summaryrefslogtreecommitdiffstats
path: root/test
diff options
context:
space:
mode:
authorEric Christopher <echristo@gmail.com>2013-05-14 18:33:40 +0000
committerEric Christopher <echristo@gmail.com>2013-05-14 18:33:40 +0000
commitf276c70bb8ff25e7c0ef13e9afc59623a3c135ba (patch)
treed4e3e6e70445e0a3930f3224a1373f4ce8897037 /test
parentedf0dda52849850a199136475bdb975df11997aa (diff)
downloadexternal_llvm-f276c70bb8ff25e7c0ef13e9afc59623a3c135ba.zip
external_llvm-f276c70bb8ff25e7c0ef13e9afc59623a3c135ba.tar.gz
external_llvm-f276c70bb8ff25e7c0ef13e9afc59623a3c135ba.tar.bz2
Reapply "Subtract isn't commutative, fix this for MMX psub." with
a somewhat randomly chosen cpu that will minimize cpu specific differences on bots. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181814 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
-rw-r--r--test/CodeGen/X86/x86-64-psub.ll213
1 files changed, 213 insertions, 0 deletions
diff --git a/test/CodeGen/X86/x86-64-psub.ll b/test/CodeGen/X86/x86-64-psub.ll
new file mode 100644
index 0000000..7869a80
--- /dev/null
+++ b/test/CodeGen/X86/x86-64-psub.ll
@@ -0,0 +1,213 @@
+; RUN: llc -mtriple=x86_64-pc-linux -mcpu=corei7 < %s | FileCheck %s
+
+; MMX packed sub opcodes were wrongly marked as commutative.
+; This test checks that the operands of packed sub instructions are
+; never interchanged by the "Two-Address instruction pass".
+
+declare { i64, double } @getFirstParam()
+declare { i64, double } @getSecondParam()
+
+define i64 @test_psubb() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
+ %3 = bitcast <8 x i8> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
+ %5 = bitcast <8 x i8> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psub.b(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <8 x i8>
+ %8 = bitcast <8 x i8> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubb:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubb [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+define i64 @test_psubw() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
+ %3 = bitcast <4 x i16> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
+ %5 = bitcast <4 x i16> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psub.w(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <4 x i16>
+ %8 = bitcast <4 x i16> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubw:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubw [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+
+define i64 @test_psubd() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <2 x i32>
+ %3 = bitcast <2 x i32> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <2 x i32>
+ %5 = bitcast <2 x i32> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psub.d(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <2 x i32>
+ %8 = bitcast <2 x i32> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubd:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubd [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+define i64 @test_psubsb() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
+ %3 = bitcast <8 x i8> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
+ %5 = bitcast <8 x i8> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psubs.b(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <8 x i8>
+ %8 = bitcast <8 x i8> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubsb:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubsb [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+define i64 @test_psubswv() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
+ %3 = bitcast <4 x i16> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
+ %5 = bitcast <4 x i16> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psubs.w(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <4 x i16>
+ %8 = bitcast <4 x i16> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubswv:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubsw [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+define i64 @test_psubusbv() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
+ %3 = bitcast <8 x i8> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
+ %5 = bitcast <8 x i8> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psubus.b(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <8 x i8>
+ %8 = bitcast <8 x i8> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubusbv:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubusb [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+define i64 @test_psubuswv() {
+entry:
+ %call = tail call { i64, double } @getFirstParam()
+ %0 = extractvalue { i64, double } %call, 0
+ %call2 = tail call { i64, double } @getSecondParam()
+ %1 = extractvalue { i64, double } %call2, 0
+ %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
+ %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
+ %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
+ %3 = bitcast <4 x i16> %2 to x86_mmx
+ %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
+ %5 = bitcast <4 x i16> %4 to x86_mmx
+ %6 = tail call x86_mmx @llvm.x86.mmx.psubus.w(x86_mmx %3, x86_mmx %5) nounwind
+ %7 = bitcast x86_mmx %6 to <4 x i16>
+ %8 = bitcast <4 x i16> %7 to <1 x i64>
+ %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
+ ret i64 %retval.0.extract.i15
+}
+
+; CHECK: test_psubuswv:
+; CHECK: callq getFirstParam
+; CHECK: callq getSecondParam
+; CHECK: movd %rax, [[PARAM2:%[a-z0-9]+]]
+; CHECK: movq (%rsp), [[PARAM1:%[a-z0-9]+]]
+; CHECK: psubusw [[PARAM2]], [[PARAM1]]
+; CHECK: ret
+
+
+declare x86_mmx @llvm.x86.mmx.psubus.w(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psubus.b(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psubs.w(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psubs.b(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psub.d(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psub.w(x86_mmx, x86_mmx) nounwind readnone
+
+declare x86_mmx @llvm.x86.mmx.psub.b(x86_mmx, x86_mmx) nounwind readnone