[llvm] [IR] Add `llvm.modf` intrinsic (PR #121948)

[Benjamin Maxwell via llvm-commits]

================
@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --filter "(bl|ptrue)" --version 5
+; RUN: llc -mtriple=aarch64-gnu-linux -mattr=+neon,+sve -vector-library=sleefgnuabi < %s | FileCheck %s -check-prefix=SLEEF
+; RUN: llc -mtriple=aarch64-gnu-linux -mattr=+neon,+sve -vector-library=ArmPL < %s | FileCheck %s -check-prefix=ARMPL
+
+define <4 x float> @test_modf_v4f32(<4 x float> %x, ptr %out_integral) {
+; SLEEF-LABEL: test_modf_v4f32:
+; SLEEF:    bl _ZGVnN4vl4_modff
+;
+; ARMPL-LABEL: test_modf_v4f32:
+; ARMPL:    bl armpl_vmodfq_f32
----------------
MacDue wrote:

I've added `modf_store_merging_load_before_store()` and you can see the behaviour is correct (the load is before the call, and the value is saved around the call). 

https://github.com/llvm/llvm-project/pull/121948