1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/AMDGPU/llvm.amdgcn.readlane.ll
Changpeng Fang 351c66ab91 AMDGCN/SI: Implement readlane/readfirstlane intrinsics
Summary:
  This patch implements readlane/readfirstlane intrinsics.
TODO: need to define a new register class to consider the case
that the source could be a vector register or M0.

Reviewed by:
  arsenm and tstellarAMD

Differential Revision:
  http://reviews.llvm.org/D22489

llvm-svn: 279660
2016-08-24 20:35:23 +00:00

44 lines
1.6 KiB
LLVM

; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
declare i32 @llvm.amdgcn.readlane(i32, i32) #0
; CHECK-LABEL: {{^}}test_readlane_sreg:
; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, s{{[0-9]+}}
define void @test_readlane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
%readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_readlane_imm_sreg:
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
define void @test_readlane_imm_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
%readlane = call i32 @llvm.amdgcn.readlane(i32 32, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
; TODO: m0 should be folded.
; CHECK-LABEL: {{^}}test_readlane_m0_sreg:
; CHECK: s_mov_b32 m0, -1
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
define void @test_readlane_m0_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
%m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
%readlane = call i32 @llvm.amdgcn.readlane(i32 %m0, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_readlane_imm:
; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, 32
define void @test_readlane_imm(i32 addrspace(1)* %out, i32 %src0) #1 {
%readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 32) #0
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind }