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/uniform-loop-inside-nonunif...

70 lines
1.7 KiB
LLVM
Raw Normal View History

AMDGPU: Handle cbranch vccz/vccnz llvm-svn: 270297
2016-05-21 08:29:40 +08:00
; RUN: llc -march=amdgcn -mcpu=verde < %s | FileCheck %s
AMDGPU: Prevent uniform loops from becoming infinite Summary: Uniform loops where the branch leaving the loop is predicated on VCCNZ must be skipped if EXEC = 0, otherwise they will be infinite. Reviewers: tstellarAMD, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18137 llvm-svn: 263658
2016-03-17 04:14:33 +08:00
; Test a simple uniform loop that lives inside non-uniform control flow.
AMDGPU: Handle cbranch vccz/vccnz llvm-svn: 270297
2016-05-21 08:29:40 +08:00
; CHECK-LABEL: {{^}}test1:
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. llvm-svn: 282832
2016-09-30 09:50:20 +08:00
; CHECK: v_cmp_ne_u32_e32 vcc, 0
AMDGPU: Handle cbranch vccz/vccnz llvm-svn: 270297
2016-05-21 08:29:40 +08:00
; CHECK: s_and_saveexec_b64
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
; CHECK-NEXT: ; mask branch
[AMDGPU] Revert b0efc4fd6 (https://reviews.llvm.org/D40556) llvm-svn: 330818
2018-04-25 20:32:46 +08:00
; CHECK-NEXT: s_cbranch_execz BB{{[0-9]+_[0-9]+}}
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
; CHECK-NEXT: BB{{[0-9]+_[0-9]+}}: ; %loop_body.preheader
AMDGPU: Handle cbranch vccz/vccnz llvm-svn: 270297
2016-05-21 08:29:40 +08:00
; CHECK: [[LOOP_BODY_LABEL:BB[0-9]+_[0-9]+]]:
[AMDGPU] Revert b0efc4fd6 (https://reviews.llvm.org/D40556) llvm-svn: 330818
2018-04-25 20:32:46 +08:00
; CHECK: s_cbranch_vccz [[LOOP_BODY_LABEL]]
AMDGPU: Handle cbranch vccz/vccnz llvm-svn: 270297
2016-05-21 08:29:40 +08:00
; CHECK: s_endpgm
AMDGPU: Add a shader calling convention This makes it possible to distinguish between mesa shaders and other kernels even in the presence of compute shaders. Patch By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Differential Revision: http://reviews.llvm.org/D18559 llvm-svn: 265589
2016-04-07 03:40:20 +08:00
define amdgpu_ps void @test1(<8 x i32> inreg %rsrc, <2 x i32> %addr.base, i32 %y, i32 %p) {
AMDGPU: Prevent uniform loops from becoming infinite Summary: Uniform loops where the branch leaving the loop is predicated on VCCNZ must be skipped if EXEC = 0, otherwise they will be infinite. Reviewers: tstellarAMD, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18137 llvm-svn: 263658
2016-03-17 04:14:33 +08:00
main_body:
%cc = icmp eq i32 %p, 0
br i1 %cc, label %out, label %loop_body
loop_body:
%counter = phi i32 [ 0, %main_body ], [ %incr, %loop_body ]
; Prevent the loop from being optimized out
call void asm sideeffect "", "" ()
%incr = add i32 %counter, 1
%lc = icmp sge i32 %incr, 1000
br i1 %lc, label %out, label %loop_body
out:
ret void
}
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
; CHECK-LABEL: {{^}}test2:
; CHECK: s_and_saveexec_b64
; CHECK-NEXT: ; mask branch
[AMDGPU] Revert b0efc4fd6 (https://reviews.llvm.org/D40556) llvm-svn: 330818
2018-04-25 20:32:46 +08:00
; CHECK-NEXT: s_cbranch_execz
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 @test2(i32 addrspace(1)* %out, i32 %a, i32 %b) {
AMDGPU/SI: Fix threshold calculation for branching when exec is zero Summary: When control flow is implemented using the exec mask, the compiler will insert branch instructions to skip over the masked section when exec is zero if the section contains more than a certain number of instructions. The previous code would only count instructions in successor blocks, and this patch modifies the code to start counting instructions in all blocks between the start and end of the branch. Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18282 llvm-svn: 263969
2016-03-22 02:56:58 +08:00
main_body:
%tid = call i32 @llvm.amdgcn.workitem.id.x() #1
%cc = icmp eq i32 %tid, 0
br i1 %cc, label %done1, label %if
if:
%cmp = icmp eq i32 %a, 0
br i1 %cmp, label %done0, label %loop_body
loop_body:
%counter = phi i32 [ 0, %if ], [0, %done0], [ %incr, %loop_body ]
; Prevent the loop from being optimized out
call void asm sideeffect "", "" ()
%incr = add i32 %counter, 1
%lc = icmp sge i32 %incr, 1000
br i1 %lc, label %done1, label %loop_body
done0:
%cmp0 = icmp eq i32 %b, 0
br i1 %cmp0, label %done1, label %loop_body
done1:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
AMDGPU: Prevent uniform loops from becoming infinite Summary: Uniform loops where the branch leaving the loop is predicated on VCCNZ must be skipped if EXEC = 0, otherwise they will be infinite. Reviewers: tstellarAMD, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18137 llvm-svn: 263658
2016-03-17 04:14:33 +08:00
attributes #1 = { nounwind readonly }