818b39ef64
This patch updates the definition of `AArch64ISD::INIT_TPIDR2OBJ` to take the number of save slices (which is currently always all ZA slices). Using this, we can initialize the TPIDR2 block with a single STP of the save buffer pointer and the number of save slices. The reserved bytes (10-15) will be implicitly zeroed as the result of RDSVL will always be <= 16-bits. Note: We used to write the number of save slices to the TPIDR2 block before every call with a lazy save; however, based on 6.6.9 "Changes to the TPIDR2 block" in the aapcs64 (https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#changes-to-the-tpidr2-block), it seems we can rely on callers preserving the contents of the TPIDR2 block.
116 lines
4.6 KiB
LLVM
116 lines
4.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -verify-machineinstrs -aarch64-new-sme-abi < %s | FileCheck %s --check-prefix=CHECK-NEWLOWERING
|
|
|
|
declare void @private_za_callee()
|
|
|
|
; Ensure that we don't use tail call optimization when a lazy-save is required.
|
|
define void @disable_tailcallopt() "aarch64_inout_za" nounwind {
|
|
; CHECK-LABEL: disable_tailcallopt:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: sub x10, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB0_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NEWLOWERING-LABEL: disable_tailcallopt:
|
|
; CHECK-NEWLOWERING: // %bb.0:
|
|
; CHECK-NEWLOWERING-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
|
|
; CHECK-NEWLOWERING-NEXT: mov x29, sp
|
|
; CHECK-NEWLOWERING-NEXT: sub sp, sp, #16
|
|
; CHECK-NEWLOWERING-NEXT: rdsvl x8, #1
|
|
; CHECK-NEWLOWERING-NEXT: mov x9, sp
|
|
; CHECK-NEWLOWERING-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEWLOWERING-NEXT: mov sp, x9
|
|
; CHECK-NEWLOWERING-NEXT: sub x10, x29, #16
|
|
; CHECK-NEWLOWERING-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEWLOWERING-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEWLOWERING-NEXT: bl private_za_callee
|
|
; CHECK-NEWLOWERING-NEXT: smstart za
|
|
; CHECK-NEWLOWERING-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEWLOWERING-NEXT: sub x0, x29, #16
|
|
; CHECK-NEWLOWERING-NEXT: cbnz x8, .LBB0_2
|
|
; CHECK-NEWLOWERING-NEXT: // %bb.1:
|
|
; CHECK-NEWLOWERING-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEWLOWERING-NEXT: .LBB0_2:
|
|
; CHECK-NEWLOWERING-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEWLOWERING-NEXT: mov sp, x29
|
|
; CHECK-NEWLOWERING-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
|
|
; CHECK-NEWLOWERING-NEXT: ret
|
|
tail call void @private_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; Ensure we set up and restore the lazy save correctly for instructions which are lowered to lib calls
|
|
define fp128 @f128_call_za(fp128 %a, fp128 %b) "aarch64_inout_za" nounwind {
|
|
; CHECK-LABEL: f128_call_za:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: sub x10, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEXT: bl __addtf3
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB1_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB1_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NEWLOWERING-LABEL: f128_call_za:
|
|
; CHECK-NEWLOWERING: // %bb.0:
|
|
; CHECK-NEWLOWERING-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
|
|
; CHECK-NEWLOWERING-NEXT: mov x29, sp
|
|
; CHECK-NEWLOWERING-NEXT: sub sp, sp, #16
|
|
; CHECK-NEWLOWERING-NEXT: rdsvl x8, #1
|
|
; CHECK-NEWLOWERING-NEXT: mov x9, sp
|
|
; CHECK-NEWLOWERING-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEWLOWERING-NEXT: mov sp, x9
|
|
; CHECK-NEWLOWERING-NEXT: sub x10, x29, #16
|
|
; CHECK-NEWLOWERING-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEWLOWERING-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEWLOWERING-NEXT: bl __addtf3
|
|
; CHECK-NEWLOWERING-NEXT: smstart za
|
|
; CHECK-NEWLOWERING-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEWLOWERING-NEXT: sub x0, x29, #16
|
|
; CHECK-NEWLOWERING-NEXT: cbnz x8, .LBB1_2
|
|
; CHECK-NEWLOWERING-NEXT: // %bb.1:
|
|
; CHECK-NEWLOWERING-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEWLOWERING-NEXT: .LBB1_2:
|
|
; CHECK-NEWLOWERING-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEWLOWERING-NEXT: mov sp, x29
|
|
; CHECK-NEWLOWERING-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
|
|
; CHECK-NEWLOWERING-NEXT: ret
|
|
%res = fadd fp128 %a, %b
|
|
ret fp128 %res
|
|
}
|