aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorEvandro Menezes <e.menezes@samsung.com>2019-08-05 18:09:14 +0000
committerEvandro Menezes <e.menezes@samsung.com>2019-08-05 18:09:14 +0000
commita005c1ac4f3bdadf8643888c2168ebe432649e2e (patch)
treec34dec57e8f0bb76137a16a70e9b9057de1ecbac /llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
parent[InstCombine][NFC] Tests for non-canonical clamp-like pattern (diff)
downloadllvm-project-a005c1ac4f3bdadf8643888c2168ebe432649e2e.tar.gz
llvm-project-a005c1ac4f3bdadf8643888c2168ebe432649e2e.tar.bz2
llvm-project-a005c1ac4f3bdadf8643888c2168ebe432649e2e.zip
[AArch64] Expand bcmp() for small block lengths
Patch D56593 by @courbet results in calls to `bcmp()` in some cases, should the target support the it. Unless `TTI::MemCmpExpansionOptions()` is overridden by the target. In a proprietary benchmark we see a performance drop of about 12% on PNG compression before this patch, though it passes all tests. This patch mirrors X86 for AArch64 and initializes `TTI::MemCmpExpansionOptions()` to then expand calls to `bcmp()` when appropriate. No tuning of the parameters was performed, but, at this point, it's enough to recover the performance drop above. This problem also exists on ARM. Once a consensus is reached for AArch64, we can work to fix ARM as well. Authors: - Evandro Menezes (@evandro) <e.menezes@samsung.com> - Brian Rzycki (@brzycki) <b.rzycki@samsung.com> Differential revision: https://reviews.llvm.org/D64805 llvm-svn: 367898
Diffstat (limited to 'llvm/test/CodeGen/AArch64/bcmp-inline-small.ll')
-rw-r--r--llvm/test/CodeGen/AArch64/bcmp-inline-small.ll44
1 files changed, 44 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll b/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
new file mode 100644
index 000000000000..da42b1d6863c
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
@@ -0,0 +1,44 @@
+; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu | FileCheck %s --check-prefixes=CHECK,CHECKN
+; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu -mattr=strict-align | FileCheck %s --check-prefixes=CHECK,CHECKS
+
+declare i32 @bcmp(i8*, i8*, i64) nounwind readonly
+declare i32 @memcmp(i8*, i8*, i64) nounwind readonly
+
+define i1 @bcmp_b2(i8* %s1, i8* %s2) {
+entry:
+ %bcmp = call i32 @bcmp(i8* %s1, i8* %s2, i64 15)
+ %ret = icmp eq i32 %bcmp, 0
+ ret i1 %ret
+
+; CHECK-LABEL: bcmp_b2:
+; CHECK-NOT: bl bcmp
+; CHECKN: ldr x
+; CHECKN-NEXT: ldr x
+; CHECKN-NEXT: ldur x
+; CHECKN-NEXT: ldur x
+; CHECKS: ldr x
+; CHECKS-NEXT: ldr x
+; CHECKS-NEXT: ldr w
+; CHECKS-NEXT: ldr w
+; CHECKS-NEXT: ldrh w
+; CHECKS-NEXT: ldrh w
+; CHECKS-NEXT: ldrb w
+; CHECKS-NEXT: ldrb w
+}
+
+define i1 @bcmp_bs(i8* %s1, i8* %s2) optsize {
+entry:
+ %memcmp = call i32 @memcmp(i8* %s1, i8* %s2, i64 31)
+ %ret = icmp eq i32 %memcmp, 0
+ ret i1 %ret
+
+; CHECK-LABEL: bcmp_bs:
+; CHECKN-NOT: bl memcmp
+; CHECKN: ldp x
+; CHECKN-NEXT: ldp x
+; CHECKN-NEXT: ldr x
+; CHECKN-NEXT: ldr x
+; CHECKN-NEXT: ldur x
+; CHECKN-NEXT: ldur x
+; CHECKS: bl memcmp
+}