File: adjust-writemask-vectorized.ll

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-6~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 1,418,812 kB
  • sloc: cpp: 5,290,827; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,900; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,892; xml: 953; cs: 573; fortran: 539
file content (14 lines) | stat: -rw-r--r-- 733 bytes parent folder | download | duplicates (11) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
 
; RUN: llc -march=amdgcn -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s

; Check that write mask is 0xf.

; GCN-LABEL: {{^}}sample_2d_vectorized_use:
; GCN: image_sample v[{{[0-9:]+}}], v[{{[0-9:]+}}], s[{{[0-9:]+}}], s[{{[0-9:]+}}] dmask:0xf
define amdgpu_ps <4 x float> @sample_2d_vectorized_use(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s, float %t, <4 x float> %a) {
main_body:
  %v = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
  %r = fadd <4 x float> %v, %a
  ret <4 x float> %r
}

declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32)