11bf7da64a
The GPUDivergenceAnalysis is now renamed to just "DivergenceAnalysis" since there is no conflict with LegacyDivergenceAnalysis. In the legacy PM, this analysis can only be used through the legacy DA serving as a wrapper. It is now made available as a pass in the new PM, and has no relation with the legacy DA. The new DA currently cannot handle irreducible control flow; its presence can cause the analysis to run indefinitely. The analysis is now modified to detect this and report all instructions in the function as divergent. This is super conservative, but allows the analysis to be used without hanging the compiler. Reviewed By: aeubanks Differential Revision: https://reviews.llvm.org/D96615
19 lines
746 B
LLVM
19 lines
746 B
LLVM
; RUN: opt %s -mtriple amdgcn-- -enable-new-pm=0 -analyze -divergence -use-gpu-divergence-analysis | FileCheck %s
|
|
; RUN: opt -mtriple amdgcn-- -passes='print<divergence>' -disable-output %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: DIVERGENT: %tmp = cmpxchg volatile
|
|
define amdgpu_kernel void @unreachable_loop(i32 %tidx) #0 {
|
|
entry:
|
|
unreachable
|
|
|
|
unreachable_loop: ; preds = %do.body.i, %if.then11
|
|
%tmp = cmpxchg volatile i32 addrspace(1)* null, i32 0, i32 0 seq_cst seq_cst
|
|
%cmp.i = extractvalue { i32, i1 } %tmp, 1
|
|
br i1 %cmp.i, label %unreachable_loop, label %end
|
|
|
|
end: ; preds = %do.body.i51, %atomicAdd_g_f.exit
|
|
unreachable
|
|
}
|
|
|
|
attributes #0 = { norecurse nounwind }
|