[AMDGPU] Mark test functions with hidden visibility

[scott.linder]

Summary

Prepares for future patch which affect codegen for calls to preemptible functions.

[arsenm]

LGTM

test/CodeGen/AMDGPU/byval-frame-setup.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI %s
 
 %struct.ByValStruct = type { [4 x i32] }
 
 ; GCN-LABEL: {{^}}void_func_byval_struct:
 ; GCN: s_mov_b32 s5, s32
 ; GCN: buffer_load_dword [[LOAD0:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], s5 offset:4{{$}}
 ; GCN-NOT: s32
 
 ; GCN: buffer_load_dword [[LOAD1:v[0-9]+]], off, s[0:3], s5 offset:20{{$}}
 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD1]], off, s[0:3], s5 offset:20{{$}}
 ; GCN-NOT: s32
-define void @void_func_byval_struct(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg1) #1 {
+define hidden void @void_func_byval_struct(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 4 %arg1) #1 {
 entry:
   %arrayidx = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg0, i32 0, i32 0, i32 0
   %tmp = load volatile i32, i32 addrspace(5)* %arrayidx, align 4
   %add = add nsw i32 %tmp, 1
   store volatile i32 %add, i32 addrspace(5)* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg1, i32 0, i32 0, i32 0
   %tmp1 = load volatile i32, i32 addrspace(5)* %arrayidx2, align 4
   %add3 = add nsw i32 %tmp1, 2

 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], s5 offset:8{{$}}
 ; GCN-NOT: s32
 
 ; GCN: buffer_load_dword [[LOAD1:v[0-9]+]], off, s[0:3], s5 offset:24{{$}}
 ; GCN-NOT: s32
 ; GCN: buffer_store_dword [[LOAD1]], off, s[0:3], s5 offset:24{{$}}
 ; GCN-NOT: s32
-define void @void_func_byval_struct_align8(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg1) #1 {
+define hidden void @void_func_byval_struct_align8(%struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg0, %struct.ByValStruct addrspace(5)* byval noalias nocapture align 8 %arg1) #1 {
 entry:
   %arrayidx = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg0, i32 0, i32 0, i32 0
   %tmp = load volatile i32, i32 addrspace(5)* %arrayidx, align 8
   %add = add nsw i32 %tmp, 1
   store volatile i32 %add, i32 addrspace(5)* %arrayidx, align 8
   %arrayidx2 = getelementptr inbounds %struct.ByValStruct, %struct.ByValStruct addrspace(5)* %arg1, i32 0, i32 0, i32 0
   %tmp1 = load volatile i32, i32 addrspace(5)* %arrayidx2, align 8
   %add3 = add nsw i32 %tmp1, 2

test/CodeGen/AMDGPU/call-argument-types.ll

 ; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,MESA %s
 ; RUN: llc -march=amdgcn -mcpu=hawaii -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,MESA %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,VI,MESA %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -mattr=-flat-for-global -amdgpu-scalarize-global-loads=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,HSA %s
 
