llvm-project/llvm/test/CodeGen/AMDGPU/nested-calls.ll
Matt Arsenault 34c8b835b1 AMDGPU: Don't fix emergency stack slot at offset 0
This forced the caller to be aware of this, which is an ugly ABI
feature.

Partially reverts r295877. The original reasons for doing this are
mostly fixed. Alloca is now in a non-0 address space, so it should be
OK to have 0 as a valid pointer. Since we treat the absolute address
as the pointer value, this part only really needed to apply to
kernels.

Since r357093, we avoid the need to increment/decrement the offset
register in more cases, and since r354816 the scavenger can fail
without spilling, so it's less critical that we try to avoid an offset
that fits in the MUBUF offset.

Restrict to callable functions for now to split this into 2 steps to
limit thte number of test updates and in case anything breaks.

llvm-svn: 362665
2019-06-05 22:37:50 +00:00

60 lines
2.4 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
; RUN: llc -march=amdgcn -mcpu=hawaii -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=CI %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 -check-prefix=VI %s
; Test calls when called by other callable functions rather than
; kernels.
declare void @external_void_func_i32(i32) #0
; GCN-LABEL: {{^}}test_func_call_external_void_func_i32_imm:
; GCN: s_waitcnt
; GCN: s_mov_b32 s5, s32
; GCN-DAG: s_add_u32 s32, s32, 0x400
; Spill CSR VGPR used for SGPR spilling
; GCN: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_store_dword v32, off, s[0:3], s5 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN-DAG: v_writelane_b32 v32, s33, 0
; GCN-DAG: v_writelane_b32 v32, s34, 1
; GCN-DAG: v_writelane_b32 v32, s35, 2
; GCN: s_swappc_b64
; GCN: v_readlane_b32 s35, v32, 2
; GCN: v_readlane_b32 s34, v32, 1
; GCN: v_readlane_b32 s33, v32, 0
; GCN: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_load_dword v32, off, s[0:3], s5 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN: s_sub_u32 s32, s32, 0x400
; GCN: s_setpc_b64
define void @test_func_call_external_void_func_i32_imm() #0 {
call void @external_void_func_i32(i32 42)
ret void
}
; GCN-LABEL: {{^}}test_func_call_external_void_func_i32_imm_stack_use:
; GCN: s_waitcnt
; GCN: s_mov_b32 s5, s32
; GCN-DAG: s_add_u32 s32, s32, 0x1400{{$}}
; GCN-DAG: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s5 offset
; GCN: s_swappc_b64
; GCN: s_sub_u32 s32, s32, 0x1400{{$}}
; GCN: s_setpc_b64
define void @test_func_call_external_void_func_i32_imm_stack_use() #0 {
%alloca = alloca [16 x i32], align 4, addrspace(5)
%gep0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 0
%gep15 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 16
store volatile i32 0, i32 addrspace(5)* %gep0
store volatile i32 0, i32 addrspace(5)* %gep15
call void @external_void_func_i32(i32 42)
ret void
}
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind noinline }