mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
02f664086c
The addend in a REL32 reloc needs to be adjusted to account for the offset from the PC value returned by the s_getpc instruction to the point where the reloc is applied. This was being done correctly for (GOTPC)REL32_LO but not for (GOTPC)REL32_HI. This will only make a difference if the target symbol happens to get loaded almost exactly a multiple of 4G away from the relocated instructions. Differential Revision: https://reviews.llvm.org/D86938
52 lines
2.3 KiB
LLVM
52 lines
2.3 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji < %s | FileCheck %s
|
|
|
|
declare void @func(i32 addrspace(1)* %out)
|
|
|
|
declare protected void @protected_func(i32 addrspace(1)* %out)
|
|
|
|
declare hidden void @hidden_func(i32 addrspace(1)* %out)
|
|
|
|
; CHECK-LABEL: call_func:
|
|
; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
|
|
; CHECK: s_add_u32 s[[GOT_ADDR_LO:[0-9]+]], s[[PC_LO]], func@gotpcrel32@lo+4
|
|
; CHECK: s_addc_u32 s[[GOT_ADDR_HI:[0-9]+]], s[[PC_HI]], func@gotpcrel32@hi+12
|
|
; CHECK: s_load_dwordx2 s{{\[}}[[ADDR_LO:[0-9]+]]:[[ADDR_HI:[0-9]+]]{{\]}}, s{{\[}}[[GOT_ADDR_LO]]:[[GOT_ADDR_HI]]{{\]}}, 0x0
|
|
; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
|
|
define amdgpu_kernel void @call_func(i32 addrspace(1)* %out) {
|
|
call void @func(i32 addrspace(1)* %out)
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: call_protected_func:
|
|
; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
|
|
; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], protected_func@rel32@lo+4
|
|
; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], protected_func@rel32@hi+12
|
|
; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
|
|
define amdgpu_kernel void @call_protected_func(i32 addrspace(1)* %out) {
|
|
call void @protected_func(i32 addrspace(1)* %out)
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: call_hidden_func:
|
|
; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
|
|
; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], hidden_func@rel32@lo+4
|
|
; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], hidden_func@rel32@hi+12
|
|
; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
|
|
define amdgpu_kernel void @call_hidden_func(i32 addrspace(1)* %out) {
|
|
call void @hidden_func(i32 addrspace(1)* %out)
|
|
ret void
|
|
}
|
|
|
|
declare i64 @funci()
|
|
|
|
; CHECK-LABEL: tail_call_func:
|
|
; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
|
|
; CHECK: s_add_u32 s[[GOT_ADDR_LO:[0-9]+]], s[[PC_LO]], funci@gotpcrel32@lo+4
|
|
; CHECK: s_addc_u32 s[[GOT_ADDR_HI:[0-9]+]], s[[PC_HI]], funci@gotpcrel32@hi+12
|
|
; CHECK: s_load_dwordx2 s{{\[}}[[ADDR_LO:[0-9]+]]:[[ADDR_HI:[0-9]+]]{{\]}}, s{{\[}}[[GOT_ADDR_LO]]:[[GOT_ADDR_HI]]{{\]}}, 0x0
|
|
; CHECK: s_setpc_b64 s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
|
|
define i64 @tail_call_func() {
|
|
%ret = tail call i64 @funci()
|
|
ret i64 %ret
|
|
}
|