-declare void @external_void_func_i1(i1) #0
-declare void @external_void_func_i1_signext(i1 signext) #0
-declare void @external_void_func_i1_zeroext(i1 zeroext) #0
-
-declare void @external_void_func_i8(i8) #0
-declare void @external_void_func_i8_signext(i8 signext) #0
-declare void @external_void_func_i8_zeroext(i8 zeroext) #0
-
-declare void @external_void_func_i16(i16) #0
-declare void @external_void_func_i16_signext(i16 signext) #0
-declare void @external_void_func_i16_zeroext(i16 zeroext) #0
-
-declare void @external_void_func_i32(i32) #0
-declare void @external_void_func_i64(i64) #0
-declare void @external_void_func_v2i64(<2 x i64>) #0
-declare void @external_void_func_v3i64(<3 x i64>) #0
-declare void @external_void_func_v4i64(<4 x i64>) #0
-
-declare void @external_void_func_f16(half) #0
-declare void @external_void_func_f32(float) #0
-declare void @external_void_func_f64(double) #0
-declare void @external_void_func_v2f32(<2 x float>) #0
-declare void @external_void_func_v2f64(<2 x double>) #0
-declare void @external_void_func_v3f64(<3 x double>) #0
-
-declare void @external_void_func_v2i16(<2 x i16>) #0
-declare void @external_void_func_v2f16(<2 x half>) #0
-declare void @external_void_func_v3i16(<3 x i16>) #0
-declare void @external_void_func_v3f16(<3 x half>) #0
-declare void @external_void_func_v4i16(<4 x i16>) #0
-declare void @external_void_func_v4f16(<4 x half>) #0
-
-declare void @external_void_func_v2i32(<2 x i32>) #0
-declare void @external_void_func_v3i32(<3 x i32>) #0
-declare void @external_void_func_v3i32_i32(<3 x i32>, i32) #0
-declare void @external_void_func_v4i32(<4 x i32>) #0
-declare void @external_void_func_v8i32(<8 x i32>) #0
-declare void @external_void_func_v16i32(<16 x i32>) #0
-declare void @external_void_func_v32i32(<32 x i32>) #0
-declare void @external_void_func_v32i32_i32(<32 x i32>, i32) #0
+declare hidden void @external_void_func_i1(i1) #0
+declare hidden void @external_void_func_i1_signext(i1 signext) #0
+declare hidden void @external_void_func_i1_zeroext(i1 zeroext) #0
+
+declare hidden void @external_void_func_i8(i8) #0
+declare hidden void @external_void_func_i8_signext(i8 signext) #0
+declare hidden void @external_void_func_i8_zeroext(i8 zeroext) #0
+
+declare hidden void @external_void_func_i16(i16) #0
+declare hidden void @external_void_func_i16_signext(i16 signext) #0
+declare hidden void @external_void_func_i16_zeroext(i16 zeroext) #0
+
+declare hidden void @external_void_func_i32(i32) #0
+declare hidden void @external_void_func_i64(i64) #0
+declare hidden void @external_void_func_v2i64(<2 x i64>) #0
+declare hidden void @external_void_func_v3i64(<3 x i64>) #0
+declare hidden void @external_void_func_v4i64(<4 x i64>) #0
+
+declare hidden void @external_void_func_f16(half) #0
+declare hidden void @external_void_func_f32(float) #0
+declare hidden void @external_void_func_f64(double) #0
+declare hidden void @external_void_func_v2f32(<2 x float>) #0
+declare hidden void @external_void_func_v2f64(<2 x double>) #0
+declare hidden void @external_void_func_v3f64(<3 x double>) #0
+
+declare hidden void @external_void_func_v2i16(<2 x i16>) #0
+declare hidden void @external_void_func_v2f16(<2 x half>) #0
+declare hidden void @external_void_func_v3i16(<3 x i16>) #0
+declare hidden void @external_void_func_v3f16(<3 x half>) #0
+declare hidden void @external_void_func_v4i16(<4 x i16>) #0
+declare hidden void @external_void_func_v4f16(<4 x half>) #0
+
+declare hidden void @external_void_func_v2i32(<2 x i32>) #0
+declare hidden void @external_void_func_v3i32(<3 x i32>) #0
+declare hidden void @external_void_func_v3i32_i32(<3 x i32>, i32) #0
+declare hidden void @external_void_func_v4i32(<4 x i32>) #0
+declare hidden void @external_void_func_v8i32(<8 x i32>) #0
+declare hidden void @external_void_func_v16i32(<16 x i32>) #0
+declare hidden void @external_void_func_v32i32(<32 x i32>) #0
+declare hidden void @external_void_func_v32i32_i32(<32 x i32>, i32) #0
 
 ; return value and argument
-declare i32 @external_i32_func_i32(i32) #0
+declare hidden i32 @external_i32_func_i32(i32) #0
 
 ; Structs
-declare void @external_void_func_struct_i8_i32({ i8, i32 }) #0
-declare void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval) #0
-declare void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* sret, { i8, i32 } addrspace(5)* byval) #0
+declare hidden void @external_void_func_struct_i8_i32({ i8, i32 }) #0
+declare hidden void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval) #0
+declare hidden void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* sret, { i8, i32 } addrspace(5)* byval) #0
 
-declare void @external_void_func_v16i8(<16 x i8>) #0
+declare hidden void @external_void_func_v16i8(<16 x i8>) #0
 
 
 ; FIXME: Should be passing -1
 ; GCN-LABEL: {{^}}test_call_external_void_func_i1_imm:
 ; MESA: s_mov_b32 s36, SCRATCH_RSRC_DWORD
 
 ; MESA-DAG: s_mov_b64 s[0:1], s[36:37]
 

 ; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:16 ; 4-byte Folded Reload
 ; GCN: s_setpc_b64
 define void @tail_call_stack_passed_arg_alignment_v32i32_f64(<32 x i32> %val, double %tmp) #0 {
 entry:
   tail call void @stack_passed_f64_arg(<32 x i32> %val, double %tmp)
   ret void
 }
 
