en Copyright 2015 Java http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#df29ec2f AMDGPU: Select i8/i16 global and flat atomic load/storeAs far as I know these should be atomic anyway, as long as the addressis aligned. Unaligned atomics hit an ugly error in AtomicExpand. List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Tue, 12 Apr 2022 22:10:02 +0000 Matt Arsenault <Matthew.Arsenault@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#4cef9812 AMDGPU: Add some missing atomics testsWe had no FP atomic load/store coverage. List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Sun, 26 Apr 2020 15:11:43 +0000 Matt Arsenault <Matthew.Arsenault@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#0cb08e44 Allow FP types for atomicrmw xchgllvm-svn: 351427 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Thu, 17 Jan 2019 10:49:01 +0000 Matt Arsenault <Matthew.Arsenault@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#2a22c5de [AMDGPU] Switch to the new addr space mapping by defaultThis requires corresponding clang change.Differential Revision: https://reviews.llvm.org/D40955llvm-svn: 324101 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Fri, 02 Feb 2018 16:07:16 +0000 Yaxun Liu <Yaxun.Liu@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#e9a5a77e AMDGPU: Implement memory modelllvm-svn: 308781 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Fri, 21 Jul 2017 21:19:23 +0000 Konstantin Zhuravlyov <kzhuravl_dev@outlook.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#db7c6a87 AMDGPU: Start selecting flat instruction offsetsllvm-svn: 305201 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Mon, 12 Jun 2017 16:53:51 +0000 Matt Arsenault <Matthew.Arsenault@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#3dbeefa9 AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernelCurrently the default C calling convention functions are treatedthe same as compute kernels. Make this explicit so the defaultcalling convention can be changed to a non-kernel.Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'on the relevant test directories (and undoing in one place that actuallywanted a non-kernel).llvm-svn: 298444 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Tue, 21 Mar 2017 21:39:51 +0000 Matt Arsenault <Matthew.Arsenault@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#79da2a76 [AMDGPU] Remove getBidirectionalReasonRankThis method inverts the Reason field of a scheduling candidate.It does right comparison between RegCritical and RegExcess, buteverything else is broken. In fact it can prefer less strong reasonsuch as Weak over RegCritical because Weak > -RegCritical.The CandReason enum is properly sorted, so just remove artificialranking.Differential Revision: https://reviews.llvm.org/D30557llvm-svn: 297536 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Sat, 11 Mar 2017 00:29:27 +0000 Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll#7757c59e AMDGPU: Fix flat atomicsThe flat atomics could already be selected, but onlywhen using flat instructions for global memory. Addpatterns for flat addresses.llvm-svn: 272345 List of files: /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/flat_atomics.ll Thu, 09 Jun 2016 23:42:54 +0000 Matt Arsenault <Matthew.Arsenault@amd.com>