/freebsd/contrib/llvm-project/llvm/lib/Target/AMDGPU/ |
H A D | AMDGPUSubtarget.h | 92 /// \returns Subtarget's default pair of minimum/maximum number of waves per 93 /// execution unit for function \p F, or minimum/maximum number of waves per 94 /// execution unit explicitly requested using "amdgpu-waves-per-eu" attribute 99 /// compatible with minimum/maximum number of waves limited by flat work group 274 /// \returns Number of waves per execution unit required to support the given 279 /// \returns Minimum number of waves per execution unit supported by the 283 /// \returns Maximum number of waves per execution unit supported by the
|
H A D | GCNSubtarget.h | 1306 /// Return the maximum number of waves per SIMD for kernels using \p SGPRs 1310 /// Return the maximum number of waves per SIMD for kernels using \p VGPRs 1405 /// \returns Minimum number of SGPRs that meets the given number of waves per 1411 /// \returns Maximum number of SGPRs that meets the given number of waves per 1435 /// \returns Maximum number of SGPRs that meets number of waves per execution 1439 /// \returns Value that meets number of waves per execution unit requirement 1441 /// subtarget's specifications, or does not meet number of waves per execution 1445 /// \returns Maximum number of SGPRs that meets number of waves per execution 1449 /// \returns Value that meets number of waves per execution unit requirement 1451 /// subtarget's specifications, or does not meet number of waves per execution [all …]
|
H A D | SIMemoryLegalizer.cpp | 1132 // not needed as LDS operations for all waves are executed in a total in insertWait() 1133 // global ordering as observed by all waves. Required if also in insertWait() 1154 // is not needed as GDS operations for all waves are executed in a total in insertWait() 1155 // global ordering as observed by all waves. Required if also in insertWait() 1310 // In threadgroup split mode the waves of a work-group can be executing on in enableLoadCacheBypass() 1312 // Otherwise in non-threadgroup split mode all waves of a work-group are in enableLoadCacheBypass() 1451 // In threadgroup split mode the waves of a work-group can be executing on in insertWait() 1453 // to complete to ensure they are visible to waves in the other CUs. in insertWait() 1454 // Otherwise in non-threadgroup split mode all waves of a work-group are on in insertWait() 1455 // the same CU, so no need to wait for global memory as all waves in the in insertWait() [all …]
|
H A D | AMDGPUSubtarget.cpp | 342 // allows the given function to achieve an occupancy of NWaves waves per 360 // Returns the maximum occupancy, in number of waves per SIMD / EU, that can 385 // Round to the number of waves per CU. in getOccupancyWithLocalMemSize() 389 // Number of waves per EU (SIMD). in getOccupancyWithLocalMemSize() 392 // Clamp to the maximum possible number of waves. in getOccupancyWithLocalMemSize() 450 // Default minimum/maximum number of waves per execution unit. in getEffectiveWavesPerEU() 455 // number of waves per execution unit to values implied by requested in getEffectiveWavesPerEU() 480 // Default minimum/maximum number of waves per execution unit. in getWavesPerEU() 483 // Requested minimum/maximum number of waves per execution unit. in getWavesPerEU() 485 AMDGPU::getIntegerPairAttribute(F, "amdgpu-waves-per-eu", Default, true); in getWavesPerEU() [all …]
|
H A D | SIProgramInfo.h | 76 // Number of SGPRs that meets number of waves per execution unit request. 79 // Number of VGPRs that meets number of waves per execution unit request.
|
H A D | R600Subtarget.h | 151 /// \returns Number of waves per execution unit required to support the given 158 /// \returns Minimum number of waves per execution unit supported by the
|
H A D | SIRegisterInfo.h | 410 /// Return all SGPR128 which satisfy the waves per execution unit requirement 414 /// Return all SGPR64 which satisfy the waves per execution unit requirement 418 /// Return all SGPR32 which satisfy the waves per execution unit requirement
|
H A D | AMDGPUPerfHintAnalysis.h | 11 /// kernel may benefit from limiting number of waves to reduce cache thrashing.
|
H A D | SIMachineFunctionInfo.h | 423 // A pair of default/requested minimum/maximum number of waves per execution 1038 /// \returns A pair of default/requested minimum/maximum number of waves per 1044 /// \returns Default/requested minimum number of waves per execution unit. 1049 /// \returns Default/requested maximum number of waves per execution unit.
