a65ccc1b9f
On processors supporting vector registers and SIMD instructions, enable i128 as legal type in VRs. This allows many operations to be implemented via native instructions directly in VRs (including add, subtract, logical operations and shifts). For a few other operations (e.g. multiply and divide, as well as atomic operations), we need to move the i128 value back to a GPR pair to use the corresponding instruction there. Overall, this is still beneficial. The patch includes the following LLVM changes: - Enable i128 as legal type - Set up legal operations (in SystemZInstrVector.td) - Custom expansion for i128 add/subtract with carry - Custom expansion for i128 comparisons and selects - Support for moving i128 to/from GPR pairs when required - Handle 128-bit integer constant values everywhere - Use i128 as intrinsic operand type where appropriate - Updated and new test cases In addition, clang builtins are updated to reflect the intrinsic operand type changes (which also improves compatibility with GCC).
113 lines
3.6 KiB
LLVM
113 lines
3.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; Test 128-bit division and remainder in vector registers on z13 using libcalls
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
|
|
|
|
; Divide signed.
|
|
define i128 @f1(i128 %a, i128 %b) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: stmg %r13, %r15, 104(%r15)
|
|
; CHECK-NEXT: .cfi_offset %r13, -56
|
|
; CHECK-NEXT: .cfi_offset %r14, -48
|
|
; CHECK-NEXT: .cfi_offset %r15, -40
|
|
; CHECK-NEXT: aghi %r15, -208
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 368
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vl %v1, 0(%r4), 3
|
|
; CHECK-NEXT: lgr %r13, %r2
|
|
; CHECK-NEXT: la %r2, 192(%r15)
|
|
; CHECK-NEXT: la %r3, 176(%r15)
|
|
; CHECK-NEXT: la %r4, 160(%r15)
|
|
; CHECK-NEXT: vst %v1, 160(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 176(%r15), 3
|
|
; CHECK-NEXT: brasl %r14, __divti3@PLT
|
|
; CHECK-NEXT: vl %v0, 192(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 0(%r13), 3
|
|
; CHECK-NEXT: lmg %r13, %r15, 312(%r15)
|
|
; CHECK-NEXT: br %r14
|
|
%res = sdiv i128 %a, %b
|
|
ret i128 %res
|
|
}
|
|
|
|
; Divide unsigned.
|
|
define i128 @f2(i128 %a, i128 %b) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: stmg %r13, %r15, 104(%r15)
|
|
; CHECK-NEXT: .cfi_offset %r13, -56
|
|
; CHECK-NEXT: .cfi_offset %r14, -48
|
|
; CHECK-NEXT: .cfi_offset %r15, -40
|
|
; CHECK-NEXT: aghi %r15, -208
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 368
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vl %v1, 0(%r4), 3
|
|
; CHECK-NEXT: lgr %r13, %r2
|
|
; CHECK-NEXT: la %r2, 192(%r15)
|
|
; CHECK-NEXT: la %r3, 176(%r15)
|
|
; CHECK-NEXT: la %r4, 160(%r15)
|
|
; CHECK-NEXT: vst %v1, 160(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 176(%r15), 3
|
|
; CHECK-NEXT: brasl %r14, __udivti3@PLT
|
|
; CHECK-NEXT: vl %v0, 192(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 0(%r13), 3
|
|
; CHECK-NEXT: lmg %r13, %r15, 312(%r15)
|
|
; CHECK-NEXT: br %r14
|
|
%res = udiv i128 %a, %b
|
|
ret i128 %res
|
|
}
|
|
|
|
; Remainder signed.
|
|
define i128 @f3(i128 %a, i128 %b) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: stmg %r13, %r15, 104(%r15)
|
|
; CHECK-NEXT: .cfi_offset %r13, -56
|
|
; CHECK-NEXT: .cfi_offset %r14, -48
|
|
; CHECK-NEXT: .cfi_offset %r15, -40
|
|
; CHECK-NEXT: aghi %r15, -208
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 368
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vl %v1, 0(%r4), 3
|
|
; CHECK-NEXT: lgr %r13, %r2
|
|
; CHECK-NEXT: la %r2, 192(%r15)
|
|
; CHECK-NEXT: la %r3, 176(%r15)
|
|
; CHECK-NEXT: la %r4, 160(%r15)
|
|
; CHECK-NEXT: vst %v1, 160(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 176(%r15), 3
|
|
; CHECK-NEXT: brasl %r14, __modti3@PLT
|
|
; CHECK-NEXT: vl %v0, 192(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 0(%r13), 3
|
|
; CHECK-NEXT: lmg %r13, %r15, 312(%r15)
|
|
; CHECK-NEXT: br %r14
|
|
%res = srem i128 %a, %b
|
|
ret i128 %res
|
|
}
|
|
|
|
; Remainder unsigned.
|
|
define i128 @f4(i128 %a, i128 %b) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: stmg %r13, %r15, 104(%r15)
|
|
; CHECK-NEXT: .cfi_offset %r13, -56
|
|
; CHECK-NEXT: .cfi_offset %r14, -48
|
|
; CHECK-NEXT: .cfi_offset %r15, -40
|
|
; CHECK-NEXT: aghi %r15, -208
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 368
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vl %v1, 0(%r4), 3
|
|
; CHECK-NEXT: lgr %r13, %r2
|
|
; CHECK-NEXT: la %r2, 192(%r15)
|
|
; CHECK-NEXT: la %r3, 176(%r15)
|
|
; CHECK-NEXT: la %r4, 160(%r15)
|
|
; CHECK-NEXT: vst %v1, 160(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 176(%r15), 3
|
|
; CHECK-NEXT: brasl %r14, __umodti3@PLT
|
|
; CHECK-NEXT: vl %v0, 192(%r15), 3
|
|
; CHECK-NEXT: vst %v0, 0(%r13), 3
|
|
; CHECK-NEXT: lmg %r13, %r15, 312(%r15)
|
|
; CHECK-NEXT: br %r14
|
|
%res = urem i128 %a, %b
|
|
ret i128 %res
|
|
}
|