maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll

53 lines
1.6 KiB
LLVM
Raw Normal View History

[AMDGPU] Add AMDGPUAliasAnalysis to opt pipeline Previously it was added only to the BE. Differential Revision: https://reviews.llvm.org/D31323 llvm-svn: 298721
2017-03-25 02:01:14 +08:00
; RUN: opt -mtriple=amdgcn-- -O3 -aa-eval -print-all-alias-modref-info -disable-output < %s 2>&1 | FileCheck %s
AMDGPU/R600: Fix amdgpu alias analysis pass. R600 uses higher AS number to access kernel parameters Fixes: r298846 Differential Revision: https://reviews.llvm.org/D31520 llvm-svn: 299245
2017-04-01 03:26:23 +08:00
; RUN: opt -mtriple=r600-- -O3 -aa-eval -print-all-alias-modref-info -disable-output < %s 2>&1 | FileCheck %s
[AMDGPU] Add AMDGPUAliasAnalysis to opt pipeline Previously it was added only to the BE. Differential Revision: https://reviews.llvm.org/D31323 llvm-svn: 298721
2017-03-25 02:01:14 +08:00
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
; CHECK: NoAlias: i8 addrspace(1)* %p1, i8 addrspace(5)* %p
[AMDGPU] Add AMDGPUAliasAnalysis to opt pipeline Previously it was added only to the BE. Differential Revision: https://reviews.llvm.org/D31323 llvm-svn: 298721
2017-03-25 02:01:14 +08:00
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
define void @test(i8 addrspace(5)* %p, i8 addrspace(1)* %p1) {
[AMDGPU] Add AMDGPUAliasAnalysis to opt pipeline Previously it was added only to the BE. Differential Revision: https://reviews.llvm.org/D31323 llvm-svn: 298721
2017-03-25 02:01:14 +08:00
ret void
}
AMDGPU: fix existing alias rules for constant and global Constant and global may alias, also one rules table wasn't ordered correctly. Pinpointed by Matt. v2: add a test with swapped parameters llvm-svn: 340416
2018-08-23 00:08:43 +08:00
; CHECK: MayAlias: i8 addrspace(1)* %p1, i8 addrspace(4)* %p
define void @test_constant_vs_global(i8 addrspace(4)* %p, i8 addrspace(1)* %p1) {
ret void
}
; CHECK: MayAlias: i8 addrspace(1)* %p, i8 addrspace(4)* %p1
define void @test_global_vs_constant(i8 addrspace(1)* %p, i8 addrspace(4)* %p1) {
ret void
}
AMDGPU: bump AS.MAX_COMMON_ADDRESS to 6 since 32-bit addr space 32-bit constant address space is declared as 6, so the maximum number of address spaces is 6, not 5. Fixes "LLVM ERROR: Pointer address space out of range". v5: rename MAX_COMMON_ADDRESS to MAX_AMDGPU_ADDRESS v4: - fix compilation issues - fix out of bounds access v3: use static_assert() v2: add a very simple test for 32-bit addr space Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106630 llvm-svn: 340417
2018-08-23 00:08:48 +08:00
; CHECK: MayAlias: i8 addrspace(1)* %p1, i8 addrspace(6)* %p
define void @test_constant_32bit_vs_global(i8 addrspace(6)* %p, i8 addrspace(1)* %p1) {
ret void
}
; CHECK: MayAlias: i8 addrspace(4)* %p1, i8 addrspace(6)* %p
define void @test_constant_32bit_vs_constant(i8 addrspace(6)* %p, i8 addrspace(4)* %p1) {
ret void
}
AMDGPU: Don't error on out of bounds address spaces We should never abort on valid IR. The most reasonable interpretation of an arbitrary address space pointer is probably some kind of special subset of global memory. llvm-svn: 341894
2018-09-11 12:00:41 +08:00
; CHECK: MayAlias: i8 addrspace(999)* %p0, i8* %p
define void @test_0_999(i8 addrspace(0)* %p, i8 addrspace(999)* %p0) {
ret void
}
; CHECK: MayAlias: i8 addrspace(999)* %p, i8* %p1
define void @test_999_0(i8 addrspace(999)* %p, i8 addrspace(0)* %p1) {
ret void
}
; CHECK: MayAlias: i8 addrspace(1)* %p, i8 addrspace(999)* %p1
define void @test_1_999(i8 addrspace(1)* %p, i8 addrspace(999)* %p1) {
ret void
}
; CHECK: MayAlias: i8 addrspace(1)* %p1, i8 addrspace(999)* %p
define void @test_999_1(i8 addrspace(999)* %p, i8 addrspace(1)* %p1) {
ret void
}