test/CodeGen/AMDGPU/r600.add.ll

; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -enable-var-scope -check-prefix=EG -check-prefix=FUNC %s

; FUNC-LABEL: {{^}}s_add_i32:
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define amdgpu_kernel void @s_add_i32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
  %b_ptr = getelementptr i32, ptr addrspace(1) %in, i32 1
  %a = load i32, ptr addrspace(1) %in
  %b = load i32, ptr addrspace(1) %b_ptr
  %result = add i32 %a, %b
  store i32 %result, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}s_add_v2i32:
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define amdgpu_kernel void @s_add_v2i32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
  %b_ptr = getelementptr <2 x i32>, ptr addrspace(1) %in, i32 1
  %a = load <2 x i32>, ptr addrspace(1) %in
  %b = load <2 x i32>, ptr addrspace(1) %b_ptr
  %result = add <2 x i32> %a, %b
  store <2 x i32> %result, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}s_add_v4i32:
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define amdgpu_kernel void @s_add_v4i32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
  %b_ptr = getelementptr <4 x i32>, ptr addrspace(1) %in, i32 1
  %a = load <4 x i32>, ptr addrspace(1) %in
  %b = load <4 x i32>, ptr addrspace(1) %b_ptr
  %result = add <4 x i32> %a, %b
  store <4 x i32> %result, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}s_add_v8i32:
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
define amdgpu_kernel void @s_add_v8i32(ptr addrspace(1) %out, <8 x i32> %a, <8 x i32> %b) {
entry:
  %0 = add <8 x i32> %a, %b
  store <8 x i32> %0, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}s_add_v16i32:
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
; EG: ADD_INT
define amdgpu_kernel void @s_add_v16i32(ptr addrspace(1) %out, <16 x i32> %a, <16 x i32> %b) {
entry:
  %0 = add <16 x i32> %a, %b
  store <16 x i32> %0, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}v_add_i32:
define amdgpu_kernel void @v_add_i32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
  %tid = call i32 @llvm.r600.read.tidig.x()
  %gep = getelementptr inbounds i32, ptr addrspace(1) %in, i32 %tid
  %b_ptr = getelementptr i32, ptr addrspace(1) %gep, i32 1
  %a = load volatile i32, ptr addrspace(1) %gep
  %b = load volatile i32, ptr addrspace(1) %b_ptr
  %result = add i32 %a, %b
  store i32 %result, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}v_add_imm_i32:
define amdgpu_kernel void @v_add_imm_i32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
  %tid = call i32 @llvm.r600.read.tidig.x()
  %gep = getelementptr inbounds i32, ptr addrspace(1) %in, i32 %tid
  %b_ptr = getelementptr i32, ptr addrspace(1) %gep, i32 1
  %a = load volatile i32, ptr addrspace(1) %gep
  %result = add i32 %a, 123
  store i32 %result, ptr addrspace(1) %out
  ret void
}

; FUNC-LABEL: {{^}}add64:
; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.XY]]
; EG-DAG: ADD_INT {{[* ]*}}
; EG-DAG: ADDC_UINT
; EG-DAG: ADD_INT
; EG-DAG: ADD_INT {{[* ]*}}
; EG-NOT: SUB
define amdgpu_kernel void @add64(ptr addrspace(1) %out, i64 %a, i64 %b) {
entry:
  %add = add i64 %a, %b
  store i64 %add, ptr addrspace(1) %out
  ret void
}

; The v_addc_u32 and v_add_i32 instruction can't read SGPRs, because they
; use VCC.  The test is designed so that %a will be stored in an SGPR and
; %0 will be stored in a VGPR, so the comiler will be forced to copy %a
; to a VGPR before doing the add.

; FUNC-LABEL: {{^}}add64_sgpr_vgpr:
; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.XY]]
; EG-DAG: ADD_INT {{[* ]*}}
; EG-DAG: ADDC_UINT
; EG-DAG: ADD_INT
; EG-DAG: ADD_INT {{[* ]*}}
; EG-NOT: SUB
define amdgpu_kernel void @add64_sgpr_vgpr(ptr addrspace(1) %out, i64 %a, ptr addrspace(1) %in) {
entry:
  %0 = load i64, ptr addrspace(1) %in
  %1 = add i64 %a, %0
  store i64 %1, ptr addrspace(1) %out
  ret void
}

; Test i64 add inside a branch.
; FUNC-LABEL: {{^}}add64_in_branch:
; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.XY]]
; EG-DAG: ADD_INT {{[* ]*}}
; EG-DAG: ADDC_UINT
; EG-DAG: ADD_INT
; EG-DAG: ADD_INT {{[* ]*}}
; EG-NOT: SUB
define amdgpu_kernel void @add64_in_branch(ptr addrspace(1) %out, ptr addrspace(1) %in, i64 %a, i64 %b, i64 %c) {
entry:
  %0 = icmp eq i64 %a, 0
  br i1 %0, label %if, label %else

if:
  %1 = load i64, ptr addrspace(1) %in
  br label %endif

else:
  %2 = add i64 %a, %b
  br label %endif

endif:
  %3 = phi i64 [%1, %if], [%2, %else]
  store i64 %3, ptr addrspace(1) %out
  ret void
}

declare i32 @llvm.r600.read.tidig.x() #1

attributes #0 = { nounwind }
attributes #1 = { nounwind readnone speculatable }