The maxSharedMemoryPerMultiProcessor attribute is meant to describe
the number of bytes of shared memory (LDS space in AMD terminology)
in each SM (CU in AMD terminology). For instance, on AMD GPUs this
is often 64KB per CU, and some Nvidia GPUs it's 96KB per SM.
This shared memory is a different address space from the normal
global memory. However, the current HIP-HCC properties fill this
in with a size that matches the totalGlboalMem property. This gives
a drastically too-high calculation for the amount of LDS space that
each CU has -- tens of GBs vs. 10s of KBs.
This patch fixes this by pulling the maxSharedMemoryPerMultiProcessor
property from the HSA pool that describes how much workgroup-local
space is available on each CU. The HSA runtime eventually pulls
this from the topology information about LDSSizeInKB, defined as
"Size of Local Data Store in Kilobytes per SIMD".
Previously, this HSA query was used to fill in the value of the
sharedMemPerBlock property. On today's AMD GPUs, we know that
the amount of LDS avaialble to the workgroup is identical to the
amount of LDS space in the CU. However, in the future this may
differ. As such, this patch changes around the order and fills
in the "PerMultiProcessor" property from the HSA query (since
what's what the query is defined to return), and then separately
fills in the "PerBlock" property as we know it.
[ROCm/clr commit: 44b16df84f]
* Use hipExtLaunchKernelGGL in dispatchlatency sample
* Let it run on NVCC path too
* Refactoring
* Add test_kernel source
* Remove ResultDB
* Remove error checks
[ROCm/clr commit: 8b8e4a66b4]
- Expand message when HIP version mismatch detected.
- Doc touchup.
- change sorting of hipBusBandwidth so byte results shown at top.
-
Change-Id: Ifb4e44a5fdfb65d59c4994b11e5f13385705f7e0
[ROCm/clr commit: 061bcc6a5c]
- Enable -O3 for hipDispatchLatency.
- Use nearly-null kernel to prevent it from being optimized away.
- Formatting for hipDispatchLatency.
- Formatting for hipInfo.
[ROCm/clr commit: e8beacbfb1]
- set USE_PEER_TO_PEER=3 (requires HCC "am_memtracker_update_peers")
- when enabling peer, turn it on for previously allocated memory.
- hipDeviceCanAccessPeer is no longer self-ware (self does not qualify
as a peer)
- device peerlist always includes self, so when we call allow_access
we never remove self access.
- hipDeviceReset() removes old peer mappings.
[ROCm/clr commit: 9e7efd7c65]
Note hipHostMalloc (not hipHostAlloc or hipMallocHost).
- the hipHost* is used for all HIP APIs dealing with Host memory.
(including hipHostMalloc, hipHostFree, hipHostRegister,
hipHostUnregister, hipHostGetFlags, hipHostGetDevicePointer).
- hipMallocHost is consistent with "hipMalloc" for allocating device
memory. Enumerations hipHostMalloc* also used as optional
flags parm to hipHostMalloc.
[ROCm/clr commit: 2d0fade1f7]
Joseph Greathouse
Rahul Garg
Sarbojit2019
chrispaquot
ansurya
Evgeny Mankov
Maneesh Gupta
Rahul Garg
Ben Sander
Aditya Atluri
Sandeep Kumar
Aditya Atluri