File: extload-align.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 (24 lines) | stat: -rw-r--r-- 1,203 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
; RUN: llc -debug-only=machine-scheduler -march=amdgcn -mtriple=amdgcn-- -verify-machineinstrs %s -o - 2>&1| FileCheck -check-prefix=SI-NOHSA -check-prefix=FUNC -check-prefix=DEBUG %s
target datalayout = "A5"
; REQUIRES: asserts

; Verify that the extload generated from %eval has the default
; alignment size (2) corresponding to the underlying memory size (i16)
; size and not 4 corresponding to the sign-extended size (i32).

; DEBUG: {{^}}# Machine code for function extload_align:
; DEBUG: (volatile load 2 from %ir.a, addrspace 5)
; DEBUG: {{^}}# End machine code for function extload_align.

define amdgpu_kernel void @extload_align(i32 addrspace(5)* %out, i32 %index) #0 {
  %v0 = alloca [4 x i16], addrspace(5)
  %a1 = getelementptr inbounds [4 x i16], [4 x i16] addrspace(5)* %v0, i32 0, i32 0
  %a2 = getelementptr inbounds [4 x i16], [4 x i16] addrspace(5)* %v0, i32 0, i32 1
  store volatile i16 0, i16 addrspace(5)* %a1
  store volatile i16 1, i16 addrspace(5)* %a2
  %a = getelementptr inbounds [4 x i16], [4 x i16] addrspace(5)* %v0, i32 0, i32 %index
  %val = load volatile i16, i16 addrspace(5)* %a
  %eval = sext i16 %val to i32
  store i32 %eval, i32 addrspace(5)* %out
  ret void
}