Bugzilla – Attachment 547 Details for
Bug 945
error C4789 (Visual Studio)
Home
|
New
|
Browse
|
Search
|
[?]
|
Reports
|
Requests
|
Help
|
Log In
[x]
|
Forgot Password
Login:
[x]
This bugzilla service is closed. All entries have been migrated to
https://gitlab.com/libeigen/eigen
[patch]
workaround
vs_workaround.diff (text/plain), 1.74 KB, created by
Gael Guennebaud
on 2015-02-17 17:32:19 UTC
(
hide
)
Description:
workaround
Filename:
MIME Type:
Creator:
Gael Guennebaud
Created:
2015-02-17 17:32:19 UTC
Size:
1.74 KB
patch
obsolete
>diff --git a/Eigen/src/Core/products/GeneralBlockPanelKernel.h b/Eigen/src/Core/products/GeneralBlockPanelKernel.h >--- a/Eigen/src/Core/products/GeneralBlockPanelKernel.h >+++ b/Eigen/src/Core/products/GeneralBlockPanelKernel.h >@@ -1740,24 +1740,24 @@ EIGEN_DONT_INLINE void gemm_pack_rhs<Sca > const Scalar* b3 = &rhs[(j2+3)*rhsStride]; > > Index k=0; > if((PacketSize%4)==0) // TODO enbale vectorized transposition for PacketSize==2 ?? > { > for(; k<peeled_k; k+=PacketSize) { > PacketBlock<Packet,(PacketSize%4)==0?4:PacketSize> kernel; > kernel.packet[0] = ploadu<Packet>(&b0[k]); >- kernel.packet[1] = ploadu<Packet>(&b1[k]); >- kernel.packet[2] = ploadu<Packet>(&b2[k]); >- kernel.packet[3] = ploadu<Packet>(&b3[k]); >+ kernel.packet[1%PacketSize] = ploadu<Packet>(&b1[k]); >+ kernel.packet[2%PacketSize] = ploadu<Packet>(&b2[k]); >+ kernel.packet[3%PacketSize] = ploadu<Packet>(&b3[k]); > ptranspose(kernel); > pstoreu(blockB+count+0*PacketSize, cj.pconj(kernel.packet[0])); >- pstoreu(blockB+count+1*PacketSize, cj.pconj(kernel.packet[1])); >- pstoreu(blockB+count+2*PacketSize, cj.pconj(kernel.packet[2])); >- pstoreu(blockB+count+3*PacketSize, cj.pconj(kernel.packet[3])); >+ pstoreu(blockB+count+1*PacketSize, cj.pconj(kernel.packet[1%PacketSize])); >+ pstoreu(blockB+count+2*PacketSize, cj.pconj(kernel.packet[2%PacketSize])); >+ pstoreu(blockB+count+3*PacketSize, cj.pconj(kernel.packet[3%PacketSize])); > count+=4*PacketSize; > } > } > for(; k<depth; k++) > { > blockB[count+0] = cj(b0[k]); > blockB[count+1] = cj(b1[k]); > blockB[count+2] = cj(b2[k]);
You cannot view the attachment while viewing its details because your browser does not support IFRAMEs.
View the attachment on a separate page
.
View Attachment As Diff
View Attachment As Raw
Actions:
View
|
Diff
Attachments on
bug 945
: 547