summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorCraig Topper <craig.topper@sifive.com>2021-06-12 09:49:32 -0700
committerTom Stellard <tstellar@redhat.com>2021-06-15 00:50:16 -0400
commita066f4eb679488cfeed2fec24574adcb55f367a1 (patch)
treea77b0bda82325e2f162354509e606fd12ee585cc
parentadae17728bad62fa9ce1635905d0b0bde30e3eba (diff)
[X86] Add ISD::FREEZE and ISD::AssertAlign to the list of opcodes that don't guarantee upper 32 bits are zero.
The freeze issue was reported here https://llvm.discourse.group/t/bug-or-feature-freeze-instruction/3639 I don't have a test for AssertAlign. I just noticed it was missing and assume it should be similar to the other two Asserts. Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D104178 (cherry picked from commit c997867dc084a1bcf631816f964b3ff49a297ba3)
-rw-r--r--llvm/lib/Target/X86/X86InstrCompiler.td11
-rw-r--r--llvm/test/CodeGen/X86/freeze.ll23
2 files changed, 30 insertions, 4 deletions
diff --git a/llvm/lib/Target/X86/X86InstrCompiler.td b/llvm/lib/Target/X86/X86InstrCompiler.td
index 7a2facf226d8..dc6361aecc60 100644
--- a/llvm/lib/Target/X86/X86InstrCompiler.td
+++ b/llvm/lib/Target/X86/X86InstrCompiler.td
@@ -1344,15 +1344,18 @@ def : Pat<(i32 (anyext_sdiv GR8:$src)), (MOVSX32rr8 GR8:$src)>;
// Any instruction that defines a 32-bit result leaves the high half of the
// register. Truncate can be lowered to EXTRACT_SUBREG. CopyFromReg may
-// be copying from a truncate. Any other 32-bit operation will zero-extend
-// up to 64 bits. AssertSext/AssertZext aren't saying anything about the upper
-// 32 bits, they're probably just qualifying a CopyFromReg.
+// be copying from a truncate. AssertSext/AssertZext/AssertAlign aren't saying
+// anything about the upper 32 bits, they're probably just qualifying a
+// CopyFromReg. FREEZE may be coming from a a truncate. Any other 32-bit
+// operation will zero-extend up to 64 bits.
def def32 : PatLeaf<(i32 GR32:$src), [{
return N->getOpcode() != ISD::TRUNCATE &&
N->getOpcode() != TargetOpcode::EXTRACT_SUBREG &&
N->getOpcode() != ISD::CopyFromReg &&
N->getOpcode() != ISD::AssertSext &&
- N->getOpcode() != ISD::AssertZext;
+ N->getOpcode() != ISD::AssertZext &&
+ N->getOpcode() != ISD::AssertAlign &&
+ N->getOpcode() != ISD::FREEZE;
}]>;
// In the case of a 32-bit def that is known to implicitly zero-extend,
diff --git a/llvm/test/CodeGen/X86/freeze.ll b/llvm/test/CodeGen/X86/freeze.ll
index cf015d3c892c..7131f3a5bc4f 100644
--- a/llvm/test/CodeGen/X86/freeze.ll
+++ b/llvm/test/CodeGen/X86/freeze.ll
@@ -122,3 +122,26 @@ define i64 @freeze_array() {
%t1 = add i64 %v1, %v2
ret i64 %t1
}
+
+; Make sure we emit a movl to zext the input before the imulq. This previously
+; failed because freeze was not listed in the instructions that don't zext their
+; result in the def32 pattern X86InstrCompiler.td.
+define i32 @freeze_zext(i64 %a) nounwind {
+; X86ASM-LABEL: freeze_zext:
+; X86ASM: # %bb.0: # %entry
+; X86ASM-NEXT: movq %rdi, %rax
+; X86ASM-NEXT: movl %eax, %ecx
+; X86ASM-NEXT: movl $3435973837, %edx # imm = 0xCCCCCCCD
+; X86ASM-NEXT: imulq %rcx, %rdx
+; X86ASM-NEXT: shrq $35, %rdx
+; X86ASM-NEXT: addl %edx, %edx
+; X86ASM-NEXT: leal (%rdx,%rdx,4), %ecx
+; X86ASM-NEXT: subl %ecx, %eax
+; X86ASM-NEXT: # kill: def $eax killed $eax killed $rax
+; X86ASM-NEXT: retq
+entry:
+ %x = trunc i64 %a to i32
+ %y = freeze i32 %x
+ %z = urem i32 %y, 10
+ ret i32 %z
+}