Versions in this module Expand all Collapse all v1 v1.3.1 Jul 21, 2026 v1.3.0 Jul 20, 2026 Changes in this version + var UseGemmScratch = true + func AddBiasLastDim(outDev, biasDev DevicePtr, totalElems, lastDim int) error + func AppMemFromBaseline(current MemStats) (appUsed, appFree uint64, ok bool) + func ClearScratch() + func DeviceDownloadF32(p DevicePtr, data []float32, elemOff, nElems int) error + func DeviceDownloadSlice(dev DevicePtr, data []float32, hostOff, n int) error + func DeviceFree(p DevicePtr) + func DeviceMemLine() string + func DeviceMemset(p DevicePtr, nElems int) + func DeviceMemsetAt(p DevicePtr, elemOff, nElems int) + func DeviceUploadF32(p DevicePtr, data []float32, elemOff, nElems int) error + func DeviceUploadSlice(dev DevicePtr, data []float32, hostOff, n int) error + func GemmDevice(aDev, bDev, cDev DevicePtr, M, N, K int) error + func GemmDeviceAt(aDev, bDev, cDev DevicePtr, aOff, bOff, cOff, M, N, K int) error + func GemmF32(A, B, C []float32, M, N, K int) error + func GemmStridedBatchedAt(aDev, bDev, cDev DevicePtr, aOff, bOff, cOff, M, N, K, batchCount int) error + func Init() error + func RecordMemBaseline() + func Shutdown() + type DevicePtr uintptr + func DeviceAlloc(nElems int) (DevicePtr, error) + func PtrAt(p DevicePtr, elemOff int) DevicePtr + func ScratchGemmOp(which, nElems int) (DevicePtr, error) + func ScratchGemmOut(nElems int) (DevicePtr, error) + type MemStats struct + Total uint64 + Used uint64 + func DeviceMemStats() (MemStats, bool) + func (m MemStats) Free() uint64 + func (m MemStats) Ok() bool + type TimingStats struct + AllocWait time.Duration + D2H time.Duration + Gemm time.Duration + H2D time.Duration + OOM uint64 + func SnapshotTimings() TimingStats + func (s TimingStats) Delta(base TimingStats) TimingStats
Go to main page