
It will run twice in the non-LTO pipeline with `O1` or higher. In LTO post link pipeline, it will be run once with `O2` or higher, since inline and SROA don't run in `O1`.
40 lines
1.5 KiB
LLVM
40 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a < %s | FileCheck %s
|
|
|
|
define protected amdgpu_kernel void @foo(ptr addrspace(1) %arg, ptr addrspace(1) %arg1) {
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: ; %bb.0: ; %bb
|
|
; CHECK-NEXT: s_add_u32 flat_scratch_lo, s12, s17
|
|
; CHECK-NEXT: s_addc_u32 flat_scratch_hi, s13, 0
|
|
; CHECK-NEXT: s_add_u32 s0, s0, s17
|
|
; CHECK-NEXT: s_addc_u32 s1, s1, 0
|
|
; CHECK-NEXT: s_add_u32 s8, s8, 16
|
|
; CHECK-NEXT: s_addc_u32 s9, s9, 0
|
|
; CHECK-NEXT: s_mov_b32 s13, s15
|
|
; CHECK-NEXT: s_mov_b32 s12, s14
|
|
; CHECK-NEXT: s_getpc_b64 s[18:19]
|
|
; CHECK-NEXT: s_add_u32 s18, s18, eggs@rel32@lo+4
|
|
; CHECK-NEXT: s_addc_u32 s19, s19, eggs@rel32@hi+12
|
|
; CHECK-NEXT: s_mov_b32 s14, s16
|
|
; CHECK-NEXT: v_mov_b32_e32 v31, v0
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, 0
|
|
; CHECK-NEXT: s_mov_b32 s32, 0
|
|
; CHECK-NEXT: s_swappc_b64 s[30:31], s[18:19]
|
|
; CHECK-NEXT: s_mov_b64 s[4:5], src_private_base
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, 0
|
|
; CHECK-NEXT: v_mov_b32_e32 v3, s5
|
|
; CHECK-NEXT: flat_load_dwordx2 v[2:3], v[2:3]
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: flat_store_dwordx2 v[2:3], v[0:1]
|
|
; CHECK-NEXT: s_endpgm
|
|
bb:
|
|
%tmp = addrspacecast ptr addrspace(5) null to ptr
|
|
%tmp2 = call i64 @eggs(ptr poison) #1
|
|
%tmp3 = load ptr, ptr %tmp, align 8
|
|
%tmp4 = getelementptr inbounds i64, ptr %tmp3, i64 0
|
|
store i64 %tmp2, ptr %tmp4, align 8
|
|
ret void
|
|
}
|
|
|
|
declare hidden i64 @eggs(ptr)
|