15fbdc2b96
Currently, given:
```cpp
svuint8_t foo(uint8_t *x) {
return svld1(svptrue_b8(), x);
}
```
We generate:
```gas
foo:
ptrue p0.b
ld1b { z0.b }, p0/z, [x0]
ret
```
However, on little-endian and with unaligned memory accesses allowed, we
could instead be using LDR as follows:
```gas
foo:
ldr z0, [x0]
ret
```
The second form avoids the predicate dependency.
Likewise for other types and stores.
103 lines
3.7 KiB
LLVM
103 lines
3.7 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"
|
|
|
|
%my_subtype = type <vscale x 2 x double>
|
|
%my_type = type [3 x %my_subtype]
|
|
|
|
define void @array_1D(ptr %addr) #0 {
|
|
; CHECK-LABEL: array_1D:
|
|
; 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, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 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 %my_type, align 8
|
|
%val = load %my_type, ptr %addr
|
|
store %my_type %val, ptr %ret, align 8
|
|
ret void
|
|
}
|
|
|
|
define %my_subtype @array_1D_extract(ptr %addr) #0 {
|
|
; CHECK-LABEL: array_1D_extract:
|
|
; 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, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
|
|
; CHECK-NEXT: .cfi_offset w29, -16
|
|
; CHECK-NEXT: ldr z0, [x0, #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 %my_type, align 8
|
|
%val = load %my_type, ptr %addr
|
|
%elt = extractvalue %my_type %val, 1
|
|
ret %my_subtype %elt
|
|
}
|
|
|
|
define void @array_1D_insert(ptr %addr, %my_subtype %elt) #0 {
|
|
; CHECK-LABEL: array_1D_insert:
|
|
; 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, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
|
|
; CHECK-NEXT: .cfi_offset w29, -16
|
|
; CHECK-NEXT: ldr z1, [x0, #2, mul vl]
|
|
; CHECK-NEXT: ldr z2, [x0]
|
|
; CHECK-NEXT: str z0, [sp, #1, mul vl]
|
|
; CHECK-NEXT: str z1, [sp, #2, mul vl]
|
|
; CHECK-NEXT: str z2, [sp]
|
|
; CHECK-NEXT: addvl sp, sp, #3
|
|
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%ret = alloca %my_type, align 8
|
|
%val = load %my_type, ptr %addr
|
|
%ins = insertvalue %my_type %val, %my_subtype %elt, 1
|
|
store %my_type %ins, ptr %ret, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @array_2D(ptr %addr) #0 {
|
|
; CHECK-LABEL: array_2D:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: addvl sp, sp, #-6
|
|
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x30, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 48 * VG
|
|
; CHECK-NEXT: .cfi_offset w29, -16
|
|
; CHECK-NEXT: ldr z0, [x0]
|
|
; CHECK-NEXT: ldr z1, [x0, #5, mul vl]
|
|
; CHECK-NEXT: ldr z2, [x0, #1, mul vl]
|
|
; CHECK-NEXT: ldr z3, [x0, #4, mul vl]
|
|
; CHECK-NEXT: ldr z4, [x0, #2, mul vl]
|
|
; CHECK-NEXT: ldr z5, [x0, #3, mul vl]
|
|
; CHECK-NEXT: str z0, [sp]
|
|
; CHECK-NEXT: str z1, [sp, #5, mul vl]
|
|
; CHECK-NEXT: str z3, [sp, #4, mul vl]
|
|
; CHECK-NEXT: str z5, [sp, #3, mul vl]
|
|
; CHECK-NEXT: str z4, [sp, #2, mul vl]
|
|
; CHECK-NEXT: str z2, [sp, #1, mul vl]
|
|
; CHECK-NEXT: addvl sp, sp, #6
|
|
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%ret = alloca [2 x %my_type], align 8
|
|
%val = load [2 x %my_type], ptr %addr
|
|
store [2 x %my_type] %val, ptr %ret, align 8
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "target-features"="+sve" }
|