File: hidden_diverge.ll

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 995,808 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (30 lines) | stat: -rw-r--r-- 996 bytes parent folder | download | duplicates (4) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
 
; RUN: opt %s -analyze -divergence -use-gpu-divergence-analysis | FileCheck %s

target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
target triple = "nvptx64-nvidia-cuda"

define i32 @hidden_diverge(i32 %n, i32 %a, i32 %b) {
; CHECK-LABEL: Printing analysis 'Legacy Divergence Analysis' for function 'hidden_diverge'
entry:
  %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
  %cond.var = icmp slt i32 %tid, 0
  br i1 %cond.var, label %B, label %C ; divergent
; CHECK: DIVERGENT: br i1 %cond.var,
B:
  %cond.uni = icmp slt i32 %n, 0
  br i1 %cond.uni, label %C, label %merge ; uniform
; CHECK-NOT: DIVERGENT: br i1 %cond.uni,
C:
  %phi.var.hidden = phi i32 [ 1, %entry ], [ 2, %B  ]
; CHECK: DIVERGENT: %phi.var.hidden = phi i32
  br label %merge
merge:
  %phi.ipd = phi i32 [ %a, %B ], [ %b, %C ]
; CHECK: DIVERGENT: %phi.ipd = phi i32
  ret i32 %phi.ipd
}

declare i32 @llvm.nvvm.read.ptx.sreg.tid.x()

!nvvm.annotations = !{!0}
!0 = !{i32 (i32, i32, i32)* @hidden_diverge, !"kernel", i32 1}