dK = s (the sum), rows; dV^T, columns: element (key r + 8h, column
8 nt + 2 (lane % 4) + b) at (8 nt + b) seq + 8 h words past the thread's
2513def skEpilogue = (lambda unrestricted seq : Nat . (lambda unrestricted tail : (family SM86Program) .
2514 (saMovConst (skTmp 0) (saArgument 11)
2515 (saFor 32 (lambda unrestricted i : Nat .
2516 (saFmul (naturalAdd 116 i) (naturalAdd 116 i) (skTmp 0) (naturalSelect (naturalIsZero i) saWait3 saWaitNone)))
2517 (saWide skKeyGradientStorePointer saScratch saOne (saArgument 8)
2518 (saFor 16 (lambda unrestricted i : Nat .
2519 (let unrestricted nt = (naturalDivideUnchecked i 2) in (let unrestricted h = (naturalModuloUnchecked i 2) in
2520 (saOp (sbStore64 skKeyGradientStorePointer (saElem (skDK nt) h 0)
2521 (naturalAdd (naturalMultiply nt 32) (naturalMultiply h (naturalMultiply 8 (naturalMultiply saHeadWidth 4))))
2522 saWaitNone)))))
2523 -- dV^T's offset: head h's 64 x seq plane, the quad lane's first column,
2524 -- the key
2525 (saMovImm (skTmp 1) 0
2526 (saImad (skTmp 1) saQuadLane (naturalMultiply 8 seq) (skTmp 1)
2527 (saImad (skTmp 1) skHead (naturalMultiply saHeadWidth (naturalMultiply seq 4)) (skTmp 1)
2528 (saImad (skTmp 1) skRow 4 (skTmp 1)
2529 (saWide saPointer (skTmp 1) saOne (saArgument 9)
2530 (saFor 32 (lambda unrestricted i : Nat .
2531 (let unrestricted nt = (naturalDivideUnchecked i 4) in (let unrestricted h = (naturalDivideUnchecked (naturalModuloUnchecked i 4) 2) in
2532 (let unrestricted b = (naturalModuloUnchecked i 2) in
2533 (saOp (saStore saPointer (saElem (skDV nt) h b)
2534 (naturalAdd (naturalMultiply (naturalAdd (naturalMultiply 8 nt) b) (naturalMultiply seq 4)) (naturalMultiply h 32))
2535 saWaitNone))))))
2536 tail))))))))))))The compiler supplied declaration spans and resolved links from this source snapshot. This page does not assert that this file belongs to a checked closure.