File: llvm.r600.dot4.ll

package info (click to toggle)
llvm-toolchain-17 1%3A17.0.6-22
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,799,624 kB
  • sloc: cpp: 6,428,607; ansic: 1,383,196; asm: 793,408; python: 223,504; objc: 75,364; f90: 60,502; lisp: 33,869; pascal: 15,282; sh: 9,684; perl: 7,453; ml: 4,937; awk: 3,523; makefile: 2,889; javascript: 2,149; xml: 888; fortran: 619; cs: 573
file content (11 lines) | stat: -rw-r--r-- 524 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s

declare float @llvm.r600.dot4(<4 x float>, <4 x float>) nounwind readnone

define amdgpu_kernel void @test_dp4(ptr addrspace(1) %out, ptr addrspace(1) %a, ptr addrspace(1) %b) nounwind {
  %src0 = load <4 x float>, ptr addrspace(1) %a, align 16
  %src1 = load <4 x float>, ptr addrspace(1) %b, align 16
  %dp4 = call float @llvm.r600.dot4(<4 x float> %src0, <4 x float> %src1) nounwind readnone
  store float %dp4, ptr addrspace(1) %out, align 4
  ret void
}