1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
llvm-mirror/test/CodeGen/PowerPC/MergeConsecutiveStores.ll
Stefan Pintilie 40f69f3c47 [Power9] Code Cleanup - Remove needsAggressiveScheduling()
As we already return true from needsAggressiveScheduling() for the most recent
hardware it would be cleaner to just return true for all PowerPC hardware.

Differential Revision: https://reviews.llvm.org/D48663

llvm-svn: 337488
2018-07-19 19:34:18 +00:00

69 lines
3.1 KiB
LLVM

; RUN: llc -verify-machineinstrs -mtriple=powerpc-unknown-linux-gnu -mattr=+altivec < %s | FileCheck %s
;; This test ensures that MergeConsecutiveStores does not attempt to
;; merge stores or loads when doing so would result in unaligned
;; memory operations (unless the target supports those, e.g. X86).
;; This issue happen in other situations for other targets, but PPC
;; with Altivec extensions was chosen for the test because it does not
;; support unaligned access with AltiVec instructions. If the 4
;; load/stores get merged to an v4i32 vector type severely bad code
;; gets generated: it painstakingly copies the values to a temporary
;; location on the stack, with vector ops, in order to then use
;; integer ops to load from the temporary stack location and store to
;; the final location. Yuck!
%struct.X = type { i32, i32, i32, i32 }
@fx = common global %struct.X zeroinitializer, align 4
@fy = common global %struct.X zeroinitializer, align 4
;; In this test case, lvx and stvx instructions should NOT be
;; generated, as the alignment is not sufficient for it to be
;; worthwhile.
;; CHECK-LABEL: f:
;; CHECK-DAG: lwzu
;; CHECK-DAG: stwu
;; CHECK-DAG: lwz
;; CHECK-DAG: lwz
;; CHECK-DAG: lwz
;; CHECK-DAG: stw
;; CHECK-DAG: stw
;; CHECK-DAG: stw
;; CHECK-NEXT: blr
define void @f() {
entry:
%0 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 0), align 4
%1 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 1), align 4
%2 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 2), align 4
%3 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 3), align 4
store i32 %0, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 0), align 4
store i32 %1, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 1), align 4
store i32 %2, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 2), align 4
store i32 %3, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 3), align 4
ret void
}
@gx = common global %struct.X zeroinitializer, align 16
@gy = common global %struct.X zeroinitializer, align 16
;; In this test, lvx and stvx instructions SHOULD be generated, as
;; the 16-byte alignment of the new load/store is acceptable.
;; CHECK-LABEL: g:
;; CHECK: lvx
;; CHECK: stvx
;; CHECK: blr
define void @g() {
entry:
%0 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 0), align 16
%1 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 1), align 4
%2 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 2), align 4
%3 = load i32, i32* getelementptr inbounds (%struct.X, %struct.X* @fx, i32 0, i32 3), align 4
store i32 %0, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 0), align 16
store i32 %1, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 1), align 4
store i32 %2, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 2), align 4
store i32 %3, i32* getelementptr inbounds (%struct.X, %struct.X* @fy, i32 0, i32 3), align 4
ret void
}