIP_IPC_HANDLE_SIZE];
} hipIpcEventHandle_t;
typedef struct ihipModule_t* hipModule_t;
typedef struct ihipModuleSymbol_t* hipFunction_t;
typedef struct hipFuncAttributes {
@@ -150,91 +317,8 @@ typedef struct hipFuncAttributes {
int ptxVersion;
size_t sharedSizeBytes;
} hipFuncAttributes;
typedef struct ihipEvent_t* hipEvent_t;
/*
* @brief hipDeviceAttribute_t
* @enum
* @ingroup Enumerations
*/
typedef enum hipDeviceAttribute_t {
hipDeviceAttributeMaxThreadsPerBlock, ///< Maximum number of threads per block.
hipDeviceAttributeMaxBlockDimX, ///< Maximum x-dimension of a block.
hipDeviceAttributeMaxBlockDimY, ///< Maximum y-dimension of a block.
hipDeviceAttributeMaxBlockDimZ, ///< Maximum z-dimension of a block.
hipDeviceAttributeMaxGridDimX, ///< Maximum x-dimension of a grid.
hipDeviceAttributeMaxGridDimY, ///< Maximum y-dimension of a grid.
hipDeviceAttributeMaxGridDimZ, ///< Maximum z-dimension of a grid.
hipDeviceAttributeMaxSharedMemoryPerBlock, ///< Maximum shared memory available per block in
///< bytes.
hipDeviceAttributeTotalConstantMemory, ///< Constant memory size in bytes.
hipDeviceAttributeWarpSize, ///< Warp size in threads.
hipDeviceAttributeMaxRegistersPerBlock, ///< Maximum number of 32-bit registers available to a
///< thread block. This number is shared by all thread
///< blocks simultaneously resident on a
///< multiprocessor.
hipDeviceAttributeClockRate, ///< Peak clock frequency in kilohertz.
hipDeviceAttributeMemoryClockRate, ///< Peak memory clock frequency in kilohertz.
hipDeviceAttributeMemoryBusWidth, ///< Global memory bus width in bits.
hipDeviceAttributeMultiprocessorCount, ///< Number of multiprocessors on the device.
hipDeviceAttributeComputeMode, ///< Compute mode that device is currently in.
hipDeviceAttributeL2CacheSize, ///< Size of L2 cache in bytes. 0 if the device doesn't have L2
///< cache.
hipDeviceAttributeMaxThreadsPerMultiProcessor, ///< Maximum resident threads per
///< multiprocessor.
hipDeviceAttributeComputeCapabilityMajor, ///< Major compute capability version number.
hipDeviceAttributeComputeCapabilityMinor, ///< Minor compute capability version number.
hipDeviceAttributeConcurrentKernels, ///< Device can possibly execute multiple kernels
///< concurrently.
hipDeviceAttributePciBusId, ///< PCI Bus ID.
hipDeviceAttributePciDeviceId, ///< PCI Device ID.
hipDeviceAttributeMaxSharedMemoryPerMultiprocessor, ///< Maximum Shared Memory Per
///< Multiprocessor.
hipDeviceAttributeIsMultiGpuBoard, ///< Multiple GPU devices.