|
H A D | AMDGPUMachineFunction.h | 67 // Kernel may need limited waves per EU for better performance.
|
H A D | AMDGPUSetWavePriority.cpp | 12 /// waves to issue their VMEM instructions as well.
|
H A D | AMDGPUAttributor.cpp | 181 /// Get the effective value of "amdgpu-waves-per-eu" for the function, 818 /// Propagate amdgpu-waves-per-eu attribute. 821 : AAAMDSizeRangeAttribute(IRP, A, "amdgpu-waves-per-eu") {} in AAAMDWavesPerEU()
|
H A D | AMDGPUAsmPrinter.cpp | 908 // number of waves per execution unit request. in getSIProgramInfo() 1088 AMDGPU::getIntegerPairAttribute(F, "amdgpu-waves-per-eu", {0, 0}, true); in getSIProgramInfo() 1093 "failed to meet occupancy target given by 'amdgpu-waves-per-eu' in " in getSIProgramInfo() 1534 EmitResourceUsageRemark("Occupancy", "Occupancy [waves/SIMD]", in emitResourceUsageRemarks()
|
H A D | GCNSchedStrategy.h | 122 /// maximum number of waves per simd).
|
H A D | AMDGPUPerfHintAnalysis.cpp | 11 /// kernel may benefit from limiting number of waves to reduce cache thrashing.
|
H A D | GCNSchedStrategy.cpp | 1047 // Allow memory bound functions to drop to 4 waves if not limited by an in checkScheduling() 1052 << MFI.getMinAllowedOccupancy() << " waves\n"); in checkScheduling()
|
H A D | AMDKernelCodeT.h | 333 /// apply to all waves of the grid. It is possible to specify more than 16 User
|
/freebsd/contrib/llvm-project/llvm/lib/Target/AMDGPU/Utils/ |
H A D | AMDGPUBaseInfo.h | 217 /// \returns Minimum number of waves per execution unit for given subtarget \p 221 /// \returns Maximum number of waves per execution unit for given subtarget \p 225 /// \returns Number of waves per execution unit required to support the given \p 236 /// \returns Number of waves per work group for given subtarget \p STI and 253 /// \returns Minimum number of SGPRs that meets the given number of waves per 257 /// \returns Maximum number of SGPRs that meets the given number of waves per 304 /// \returns Minimum number of VGPRs that meets given number of waves per 308 /// \returns Maximum number of VGPRs that meets given number of waves per 312 /// \returns Number of waves reachable for a given \p NumVGPRs usage for given 317 /// \returns Number of waves reachable for a given \p NumVGPRs usage, \p Granule
|
H A D | AMDGPUBaseInfo.cpp | 915 // "Per CU" really means "per whatever functional block the waves of a in getLocalMemorySize() 933 // "Per CU" really means "per whatever functional block the waves of a in getEUsPerCU()
|
/freebsd/sys/contrib/device-tree/Bindings/iio/proximity/ |
H A D | devantech-srf04.yaml | 48 Thus this GPIO is set while the ultrasonic waves are doing one round
|
/freebsd/contrib/llvm-project/clang/lib/CodeGen/Targets/ |
H A D | AMDGPU.cpp | 686 F->addFnAttr("amdgpu-waves-per-eu", AttrVal); in handleAMDGPUWavesPerEUAttr()
|
/freebsd/contrib/file/magic/Magdir/ |
H A D | games | 320 >4 ulelong 0x0000032d (Waves)
|
/freebsd/contrib/llvm-project/llvm/include/llvm/IR/ |
H A D | IntrinsicsAMDGPU.td | 2129 // bar_val is the total number of waves that will wait on this 2141 // bar_val is the total number of waves that will wait on this
|
/freebsd/contrib/llvm-project/clang/lib/CodeGen/ |
H A D | CodeGenModule.h | 1650 /// Emit the IR encoding to attach the AMD GPU waves-per-eu attribute to \p F.
|
/freebsd/contrib/llvm-project/clang/include/clang/Basic/ |
H A D | AttrDocs.td | 2702 ``<min>`` parameter specifies the requested minimum number of waves per EU, and 2703 *optional* ``<max>`` parameter specifies the requested maximum number of waves 2705 then there is no restriction on the maximum number of waves per EU other than
|