File: gv-offset-folding.ll

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (21 lines) | stat: -rw-r--r-- 858 bytes parent folder | download | duplicates (14) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
 
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -relocation-model=static < %s | FileCheck %s

@lds = external addrspace(3) global [4 x i32]

; Function Attrs: nounwind

; Offset folding is an optimization done for global variables with relocations,
; which allows you to store the offset in the r_addend of the relocation entry.
; The offset is apllied to the variables address at link time, which eliminates
; the need to emit shader instructions to do this calculation.
; We don't use relocations for local memory, so we should never fold offsets
; for local memory globals.

; CHECK-LABEL: lds_no_offset:
; CHECK: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:4
define amdgpu_kernel void @lds_no_offset() {
entry:
  %ptr = getelementptr [4 x i32], ptr addrspace(3) @lds, i32 0, i32 1
  store i32 0, ptr addrspace(3) %ptr
  ret void
}