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
38 lines
1.3 KiB
LLVM
38 lines
1.3 KiB
LLVM
; RUN: opt -mtriple amdgcn-unknown-amdhsa -enable-new-pm=0 -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
|
|
; RUN: opt -mtriple amdgcn-unknown-amdhsa -passes='print<divergence>' -disable-output %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: bb3:
|
|
; CHECK: DIVERGENT: %Guard.bb4 = phi i1 [ true, %bb1 ], [ false, %bb2 ]
|
|
; CHECK: DIVERGENT: br i1 %Guard.bb4, label %bb4, label %bb5
|
|
|
|
; Function Attrs: nounwind readnone speculatable
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
define protected amdgpu_kernel void @test() {
|
|
bb0:
|
|
%tid.x = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%i5 = icmp eq i32 %tid.x, -1
|
|
br label %bb1
|
|
|
|
bb1: ; preds = %bb2, %bb0
|
|
%lsr.iv = phi i32 [ 7, %bb0 ], [ %lsr.iv.next, %bb2 ]
|
|
br i1 %i5, label %bb2, label %bb3
|
|
|
|
bb2: ; preds = %bb1
|
|
%lsr.iv.next = add nsw i32 %lsr.iv, -1
|
|
%i14 = icmp eq i32 %lsr.iv.next, 0
|
|
br i1 %i14, label %bb3, label %bb1
|
|
|
|
bb3: ; preds = %bb2, %bb1
|
|
%Guard.bb4 = phi i1 [ true, %bb1 ], [ false, %bb2 ]
|
|
br i1 %Guard.bb4, label %bb4, label %bb5
|
|
|
|
bb4: ; preds = %bb3
|
|
br label %bb5
|
|
|
|
bb5: ; preds = %bb3, %bb4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone speculatable }
|