Files
clang-p2996/llvm/test/Analysis/DivergenceAnalysis/AMDGPU/kernel-args.ll
Nicolai Haehnle 56d0ed2a50 [DA] GPUDivergenceAnalysis for unstructured GPU kernels
Summary:
This is patch #3 of the new DivergenceAnalysis

  <https://lists.llvm.org/pipermail/llvm-dev/2018-May/123606.html>

The GPUDivergenceAnalysis is intended to eventually supersede the existing
LegacyDivergenceAnalysis. The existing LegacyDivergenceAnalysis produces
incorrect results on unstructured Control-Flow Graphs:

  <https://bugs.llvm.org/show_bug.cgi?id=37185>

This patch adds the option -use-gpu-divergence-analysis to the
LegacyDivergenceAnalysis to turn it into a transparent wrapper for the
GPUDivergenceAnalysis.

Reviewers: nhaehnle

Reviewed By: nhaehnle

Subscribers: jholewinski, jvesely, jfb, llvm-commits, alex-t, sameerds, arsenm, nhaehnle

Differential Revision: https://reviews.llvm.org/D53493

llvm-svn: 348048
2018-11-30 22:55:20 +00:00

42 lines
1.4 KiB
LLVM

; RUN: opt %s -mtriple amdgcn-- -analyze -divergence -use-gpu-divergence-analysis | FileCheck %s
; CHECK-LABEL: Printing analysis 'Legacy Divergence Analysis' for function 'test_amdgpu_ps':
; CHECK: DIVERGENT:
; CHECK-NOT: %arg0
; CHECK-NOT: %arg1
; CHECK-NOT: %arg2
; CHECK: <2 x i32> %arg3
; CHECK: DIVERGENT: <3 x i32> %arg4
; CHECK: DIVERGENT: float %arg5
; CHECK: DIVERGENT: i32 %arg6
define amdgpu_ps void @test_amdgpu_ps([4 x <16 x i8>] addrspace(2)* byval %arg0, float inreg %arg1, i32 inreg %arg2, <2 x i32> %arg3, <3 x i32> %arg4, float %arg5, i32 %arg6) #0 {
ret void
}
; CHECK-LABEL: Printing analysis 'Legacy Divergence Analysis' for function 'test_amdgpu_kernel':
; CHECK-NOT: %arg0
; CHECK-NOT: %arg1
; CHECK-NOT: %arg2
; CHECK-NOT: %arg3
; CHECK-NOT: %arg4
; CHECK-NOT: %arg5
; CHECK-NOT: %arg6
define amdgpu_kernel void @test_amdgpu_kernel([4 x <16 x i8>] addrspace(2)* byval %arg0, float inreg %arg1, i32 inreg %arg2, <2 x i32> %arg3, <3 x i32> %arg4, float %arg5, i32 %arg6) #0 {
ret void
}
; CHECK-LABEL: Printing analysis 'Legacy Divergence Analysis' for function 'test_c':
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
; CHECK: DIVERGENT:
define void @test_c([4 x <16 x i8>] addrspace(2)* byval %arg0, float inreg %arg1, i32 inreg %arg2, <2 x i32> %arg3, <3 x i32> %arg4, float %arg5, i32 %arg6) #0 {
ret void
}
attributes #0 = { nounwind }