* Add alltoallv API and implementation
* Extend Rome P2P channel limit to multinode and alltoall kernels
* topo_expl: fix compilation and sync up with main
* gtest: use RCCL alltoallv API
* Code review changes
[ROCm/rccl commit: b871ea3c0c]
* Add alltoallv API and implementation
* Extend Rome P2P channel limit to multinode and alltoall kernels
* topo_expl: fix compilation and sync up with main
* gtest: use RCCL alltoallv API
* Code review changes
The static members __HIP_Coordinates::x, ::y and ::z must be defined
outside the class. Otherwise, linker throws `undefined reference error`
when these definitions are needed in the HIP application.
Change-Id: Iabc09744b478c22e4b13cf9824877ec9cfdd4f7a
[ROCm/clr commit: 9b6d26f8b2]
The static members __HIP_Coordinates::x, ::y and ::z must be defined
outside the class. Otherwise, linker throws `undefined reference error`
when these definitions are needed in the HIP application.
Change-Id: Iabc09744b478c22e4b13cf9824877ec9cfdd4f7a
The static members __HIP_Coordinates::x, ::y and ::z must be defined
outside the class. Otherwise, linker throws `undefined reference error`
when these definitions are needed in the HIP application.
Change-Id: Iabc09744b478c22e4b13cf9824877ec9cfdd4f7a
[ROCm/hip commit: b8640f1f0d]
The static members __HIP_Coordinates::x, ::y and ::z must be defined
outside the class. Otherwise, linker throws `undefined reference error`
when these definitions are needed in the HIP application.
Change-Id: Iabc09744b478c22e4b13cf9824877ec9cfdd4f7a
The queue control stack size cannot exceed 0x7000 on ASICs
gfx1010 through gfx1031. The lower limit is not achievable
with AQL so this should have no practical effect.
Fixes control stack size overflow on large ASICs.
Change-Id: Ib78cf6e4c5f096044bf8de24debe211689891caa
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
The queue control stack size cannot exceed 0x7000 on ASICs
gfx1010 through gfx1031. The lower limit is not achievable
with AQL so this should have no practical effect.
Fixes control stack size overflow on large ASICs.
Change-Id: Ib78cf6e4c5f096044bf8de24debe211689891caa
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
[ROCm/ROCR-Runtime commit: 44f80d170d]
The error checking macro IS_OPEN returns an hsa_signal_t.
This conflicts with the return type of uint32_t.
Add an assert and rely on spurious return rule to return zero
when rocr is not initialized.
Change-Id: Ifc9bb75e22ecdd675273de59b31e5026a69c62e0
The error checking macro IS_OPEN returns an hsa_signal_t.
This conflicts with the return type of uint32_t.
Add an assert and rely on spurious return rule to return zero
when rocr is not initialized.
Change-Id: Ifc9bb75e22ecdd675273de59b31e5026a69c62e0
[ROCm/ROCR-Runtime commit: a3c4aaf95a]
Chauncey Hui
Evgeny
Wenkai Du
Vladislav Sytchenko
mshivama
Sarbojit Sarkar
Julia Jiang
Chris Freehill
Jay Cornwall
Jatin Chaudhary
Sean Keely
nunnikri
Stanley Tsang
gilbertlee-amd