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/flat-for-global-subtarget-f...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

55 lines
2.2 KiB
LLVM
Raw Normal View History

AMDGPU: Enable code object v3 for AMDHSA only Differential Revision: https://reviews.llvm.org/D54186 llvm-svn: 346923
2018-11-15 10:32:43 +08:00
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-code-object-v3,+flat-for-global < %s | FileCheck -check-prefix=HSA -check-prefix=HSA-DEFAULT -check-prefix=ALL %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-code-object-v3,-flat-for-global < %s | FileCheck -check-prefix=HSA -check-prefix=HSA-NODEFAULT -check-prefix=ALL %s
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +08:00
; RUN: llc -mtriple=amdgcn-- -mcpu=tonga < %s | FileCheck -check-prefix=HSA-NOADDR64 -check-prefix=ALL %s
; RUN: llc -mtriple=amdgcn-- -mcpu=kaveri -mattr=-flat-for-global < %s | FileCheck -check-prefix=NOHSA-DEFAULT -check-prefix=ALL %s
; RUN: llc -mtriple=amdgcn-- -mcpu=kaveri -mattr=+flat-for-global < %s | FileCheck -check-prefix=NOHSA-NODEFAULT -check-prefix=ALL %s
; RUN: llc -mtriple=amdgcn-- -mcpu=tonga < %s | FileCheck -check-prefix=NOHSA-NOADDR64 -check-prefix=ALL %s
; There are no stack objects even though flat is used by default, so
; flat_scratch_init should be disabled.
; ALL-LABEL: {{^}}test:
; HSA: .amd_kernel_code_t
; HSA: enable_sgpr_flat_scratch_init = 0
; HSA: .end_amd_kernel_code_t
; ALL-NOT: flat_scr
; HSA-DEFAULT: flat_store_dword
; HSA-NODEFAULT: buffer_store_dword
; HSA-NOADDR64: flat_store_dword
; NOHSA-DEFAULT: buffer_store_dword
; NOHSA-NODEFAULT: flat_store_dword
; NOHSA-NOADDR64: flat_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling 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 actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test(i32 addrspace(1)* %out) {
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +08:00
entry:
store i32 0, i32 addrspace(1)* %out
ret void
}
; HSA-DEFAULT: flat_store_dword
; HSA-NODEFAULT: buffer_store_dword
; HSA-NOADDR64: flat_store_dword
; NOHSA-DEFAULT: buffer_store_dword
; NOHSA-NODEFAULT: flat_store_dword
; NOHSA-NOADDR64: flat_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling 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 actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_addr64(i32 addrspace(1)* %out) {
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +08:00
entry:
[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
%out.addr = alloca i32 addrspace(1)*, align 4, addrspace(5)
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +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
store i32 addrspace(1)* %out, i32 addrspace(1)* addrspace(5)* %out.addr, align 4
%ld0 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %out.addr, align 4
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +08:00
%arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %ld0, i32 0
store i32 1, i32 addrspace(1)* %arrayidx, align 4
[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
%ld1 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %out.addr, align 4
AMDGPU: Enable FeatureFlatForGlobal on Volcanic Islands Accomplishes what r292982 was supposed to, which ended up only really making the necessary test changes. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 293310
2017-01-28 01:42:26 +08:00
%arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %ld1, i32 1
store i32 2, i32 addrspace(1)* %arrayidx1, align 4
ret void
}