[PATCH] D26790: [X86] Add a hasOneUse check to selectScalarSSELoad to keep the same load from being folded multiple times
Zvi Rackover via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 16 23:46:36 PST 2016
zvi added inline comments.
================
Comment at: test/CodeGen/X86/vec_ss_load_fold.ll:384
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: movaps %xmm0, %xmm1
-; X32-NEXT: minss (%eax), %xmm1
-; X32-NEXT: maxss (%eax), %xmm0
-; X32-NEXT: addps %xmm1, %xmm0
+; X32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X32-NEXT: movaps %xmm0, %xmm2
----------------
As the change in generated code shows, the tradeoff is increased register pressure. Do we have reason to believe that this change puts us on the preferred side?
https://reviews.llvm.org/D26790
More information about the llvm-commits
mailing list