-declare void @byval_align16_f64_arg(<32 x i32>, double addrspace(5)* byval align 16) #0
-declare void @stack_passed_f64_arg(<32 x i32>, double) #0
+declare hidden void @byval_align16_f64_arg(<32 x i32>, double addrspace(5)* byval align 16) #0
+declare hidden void @stack_passed_f64_arg(<32 x i32>, double) #0
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }
 attributes #2 = { nounwind noinline }

test/CodeGen/AMDGPU/call-constexpr.ll

define amdgpu_kernel void @test_bitcast_argument_and_return_types() #0 {
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_workitem_id_x:
 ; GCN: s_waitcnt
 ; GCN-NEXT: v_add_i32_e32 v0, vcc, v1, v0
 ; GCN-NEXT: s_setpc_b64
-define i32 @use_workitem_id_x(i32 %arg0) #0 {
+define hidden i32 @use_workitem_id_x(i32 %arg0) #0 {
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %op = add i32 %id, %arg0
   ret i32 %op
 }
 
 ; GCN-LABEL: {{^}}test_bitcast_use_workitem_id_x:
 ; GCN: v_mov_b32_e32 v1, v0
 ; GCN: s_getpc_b64
continue:
   %op = fadd float %val, 1.0
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; Callees appears last in source file to test that we still lower their
 ; arguments before we lower any calls to them.
 
-define i32 @ret_i32_noinline() #0 {
+define hidden i32 @ret_i32_noinline() #0 {
   ret i32 4
 }
 
-define i32 @ret_i32_alwaysinline() #1 {
+define hidden i32 @ret_i32_alwaysinline() #1 {
   ret i32 4
 }
 
-define i32 @ident_i32(i32 %i) #0 {
+define hidden i32 @ident_i32(i32 %i) #0 {
   ret i32 %i
 }
 
 declare i32 @llvm.amdgcn.workitem.id.x() #2
 
 attributes #0 = { nounwind noinline }
 attributes #1 = { alwaysinline nounwind }
 attributes #2 = { nounwind readnone speculatable }

test/CodeGen/AMDGPU/call-preserved-registers.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
-declare void @external_void_func_void() #0
+declare hidden void @external_void_func_void() #0
 
 ; GCN-LABEL: {{^}}test_kernel_call_external_void_func_void_clobber_s30_s31_call_external_void_func_void:
 ; GCN: s_mov_b32 s33, s7
 ; GCN: s_mov_b32 s4, s33
 ; GCN-NEXT: s_getpc_b64 s[34:35]
 ; GCN-NEXT: s_add_u32 s34, s34,
 ; GCN-NEXT: s_addc_u32 s35, s35,
 ; GCN-NEXT: s_mov_b32 s32, s33
define void @void_func_void_clobber_s30_s31() #2 {
   ret void
 }
 
 ; GCN-LABEL: {{^}}void_func_void_clobber_vcc:
 ; GCN: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT: ;;#ASMSTART
 ; GCN-NEXT: ;;#ASMEND
 ; GCN-NEXT: s_setpc_b64 s[30:31]
-define void @void_func_void_clobber_vcc() #2 {
+define hidden void @void_func_void_clobber_vcc() #2 {
   call void asm sideeffect "", "~{VCC}"() #0
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_call_void_func_void_clobber_vcc:
 ; GCN: s_getpc_b64
 ; GCN-NEXT: s_add_u32
 ; GCN-NEXT: s_addc_u32

 
 ; GCN-LABEL: {{^}}void_func_void_clobber_s33:
 ; GCN: v_writelane_b32 v0, s33, 0
 ; GCN-NEXT: #ASMSTART
 ; GCN-NEXT: ; clobber
 ; GCN-NEXT: #ASMEND
 ; GCN-NEXT: v_readlane_b32 s33, v0, 0
 ; GCN-NEXT: s_setpc_b64
-define void @void_func_void_clobber_s33() #2 {
+define hidden void @void_func_void_clobber_s33() #2 {
   call void asm sideeffect "; clobber", "~{s33}"() #0
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_call_void_func_void_clobber_s33:
 ; GCN: s_mov_b32 s33, s7
 ; GCN: s_mov_b32 s4, s33
 ; GCN-NEXT: s_getpc_b64

test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll

bb1:
   %extract0 = extractelement <4 x i32> %val0, i32 0
   %extract1 = extractelement <4 x half> %val1, i32 0
   %ins0 = insertvalue { i32, half } undef, i32 %extract0, 0
   %ins1 = insertvalue { i32, half } %ins0, half %extract1, 1
   ret { i32, half } %ins1
 }
 
 
-declare <2 x float> @func_v2f32() #0
-declare <3 x float> @func_v3f32() #0
-declare <4 x float> @func_v4f32() #0
-declare <4 x half> @func_v4f16() #0
+declare hidden <2 x float> @func_v2f32() #0
+declare hidden <3 x float> @func_v3f32() #0
+declare hidden <4 x float> @func_v4f32() #0
+declare hidden <4 x half> @func_v4f16() #0
 
