Subtract isn't commutative, fix this for MMX psub.

Patch by Andrea DiBiagio.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181809 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 220 insertions, 7 deletions

diff --git a/lib/Target/X86/X86InstrMMX.td b/lib/Target/X86/X86InstrMMX.td
index 49721df7c1..07314a092c 100644
--- a/lib/Target/X86/X86InstrMMX.td
+++ b/lib/Target/X86/X86InstrMMX.td
@@ -357,21 +357,21 @@ defm MMX_PHADDSW : SS3I_binop_rm_int_mm<0x03, "phaddsw",int_x86_ssse3_phadd_sw,
 defm MMX_PSUBB : MMXI_binop_rm_int<0xF8, "psubb", int_x86_mmx_psub_b,
                                    MMX_INTALU_ITINS>;
 defm MMX_PSUBW : MMXI_binop_rm_int<0xF9, "psubw", int_x86_mmx_psub_w,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 defm MMX_PSUBD : MMXI_binop_rm_int<0xFA, "psubd", int_x86_mmx_psub_d,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 defm MMX_PSUBQ : MMXI_binop_rm_int<0xFB, "psubq", int_x86_mmx_psub_q,
-                                   MMX_INTALUQ_ITINS, 1>;
+                                   MMX_INTALUQ_ITINS>;
 
 defm MMX_PSUBSB  : MMXI_binop_rm_int<0xE8, "psubsb" , int_x86_mmx_psubs_b,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 defm MMX_PSUBSW  : MMXI_binop_rm_int<0xE9, "psubsw" , int_x86_mmx_psubs_w,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 
 defm MMX_PSUBUSB : MMXI_binop_rm_int<0xD8, "psubusb", int_x86_mmx_psubus_b,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 defm MMX_PSUBUSW : MMXI_binop_rm_int<0xD9, "psubusw", int_x86_mmx_psubus_w,
-                                   MMX_INTALU_ITINS, 1>;
+                                   MMX_INTALU_ITINS>;
 
 defm MMX_PHSUBW  : SS3I_binop_rm_int_mm<0x05, "phsubw", int_x86_ssse3_phsub_w,
                                    MMX_PHADDSUBW>;
diff --git a/test/CodeGen/X86/x86-64-psub.ll b/test/CodeGen/X86/x86-64-psub.ll
new file mode 100644
index 0000000000..1bd2570226
--- /dev/null
+++ b/test/CodeGen/X86/x86-64-psub.ll
@@ -0,0 +1,213 @@
+; RUN: llc -mtriple=x86_64-pc-linux < %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