[X86] Don't match TESTrr from (cmp (and X, Y), 0) during isel. Defer to post processing

The (cmp (and X, Y) 0) pattern is greedy and ends up forming a TESTrr and consuming the and when it might be better to use one of the BMI/TBM like BLSR or BLSI.

This patch moves removes the pattern from isel and adds a post processing check to combine TESTrr+ANDrr into just a TESTrr. With this patch we are able to select the BMI/TBM instructions, but we'll also emit a TESTrr when the result is compared to 0. In many cases the peephole pass will be able to use optimizeCompareInstr to remove the TEST, but its probably not perfect.

Differential Revision: https://reviews.llvm.org/D55870

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@349661 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelDAGToDAG.cpp b/lib/Target/X86/X86ISelDAGToDAG.cpp
index 43d0538c4cda660d9646c6335e802ac22890029b..4ebc157b351b8411ea17dd472fbf8fc66f4dc0ba 100644 (file)
--- a/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -898,9 +898,30 @@ void X86DAGToDAGISel::PostprocessISelDAG() {
       continue;
     }
 
-    // Attempt to remove vectors moves that were inserted to zero upper bits.
+    // Look for a TESTrr+ANDrr pattern where both operands of the test are
+    // the same. Rewrite to remove the AND.
+    unsigned Opc = N->getMachineOpcode();
+    if ((Opc == X86::TEST8rr || Opc == X86::TEST16rr ||
+         Opc == X86::TEST32rr || Opc == X86::TEST64rr) &&
+        N->getOperand(0) == N->getOperand(1) &&
+        N->isOnlyUserOf(N->getOperand(0).getNode()) &&
+        N->getOperand(0).isMachineOpcode()) {
+      SDValue And = N->getOperand(0);
+      unsigned N0Opc = And.getMachineOpcode();
+      if (N0Opc == X86::AND8rr || N0Opc == X86::AND16rr ||
+          N0Opc == X86::AND32rr || N0Opc == X86::AND64rr) {
+        MachineSDNode *Test = CurDAG->getMachineNode(Opc, SDLoc(N),
+                                                     MVT::i32,
+                                                     And.getOperand(0),
+                                                     And.getOperand(1));
+        ReplaceUses(N, Test);
+        MadeChange = true;
+        continue;
+      }
+    }
 
-    if (N->getMachineOpcode() != TargetOpcode::SUBREG_TO_REG)
+    // Attempt to remove vectors moves that were inserted to zero upper bits.
+    if (Opc != TargetOpcode::SUBREG_TO_REG)
       continue;
 
     unsigned SubRegIdx = N->getConstantOperandVal(2);

diff --git a/lib/Target/X86/X86InstrArithmetic.td b/lib/Target/X86/X86InstrArithmetic.td
index 3288fe22f65ac003fa501d6d9712a7f9d3ae90aa..02379af4b4de2f161d22f211d731933ce7052715 100644 (file)
--- a/lib/Target/X86/X86InstrArithmetic.td
+++ b/lib/Target/X86/X86InstrArithmetic.td
@@ -1212,10 +1212,13 @@ def X86testpat : PatFrag<(ops node:$lhs, node:$rhs),
 let isCompare = 1 in {
   let Defs = [EFLAGS] in {
     let isCommutable = 1 in {
-      def TEST8rr  : BinOpRR_F<0x84, "test", Xi8 , X86testpat>;
-      def TEST16rr : BinOpRR_F<0x84, "test", Xi16, X86testpat>;
-      def TEST32rr : BinOpRR_F<0x84, "test", Xi32, X86testpat>;
-      def TEST64rr : BinOpRR_F<0x84, "test", Xi64, X86testpat>;
+      // Avoid selecting these and instead use a test+and. Post processing will
+      // combine them. This gives bunch of other patterns that start with
+      // and a chance to match.
+      def TEST8rr  : BinOpRR_F<0x84, "test", Xi8 , null_frag>;
+      def TEST16rr : BinOpRR_F<0x84, "test", Xi16, null_frag>;
+      def TEST32rr : BinOpRR_F<0x84, "test", Xi32, null_frag>;
+      def TEST64rr : BinOpRR_F<0x84, "test", Xi64, null_frag>;
     } // isCommutable
 
     def TEST8mr    : BinOpMR_F<0x84, "test", Xi8 , X86testpat>;

diff --git a/test/CodeGen/X86/bmi.ll b/test/CodeGen/X86/bmi.ll
index 5642f7c6e435b4ab1811c442380fc3b406af7d57..03d6df03c318b18f7c8dce7b4f6982758c6389e4 100644 (file)
--- a/test/CodeGen/X86/bmi.ll
+++ b/test/CodeGen/X86/bmi.ll
@@ -519,10 +519,7 @@ define i32 @blsi32_z(i32 %a, i32 %b) nounwind {
 define i32 @blsi32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; X86-LABEL: blsi32_z2:
 ; X86:       # %bb.0:
-; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    movl %eax, %ecx
-; X86-NEXT:    negl %ecx
-; X86-NEXT:    testl %eax, %ecx
+; X86-NEXT:    blsil {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    leal {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    cmovel %eax, %ecx
@@ -532,9 +529,7 @@ define i32 @blsi32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; X64-LABEL: blsi32_z2:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    movl %edi, %ecx
-; X64-NEXT:    negl %ecx
-; X64-NEXT:    testl %edi, %ecx
+; X64-NEXT:    blsil %edi, %ecx
 ; X64-NEXT:    cmovnel %edx, %eax
 ; X64-NEXT:    retq
   %t0 = sub i32 0, %a
@@ -629,9 +624,7 @@ define i64 @blsi64_z2(i64 %a, i64 %b, i64 %c) nounwind {
 ; X64-LABEL: blsi64_z2:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq %rsi, %rax
-; X64-NEXT:    movq %rdi, %rcx
-; X64-NEXT:    negq %rcx
-; X64-NEXT:    testq %rdi, %rcx
+; X64-NEXT:    blsiq %rdi, %rcx
 ; X64-NEXT:    cmovneq %rdx, %rax
 ; X64-NEXT:    retq
   %t0 = sub i64 0, %a
@@ -875,9 +868,7 @@ define i32 @blsr32_z(i32 %a, i32 %b) nounwind {
 define i32 @blsr32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; X86-LABEL: blsr32_z2:
 ; X86:       # %bb.0:
-; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    leal -1(%eax), %ecx
-; X86-NEXT:    testl %eax, %ecx
+; X86-NEXT:    blsrl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    leal {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    cmovel %eax, %ecx
@@ -887,9 +878,7 @@ define i32 @blsr32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; X64-LABEL: blsr32_z2:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    # kill: def $edi killed $edi def $rdi
-; X64-NEXT:    leal -1(%rdi), %ecx
-; X64-NEXT:    testl %edi, %ecx
+; X64-NEXT:    blsrl %edi, %ecx
 ; X64-NEXT:    cmovnel %edx, %eax
 ; X64-NEXT:    retq
   %t0 = sub i32 %a, 1
@@ -984,8 +973,7 @@ define i64 @blsr64_z2(i64 %a, i64 %b, i64 %c) nounwind {
 ; X64-LABEL: blsr64_z2:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq %rsi, %rax
-; X64-NEXT:    leaq -1(%rdi), %rcx
-; X64-NEXT:    testq %rdi, %rcx
+; X64-NEXT:    blsrq %rdi, %rcx
 ; X64-NEXT:    cmovneq %rdx, %rax
 ; X64-NEXT:    retq
   %t0 = sub i64 %a, 1

diff --git a/test/CodeGen/X86/tbm_patterns.ll b/test/CodeGen/X86/tbm_patterns.ll
index 7ebc5dd0d129aaff17b53a739eb38ee3ea1206ab..65cc92ca853ef7dbee963a34dc946b7c1ec81c31 100644 (file)
--- a/test/CodeGen/X86/tbm_patterns.ll
+++ b/test/CodeGen/X86/tbm_patterns.ll
@@ -150,9 +150,7 @@ define i32 @test_x86_tbm_blcfill_u32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_blcfill_u32_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl %esi, %eax
-; CHECK-NEXT:    # kill: def $edi killed $edi def $rdi
-; CHECK-NEXT:    leal 1(%rdi), %ecx
-; CHECK-NEXT:    testl %edi, %ecx
+; CHECK-NEXT:    blcfilll %edi, %ecx
 ; CHECK-NEXT:    cmovnel %edx, %eax
 ; CHECK-NEXT:    retq
   %t0 = add i32 %a, 1
@@ -189,8 +187,7 @@ define i64 @test_x86_tbm_blcfill_u64_z2(i64 %a, i64 %b, i64 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_blcfill_u64_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq %rsi, %rax
-; CHECK-NEXT:    leaq 1(%rdi), %rcx
-; CHECK-NEXT:    testq %rdi, %rcx
+; CHECK-NEXT:    blcfillq %rdi, %rcx
 ; CHECK-NEXT:    cmovneq %rdx, %rax
 ; CHECK-NEXT:    retq
   %t0 = add i64 %a, 1
@@ -334,10 +331,7 @@ define i32 @test_x86_tbm_blcic_u32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_blcic_u32_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl %esi, %eax
-; CHECK-NEXT:    movl %edi, %ecx
-; CHECK-NEXT:    notl %ecx
-; CHECK-NEXT:    incl %edi
-; CHECK-NEXT:    testl %ecx, %edi
+; CHECK-NEXT:    blcicl %edi, %ecx
 ; CHECK-NEXT:    cmovnel %edx, %eax
 ; CHECK-NEXT:    retq
   %t0 = xor i32 %a, -1
@@ -377,10 +371,7 @@ define i64 @test_x86_tbm_blcic_u64_z2(i64 %a, i64 %b, i64 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_blcic_u64_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq %rsi, %rax
-; CHECK-NEXT:    movq %rdi, %rcx
-; CHECK-NEXT:    notq %rcx
-; CHECK-NEXT:    incq %rdi
-; CHECK-NEXT:    testq %rcx, %rdi
+; CHECK-NEXT:    blcicq %rdi, %rcx
 ; CHECK-NEXT:    cmovneq %rdx, %rax
 ; CHECK-NEXT:    retq
   %t0 = xor i64 %a, -1
@@ -823,10 +814,7 @@ define i32 @test_x86_tbm_tzmsk_u32_z2(i32 %a, i32 %b, i32 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_tzmsk_u32_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl %esi, %eax
-; CHECK-NEXT:    movl %edi, %ecx
-; CHECK-NEXT:    notl %ecx
-; CHECK-NEXT:    decl %edi
-; CHECK-NEXT:    testl %edi, %ecx
+; CHECK-NEXT:    tzmskl %edi, %ecx
 ; CHECK-NEXT:    cmovnel %edx, %eax
 ; CHECK-NEXT:    retq
   %t0 = xor i32 %a, -1
@@ -866,10 +854,7 @@ define i64 @test_x86_tbm_tzmsk_u64_z2(i64 %a, i64 %b, i64 %c) nounwind {
 ; CHECK-LABEL: test_x86_tbm_tzmsk_u64_z2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq %rsi, %rax
-; CHECK-NEXT:    movq %rdi, %rcx
-; CHECK-NEXT:    notq %rcx
-; CHECK-NEXT:    decq %rdi
-; CHECK-NEXT:    testq %rdi, %rcx
+; CHECK-NEXT:    tzmskq %rdi, %rcx
 ; CHECK-NEXT:    cmovneq %rdx, %rax
 ; CHECK-NEXT:    retq
   %t0 = xor i64 %a, -1