more bugs

parent 4ca3de72
...@@ -77,7 +77,7 @@ function Dw!(so, U, si, dpar::DiracParam, lp::SpaceParm{4,6,B,D}, ymws = "ymws", ...@@ -77,7 +77,7 @@ function Dw!(so, U, si, dpar::DiracParam, lp::SpaceParm{4,6,B,D}, ymws = "ymws",
z1 = exp(2im * pi * lp.ntw[i]/gp.ng) z1 = exp(2im * pi * lp.ntw[i]/gp.ng)
z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng) z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng)
CUDA.@sync begin CUDA.@sync begin
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i, z1, z2, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i+1, z1, z2, lp)
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{lp.npls-i+8}, si, dpar.csw, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{lp.npls-i+8}, si, dpar.csw, lp)
end end
end end
...@@ -115,7 +115,7 @@ function DwdagDw!(so, U, si, dpar::DiracParam, st, lp::SpaceParm{4,6,B,D}, ymws ...@@ -115,7 +115,7 @@ function DwdagDw!(so, U, si, dpar::DiracParam, st, lp::SpaceParm{4,6,B,D}, ymws
z1 = exp(2im * pi * lp.ntw[i]/gp.ng) z1 = exp(2im * pi * lp.ntw[i]/gp.ng)
z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng) z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng)
CUDA.@sync begin CUDA.@sync begin
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i, z1, z2, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i+1, z1, z2, lp)
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(st, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, si, dpar.csw, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(st, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, si, dpar.csw, lp)
end end
end end
...@@ -137,7 +137,7 @@ function DwdagDw!(so, U, si, dpar::DiracParam, st, lp::SpaceParm{4,6,B,D}, ymws ...@@ -137,7 +137,7 @@ function DwdagDw!(so, U, si, dpar::DiracParam, st, lp::SpaceParm{4,6,B,D}, ymws
z1 = exp(2im * pi * lp.ntw[i]/gp.ng) z1 = exp(2im * pi * lp.ntw[i]/gp.ng)
z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng) z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng)
CUDA.@sync begin CUDA.@sync begin
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i, z1, z2, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i+1, z1, z2, lp)
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, st, dpar.csw, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, st, dpar.csw, lp)
end end
end end
...@@ -198,7 +198,7 @@ function g5Dw!(so, U, si, dpar, lp::SpaceParm{4,6,B,D}, ymws = "ymws", gp = "gp" ...@@ -198,7 +198,7 @@ function g5Dw!(so, U, si, dpar, lp::SpaceParm{4,6,B,D}, ymws = "ymws", gp = "gp"
z1 = exp(2im * pi * lp.ntw[i]/gp.ng) z1 = exp(2im * pi * lp.ntw[i]/gp.ng)
z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng) z2 = exp(2im * pi * lp.ntw[lp.npls-i]/gp.ng)
CUDA.@sync begin CUDA.@sync begin
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i, z1, z2, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_field_tensor!(ymws.frc1, ymws.frc2, U, gp.Ubnd, i, lp.npls-i+1, z1, z2, lp)
CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, si, dpar.csw, lp) CUDA.@cuda threads=lp.bsz blocks=lp.rsz krnl_g5Dw_impr!(so, ymws.frc1, ymws.frc2, Gamma{i+9}, Gamma{i+12}, si, dpar.csw, lp)
end end
end end
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment