mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
91f450a3a0
Summary:
We noticed in Julia that the sequence below no longer turned into
a sequence of FMA instructions in LLVM 7+, but it did in LLVM 6.
```
%29 = fmul contract <4 x double> %wide.load, %wide.load16
%30 = fmul contract <4 x double> %wide.load13, %wide.load17
%31 = fmul contract <4 x double> %wide.load14, %wide.load18
%32 = fmul contract <4 x double> %wide.load15, %wide.load19
%33 = fadd fast <4 x double> %vec.phi, %29
%34 = fadd fast <4 x double> %vec.phi10, %30
%35 = fadd fast <4 x double> %vec.phi11, %31
%36 = fadd fast <4 x double> %vec.phi12, %32
```
Unlike Clang, Julia doesn't set the `unsafe-fp-math=true` function
attribute, but rather emits more local instruction flags.
This partially undoes https://reviews.llvm.org/D46854 and if required I can try to minimize the test further.
Reviewers: spatel, mcberg2017
Reviewed By: spatel
Subscribers: chriselrod, merge_guards_bot, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71495
27 lines
1.2 KiB
LLVM
27 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=fma | FileCheck %s
|
|
|
|
; Propagation of IR FMF should not drop flags when adding the DAG reduction flag.
|
|
; This should include an FMA instruction, not separate FMUL/FADD.
|
|
|
|
define double @julia_dotf(<4 x double> %x, <4 x double> %y, <4 x double> %z, i1 %t3) {
|
|
; CHECK-LABEL: julia_dotf:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vfmadd213pd {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
|
|
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
|
|
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul contract <4 x double> %x, %y
|
|
%t2 = fadd fast <4 x double> %z, %t1
|
|
%rdx.shuf = shufflevector <4 x double> %t2, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
|
%bin.rdx22 = fadd fast <4 x double> %t2, %rdx.shuf
|
|
%rdx.shuf23 = shufflevector <4 x double> %bin.rdx22, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%bin.rdx24 = fadd fast <4 x double> %bin.rdx22, %rdx.shuf23
|
|
%t4 = extractelement <4 x double> %bin.rdx24, i32 0
|
|
ret double %t4
|
|
}
|
|
|