summaryrefslogtreecommitdiffstats
path: root/llvm/test
diff options
context:
space:
mode:
authorSimon Pilgrim <llvm-dev@redking.me.uk>2015-11-21 21:42:26 +0000
committerSimon Pilgrim <llvm-dev@redking.me.uk>2015-11-21 21:42:26 +0000
commit2829c1cf7b21d003e30a214d2414cbdbd40417d1 (patch)
treeb12fcde876d207e247ecec03b75299943457f738 /llvm/test
parentfb3fb0a309807c00de47a40e3aa91768bbdd0082 (diff)
downloadbcm5719-llvm-2829c1cf7b21d003e30a214d2414cbdbd40417d1.tar.gz
bcm5719-llvm-2829c1cf7b21d003e30a214d2414cbdbd40417d1.zip
[MachineInstrBuilder] Support for adding a ConstantPoolIndex MO with an additional offset.
MachineInstrBuilder::addDisp can already add an immediate or global address MO with an adjusted offset, this patch adds support for constant pool indices as well. All remaining MO types still assert - there are a number of other types that could support adjusted offsets but I have no test cases at this time. Required to fix a regression in D13988 found by Mikael Holmén during stress testing (test case attached). Differential Revision: http://reviews.llvm.org/D14867 llvm-svn: 253795
Diffstat (limited to 'llvm/test')
-rw-r--r--llvm/test/CodeGen/X86/insertps-from-constantpool.ll20
1 files changed, 20 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/insertps-from-constantpool.ll b/llvm/test/CodeGen/X86/insertps-from-constantpool.ll
new file mode 100644
index 00000000000..cfcfeacad06
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insertps-from-constantpool.ll
@@ -0,0 +1,20 @@
+; RUN: llc -mtriple=i686-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X32
+; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X64
+
+; Test for case where insertps folds the load of an insertion element from a constant pool.
+
+define <4 x float> @fold_from_constantpool(<4 x float> %a) {
+; X32-LABEL: fold_from_constantpool:
+; X32: # BB#0:
+; X32-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
+; X32-NEXT: retl
+;
+; X64-LABEL: fold_from_constantpool:
+; X64: # BB#0:
+; X64-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
+; X64-NEXT: retq
+ %1 = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> <float 0.0, float 1.0, float 0.0, float 0.0>, i8 64)
+ ret <4 x float> %1
+}
+
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
OpenPOWER on IntegriCloud