1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/AMDGPU/promote-alloca-globals.ll
Nicolai Haehnle 216a9fc9a1 AMDGPU: Write LDS objects out as global symbols in code generation
Summary:
The symbols use the processor-specific SHN_AMDGPU_LDS section index
introduced with a previous change. The linker is then expected to resolve
relocations, which are also emitted.

Initially disabled for HSA and PAL environments until they have caught up
in terms of linker and runtime loader.

Some notes:

- The llvm.amdgcn.groupstaticsize intrinsics can no longer be lowered
  to a constant at compile times, which means some tests can no longer
  be applied.

  The current "solution" is a terrible hack, but the intrinsic isn't
  used by Mesa, so we can keep it for now.

- We no longer know the full LDS size per kernel at compile time, which
  means that we can no longer generate a relevant error message at
  compile time. It would be possible to add a check for the size of
  individual variables, but ultimately the linker will have to perform
  the final check.

Change-Id: If66dbf33fccfbf3609aefefa2558ac0850d42275

Reviewers: arsenm, rampitec, t-tye, b-sumner, jsjodin

Subscribers: qcolombet, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D61494

llvm-svn: 364297
2019-06-25 11:52:30 +00:00

37 lines
2.1 KiB
LLVM

; RUN: opt -data-layout=A5 -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck -check-prefix=IR %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=ASM %s
@global_array0 = internal unnamed_addr addrspace(3) global [750 x [10 x i32]] undef, align 4
@global_array1 = internal unnamed_addr addrspace(3) global [750 x [10 x i32]] undef, align 4
; IR-LABEL: define amdgpu_kernel void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
; IR: alloca [10 x i32]
; ASM-LABEL: {{^}}promote_alloca_size_256:
; ASM: .amdgpu_lds global_array0, 30000, 4
; ASM: .amdgpu_lds global_array1, 30000, 4
define amdgpu_kernel void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
entry:
%stack = alloca [10 x i32], align 4, addrspace(5)
%tmp = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds [10 x i32], [10 x i32] addrspace(5)* %stack, i32 0, i32 %tmp
store i32 4, i32 addrspace(5)* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
%tmp1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds [10 x i32], [10 x i32] addrspace(5)* %stack, i32 0, i32 %tmp1
store i32 5, i32 addrspace(5)* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds [10 x i32], [10 x i32] addrspace(5)* %stack, i32 0, i32 0
%tmp2 = load i32, i32 addrspace(5)* %arrayidx10, align 4
store i32 %tmp2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds [10 x i32], [10 x i32] addrspace(5)* %stack, i32 0, i32 1
%tmp3 = load i32, i32 addrspace(5)* %arrayidx12
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %tmp3, i32 addrspace(1)* %arrayidx13
%v0 = getelementptr inbounds [750 x [10 x i32]], [750 x [10 x i32]] addrspace(3)* @global_array0, i32 0, i32 0, i32 0
store i32 %tmp3, i32 addrspace(3)* %v0
%v1 = getelementptr inbounds [750 x [10 x i32]], [750 x [10 x i32]] addrspace(3)* @global_array1, i32 0, i32 0, i32 0
store i32 %tmp3, i32 addrspace(3)* %v1
ret void
}