-declare { <4 x i32>, <4 x half> } @func_struct() #0
+declare hidden { <4 x i32>, <4 x half> } @func_struct() #0
 
 attributes #0 = { nounwind}

test/CodeGen/AMDGPU/ipra.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -enable-ipra -amdgpu-sroa=0 < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -amdgpu-sroa=0 < %s | FileCheck -check-prefix=GCN %s
 
 ; Kernels are not called, so there is no call preserved mask.
 ; GCN-LABEL: {{^}}kernel:
 ; GCN: flat_store_dword
 define amdgpu_kernel void @kernel(i32 addrspace(1)* %out) #0 {
 entry:
   store i32 0, i32 addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}func:
 ; GCN: ; NumVgprs: 8
-define void @func() #1 {
+define hidden void @func() #1 {
   call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7}"() #0
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_call:
 ; GCN-NOT: buffer_store
 ; GCN-NOT: buffer_load
 ; GCN-NOT: readlane

test/CodeGen/AMDGPU/mem-builtins.ll

 ; RUN: not llc -march=r600 < %s 2>&1 | FileCheck -check-prefix=ERROR %s
 ; RUN: llc -march=amdgcn < %s | FileCheck -check-prefix=GCN %s
 
-declare i32 @memcmp(i8 addrspace(1)* readonly nocapture, i8 addrspace(1)* readonly nocapture, i64) #0
-declare i8 addrspace(1)* @memchr(i8 addrspace(1)* readonly nocapture, i32, i64) #1
-declare i8* @strcpy(i8* nocapture, i8* readonly nocapture) #0
-declare i32 @strlen(i8* nocapture) #1
-declare i32 @strnlen(i8* nocapture, i32) #1
-declare i32 @strcmp(i8* nocapture, i8* nocapture) #1
+declare hidden i32 @memcmp(i8 addrspace(1)* readonly nocapture, i8 addrspace(1)* readonly nocapture, i64) #0
+declare hidden i8 addrspace(1)* @memchr(i8 addrspace(1)* readonly nocapture, i32, i64) #1
+declare hidden i8* @strcpy(i8* nocapture, i8* readonly nocapture) #0
+declare hidden i32 @strlen(i8* nocapture) #1
+declare hidden i32 @strnlen(i8* nocapture, i32) #1
+declare hidden i32 @strcmp(i8* nocapture, i8* nocapture) #1
 
 
 ; ERROR: error: <unknown>:0:0: in function test_memcmp void (i8 addrspace(1)*, i8 addrspace(1)*, i32*): unsupported call to function memcmp
 
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, memcmp@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, memcmp@rel32@hi+4
 define amdgpu_kernel void @test_memcmp(i8 addrspace(1)* %x, i8 addrspace(1)* %y, i32* nocapture %p) #0 {
 entry:

test/CodeGen/AMDGPU/sibling-call.ll

define fastcc i32 @i32_fastcc_i32_i32_stack_object(i32 %arg0, i32 %arg1) #1 {
   %alloca = alloca [16 x i32], align 4, addrspace(5)
   %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5
   store volatile i32 9, i32 addrspace(5)* %gep
   %add0 = add i32 %arg0, %arg1
   ret i32 %add0
 }
 
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32:
-define fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c) #1 {
+define hidden fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c) #1 {
 entry:
   %ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
   ret i32 %ret
 }
 
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_stack_object:
 ; GCN: v_mov_b32_e32 [[NINE:v[0-9]+]], 9
 ; GCN: buffer_store_dword [[NINE]], off, s[0:3], s5 offset:24

 ; GCN-NEXT: s_mov_b32 s5, s32
 ; GCN-NEXT: buffer_load_dword v1, off, s[0:3], s5 offset:4
 ; GCN-NEXT: s_waitcnt vmcnt(0)
 
 ; CIVI-NEXT: v_add_{{i|u}}32_e32 v0, vcc, v0, v1
 ; GFX9-NEXT: v_add_u32_e32 v0, v0, v1
 
 ; GCN-NEXT: s_setpc_b64 s[30:31]
-define fastcc i32 @i32_fastcc_i32_byval_i32(i32 %arg0, i32 addrspace(5)* byval align 4 %arg1) #1 {
+define hidden fastcc i32 @i32_fastcc_i32_byval_i32(i32 %arg0, i32 addrspace(5)* byval align 4 %arg1) #1 {
   %arg1.load = load i32, i32 addrspace(5)* %arg1, align 4
   %add0 = add i32 %arg0, %arg1.load
   ret i32 %add0
 }
 
 ; Tail call disallowed with byval in parent.
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_byval_i32_byval_parent:
 ; GCN-NOT: v_writelane_b32 v{{[0-9]+}}, s32