hipDeviceAttributeIntegrated, ///< iGPU
hipDeviceAttributeCooperativeLaunch, ///< Support cooperative launch
hipDeviceAttributeCooperativeMultiDeviceLaunch, ///< Support cooperative launch on multiple devices
hipDeviceAttributeMaxTexture1DWidth, ///< Maximum number of elements in 1D images
hipDeviceAttributeMaxTexture2DWidth, ///< Maximum dimension width of 2D images in image elements
hipDeviceAttributeMaxTexture2DHeight, ///< Maximum dimension height of 2D images in image elements
hipDeviceAttributeMaxTexture3DWidth, ///< Maximum dimension width of 3D images in image elements
hipDeviceAttributeMaxTexture3DHeight, ///< Maximum dimensions height of 3D images in image elements
hipDeviceAttributeMaxTexture3DDepth, ///< Maximum dimensions depth of 3D images in image elements
hipDeviceAttributeHdpMemFlushCntl, ///< Address of the HDP_MEM_COHERENCY_FLUSH_CNTL register
hipDeviceAttributeHdpRegFlushCntl, ///< Address of the HDP_REG_COHERENCY_FLUSH_CNTL register
hipDeviceAttributeMaxPitch, ///< Maximum pitch in bytes allowed by memory copies
hipDeviceAttributeTextureAlignment, ///<Alignment requirement for textures
hipDeviceAttributeTexturePitchAlignment, ///<Pitch alignment requirement for 2D texture references bound to pitched memory;
hipDeviceAttributeKernelExecTimeout, ///<Run time limit for kernels executed on the device
hipDeviceAttributeCanMapHostMemory, ///<Device can map host memory into device address space
hipDeviceAttributeEccEnabled, ///<Device has ECC support enabled
hipDeviceAttributeCooperativeMultiDeviceUnmatchedFunc, ///< Supports cooperative launch on multiple
///devices with unmatched functions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedGridDim, ///< Supports cooperative launch on multiple
///devices with unmatched grid dimensions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedBlockDim, ///< Supports cooperative launch on multiple
///devices with unmatched block dimensions
hipDeviceAttributeCooperativeMultiDeviceUnmatchedSharedMem, ///< Supports cooperative launch on multiple
///devices with unmatched shared memories
hipDeviceAttributeAsicRevision, ///< Revision of the GPU in this device
hipDeviceAttributeManagedMemory, ///< Device supports allocating managed memory on this system
hipDeviceAttributeDirectManagedMemAccessFromHost, ///< Host can directly access managed memory on
/// the device without migration
hipDeviceAttributeConcurrentManagedAccess, ///< Device can coherently access managed memory
/// concurrently with the CPU
hipDeviceAttributePageableMemoryAccess, ///< Device supports coherently accessing pageable memory
/// without calling hipHostRegister on it
hipDeviceAttributePageableMemoryAccessUsesHostPageTables, ///< Device accesses pageable memory via
/// the host's page tables
hipDeviceAttributeCanUseStreamWaitValue ///< '1' if Device supports hipStreamWaitValue32() and
///< hipStreamWaitValue64() , '0' otherwise.
} hipDeviceAttribute_t;
typedef void* hipDeviceptr_t;
/*
@@ -262,7 +346,6 @@ typedef enum hipJitOption {
hipJitOptionFastCompile,
hipJitOptionNumOptions
} hipJitOption;
/**
* @warning On AMD devices and some Nvidia devices, these hints and controls are ignored.
*/
@@ -271,7 +354,6 @@ typedef enum hipFuncAttribute {
hipFuncAttributePreferredSharedMemoryCarveout = 9,
hipFuncAttributeMax
} hipFuncAttribute;
/**
* @warning On AMD devices and some Nvidia devices, these hints and controls are ignored.
*/
@@ -282,7 +364,4 @@ typedef enum hipFuncCache_t {
hipFuncCachePreferEqual, ///< prefer equal size L1 cache and shared memory
} hipFuncCache_t;
#define HIP_LAUNCH_PARAM_BUFFER_POINTER ((void*)0x01)
#define HIP_LAUNCH_PARAM_BUFFER_SIZE ((void*)0x02)
#define HIP_LAUNCH_PARAM_END ((void*)0x03)
#endif

1
include/triton/ir/type.h
View File

@@ -129,6 +129,7 @@ public:
case VoidTyID: return "void";
case FP8TyID: return "fp8";
case FP16TyID: return "f16";
case BF16TyID: return "bf16";
case FP32TyID: return "f32";
case FP64TyID: return "f64";
case LabelTyID: return "label";