llvm-6502/test/CodeGen/PowerPC/memcpy-vec.ll
Hal Finkel e03aac601f [PowerPC] Use vector types for memcpy and friends (sometimes)
When using Altivec, we can use vector loads and stores for aligned memcpy and
friends. Starting with the P7 and VXS, we have reasonable unaligned vector
stores. Starting with the P8, we have fast unaligned loads too.

For QPX, we use vector loads are stores, but only for aligned memory accesses.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230788 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:58:28 +00:00

111 lines
2.4 KiB
LLVM

; RUN: llc -mcpu=pwr7 < %s | FileCheck %s -check-prefix=PWR7
; RUN: llc -mcpu=pwr8 < %s | FileCheck %s -check-prefix=PWR8
; RUN: llc -mcpu=a2q < %s | FileCheck %s -check-prefix=A2Q
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
; Function Attrs: nounwind
define void @foo1(double* nocapture %x, double* nocapture readonly %y) #0 {
entry:
%0 = bitcast double* %x to i8*
%1 = bitcast double* %y to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 32, i32 8, i1 false)
ret void
; PWR7-LABEL: @foo1
; PWR7-NOT: bl memcpy
; PWR7: ld {{[0-9]+}}, {{[0-9]+}}(4)
; PWR7: std {{[0-9]+}}, {{[0-9]+}}(3)
; PWR7: blr
; PWR8-LABEL: @foo1
; PWR8: lxvw4x
; PWR8: stxvw4x
; PWR8: blr
; A2Q-LABEL: @foo1
; A2Q-NOT: bl memcpy
; A2Q: ld {{[0-9]+}}, {{[0-9]+}}(4)
; A2Q: std {{[0-9]+}}, {{[0-9]+}}(3)
; A2Q: blr
}
; Function Attrs: nounwind
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #0
; Function Attrs: nounwind
define void @foo2(double* nocapture %x, double* nocapture readonly %y) #0 {
entry:
%0 = bitcast double* %x to i8*
%1 = bitcast double* %y to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 128, i32 8, i1 false)
ret void
; PWR7-LABEL: @foo2
; PWR7: bl memcpy
; PWR7: blr
; PWR8-LABEL: @foo2
; PWR8: lxvw4x
; PWR8: stxvw4x
; PWR8: blr
; A2Q-LABEL: @foo2
; A2Q-NOT: bl memcpy
; A2Q: ld {{[0-9]+}}, {{[0-9]+}}(4)
; A2Q: std {{[0-9]+}}, {{[0-9]+}}(3)
; A2Q: blr
}
; Function Attrs: nounwind
define void @bar1(double* nocapture %x) #0 {
entry:
%0 = bitcast double* %x to i8*
tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 128, i32 8, i1 false)
ret void
; PWR7-LABEL: @bar1
; PWR7-NOT: bl memset
; PWR7: stxvw4x
; PWR7: blr
; PWR8-LABEL: @bar1
; PWR8-NOT: bl memset
; PWR8: stxvw4x
; PWR8: blr
; A2Q-LABEL: @bar1
; A2Q-NOT: bl memset
; A2Q: std {{[0-9]+}}, {{[0-9]+}}(3)
; A2Q: blr
}
; Function Attrs: nounwind
define void @bar2(double* nocapture %x) #0 {
entry:
%0 = bitcast double* %x to i8*
tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 128, i32 32, i1 false)
ret void
; PWR7-LABEL: @bar2
; PWR7-NOT: bl memset
; PWR7: stxvw4x
; PWR7: blr
; PWR8-LABEL: @bar2
; PWR8-NOT: bl memset
; PWR8: stxvw4x
; PWR8: blr
; A2Q-LABEL: @bar2
; A2Q-NOT: bl memset
; A2Q: qvstfdx
; A2Q: blr
}
; Function Attrs: nounwind
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #0
attributes #0 = { nounwind }