ff5fa711b3
The main change in this patch is we go from emitting the expression: @ cfa - NumBytes - NumScalableBytes * VG To: @ cfa - VG * NumScalableBytes - NumBytes That is, VG is the first expression. This is for a future patch that adds an alternative way to resolve VG (which uses the CFA, so it is convenient for the CFA to be at the top of the stack). Since doing this is fairly churn-heavy, I took the opportunity to also save up to 4-bytes per SVE CFI expression. This is done by folding LEB128 constants to literals when in the range 0 to 31, and using the offset in `DW_OP_breg*` expressions.
32 lines
1.1 KiB
LLVM
32 lines
1.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
%struct.test = type { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> }
|
|
|
|
define void @test(ptr %addr) #0 {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: addvl sp, sp, #-3
|
|
; CHECK-NEXT: .cfi_escape 0x0f, 0x08, 0x8f, 0x10, 0x92, 0x2e, 0x00, 0x48, 0x1e, 0x22 // sp + 16 + 24 * VG
|
|
; CHECK-NEXT: .cfi_offset w29, -16
|
|
; CHECK-NEXT: ldr z0, [x0]
|
|
; CHECK-NEXT: ldr z1, [x0, #2, mul vl]
|
|
; CHECK-NEXT: ldr z2, [x0, #1, mul vl]
|
|
; CHECK-NEXT: str z0, [sp]
|
|
; CHECK-NEXT: str z1, [sp, #2, mul vl]
|
|
; CHECK-NEXT: str z2, [sp, #1, mul vl]
|
|
; CHECK-NEXT: addvl sp, sp, #3
|
|
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%ret = alloca %struct.test, align 8
|
|
%val = load %struct.test, ptr %addr
|
|
store %struct.test %val, ptr %ret, align 8
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "target-features"="+sve" }
|