[llvm] [InstCombine] Optimize `sinh` and `cosh` divisions (PR #81433)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Wed Mar 27 01:44:08 PDT 2024


================
@@ -0,0 +1,114 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -passes=instcombine < %s | FileCheck %s
+
+define double @fdiv_cosh_sinh(double %a) {
+; CHECK-LABEL: @fdiv_cosh_sinh(
+; CHECK-NEXT:    [[TMP1:%.*]] = call double @cosh(double [[A:%.*]])
+; CHECK-NEXT:    [[TMP2:%.*]] = call double @sinh(double [[A]])
+; CHECK-NEXT:    [[DIV:%.*]] = fdiv double [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret double [[DIV]]
+;
+  %1 = call double @cosh(double %a)
+  %2 = call double @sinh(double %a)
+  %div = fdiv double %1, %2
+  ret double %div
+}
+
+define double @fdiv_strict_cosh_strict_sinh_reassoc(double %a) {
+; CHECK-LABEL: @fdiv_strict_cosh_strict_sinh_reassoc(
+; CHECK-NEXT:    [[TMP1:%.*]] = call double @cosh(double [[A:%.*]])
+; CHECK-NEXT:    [[TMP2:%.*]] = call reassoc double @sinh(double [[A]])
+; CHECK-NEXT:    [[DIV:%.*]] = fdiv double [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret double [[DIV]]
+;
+  %1 = call double @cosh(double %a)
+  %2 = call reassoc double @sinh(double %a)
+  %div = fdiv double %1, %2
+  ret double %div
+}
+
+define double @fdiv_reassoc_cosh_strict_sinh_strict(double %a, ptr dereferenceable(2) %dummy) {
+; CHECK-LABEL: @fdiv_reassoc_cosh_strict_sinh_strict(
+; CHECK-NEXT:    [[TANH:%.*]] = call reassoc double @tanh(double [[A]])
+; CHECK-NEXT:    [[DIV:%.*]] = fdiv reassoc double 1.000000e+00, [[TANH]]
+; CHECK-NEXT:    ret double [[DIV]]
+;
+  %1 = call double @cosh(double %a)
+  %2 = call double @sinh(double %a)
+  %div = fdiv reassoc double %1, %2
----------------
arsenm wrote:

My interpretation of contract is allow increasing precision, in exactly the same way as FMA. I don't think it makes sense to have an entire flag that can only be interpreted for a single instruction, and we should try to interpret it in cases like this. Approximate functions has the implication that it's worse 

https://github.com/llvm/llvm-project/pull/81433


More information about the llvm-commits mailing list