RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity
a3d207d6bc
llvm-mirror/test/CodeGen/PowerPC/vsx.ll
Nemanja Ivanovic f6f0a5745d [PowerPC] Canonicalize shuffles to match more single-instruction masks on LE 
We currently miss a number of opportunities to emit single-instruction
VMRG[LH][BHW] instructions for shuffles on little endian subtargets. Although
this in itself is not a huge performance opportunity since loading the permute
vector for a VPERM can always be pulled out of loops, producing such merge
instructions is useful to downstream optimizations.
Since VPERM is essentially opaque to all subsequent optimizations, we want to
avoid it as much as possible. Other permute instructions have semantics that can
be reasoned about much more easily in later optimizations.

This patch does the following:
- Canonicalize shuffles so that the first element comes from the first vector
  (since that's what most of the mask matching functions want)
- Switch the elements that come from splat vectors so that they match the
  corresponding elements from the other vector (to allow for merges)
- Adds debugging messages for when a shuffle is matched to a VPERM so that
  anyone interested in improving this further can get the info for their code

Differential revision: https://reviews.llvm.org/D77448
2020-06-18 21:54:22 -05:00

2524 lines
67 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr7 \
; RUN: -mtriple=powerpc64-unknown-linux-gnu -mattr=+vsx \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr7 \
; RUN: -mtriple=powerpc64-unknown-linux-gnu -mattr=+vsx \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck \
; RUN: -check-prefix=CHECK-REG %s
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr7 \
; RUN: -mtriple=powerpc64-unknown-linux-gnu -mattr=+vsx -fast-isel -O0 \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck \
; RUN: -check-prefix=CHECK-FISL %s
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr8 \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu -mattr=+vsx \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck \
; RUN: -check-prefix=CHECK-LE %s
define double @test1(double %a, double %b) {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xsmuldp f1, f1, f2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test1:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xsmuldp f1, f1, f2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test1:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xsmuldp f1, f1, f2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test1:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xsmuldp f1, f1, f2
; CHECK-LE-NEXT: blr
entry:
%v = fmul double %a, %b
ret double %v
}
define double @test2(double %a, double %b) {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xsdivdp f1, f1, f2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test2:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xsdivdp f1, f1, f2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test2:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xsdivdp f1, f1, f2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test2:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xsdivdp f1, f1, f2
; CHECK-LE-NEXT: blr
entry:
%v = fdiv double %a, %b
ret double %v
}
define double @test3(double %a, double %b) {
; CHECK-LABEL: test3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xsadddp f1, f1, f2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test3:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xsadddp f1, f1, f2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test3:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xsadddp f1, f1, f2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test3:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xsadddp f1, f1, f2
; CHECK-LE-NEXT: blr
entry:
%v = fadd double %a, %b
ret double %v
}
define <2 x double> @test4(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test4:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvadddp v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test4:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xvadddp v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test4:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xvadddp v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test4:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvadddp v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = fadd <2 x double> %a, %b
ret <2 x double> %v
}
define <4 x i32> @test5(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test5:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlxor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test5:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlxor v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test5:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlxor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = xor <4 x i32> %a, %b
ret <4 x i32> %v
}
define <8 x i16> @test6(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test6:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlxor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test6:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlxor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test6:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlxor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = xor <8 x i16> %a, %b
ret <8 x i16> %v
}
define <16 x i8> @test7(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: test7:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test7:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlxor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test7:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlxor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test7:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlxor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = xor <16 x i8> %a, %b
ret <16 x i8> %v
}
define <4 x i32> @test8(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test8:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test8:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test8:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test8:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <4 x i32> %a, %b
ret <4 x i32> %v
}
define <8 x i16> @test9(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test9:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test9:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test9:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test9:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <8 x i16> %a, %b
ret <8 x i16> %v
}
define <16 x i8> @test10(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: test10:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test10:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test10:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test10:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <16 x i8> %a, %b
ret <16 x i8> %v
}
define <4 x i32> @test11(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test11:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxland v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test11:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxland v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test11:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxland v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test11:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxland v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = and <4 x i32> %a, %b
ret <4 x i32> %v
}
define <8 x i16> @test12(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test12:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxland v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test12:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxland v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test12:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxland vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test12:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxland v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = and <8 x i16> %a, %b
ret <8 x i16> %v
}
define <16 x i8> @test13(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: test13:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxland v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test13:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxland v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test13:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxland vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test13:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxland v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = and <16 x i8> %a, %b
ret <16 x i8> %v
}
define <4 x i32> @test14(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test14:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlnor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test14:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlnor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test14:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
; CHECK-FISL-NEXT: xxlnor v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test14:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlnor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <4 x i32> %a, %b
%w = xor <4 x i32> %v, <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %w
}
define <8 x i16> @test15(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test15:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlnor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test15:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlnor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test15:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
; CHECK-FISL-NEXT: xxlnor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test15:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlnor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <8 x i16> %a, %b
%w = xor <8 x i16> %v, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
ret <8 x i16> %w
}
define <16 x i8> @test16(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: test16:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlnor v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test16:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlnor v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test16:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
; CHECK-FISL-NEXT: xxlnor vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test16:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlnor v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%v = or <16 x i8> %a, %b
%w = xor <16 x i8> %v, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
ret <16 x i8> %w
}
define <4 x i32> @test17(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test17:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlandc v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test17:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlandc v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test17:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlnor vs0, v3, v3
; CHECK-FISL-NEXT: xxland v2, v2, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test17:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlandc v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%w = xor <4 x i32> %b, <i32 -1, i32 -1, i32 -1, i32 -1>
%v = and <4 x i32> %a, %w
ret <4 x i32> %v
}
define <8 x i16> @test18(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test18:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlandc v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test18:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlandc v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test18:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlnor vs0, v3, v3
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
; CHECK-FISL-NEXT: xxlandc vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test18:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlandc v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%w = xor <8 x i16> %b, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%v = and <8 x i16> %a, %w
ret <8 x i16> %v
}
define <16 x i8> @test19(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: test19:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlandc v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test19:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xxlandc v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test19:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xxlnor vs0, v3, v3
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
; CHECK-FISL-NEXT: xxlandc vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test19:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xxlandc v2, v2, v3
; CHECK-LE-NEXT: blr
entry:
%w = xor <16 x i8> %b, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%v = and <16 x i8> %a, %w
ret <16 x i8> %v
}
define <4 x i32> @test20(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) {
; CHECK-LABEL: test20:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vcmpequw v4, v4, v5
; CHECK-NEXT: xxsel v2, v3, v2, v4
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test20:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: vcmpequw v4, v4, v5
; CHECK-REG-NEXT: xxsel v2, v3, v2, v4
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test20:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: vcmpequw v4, v4, v5
; CHECK-FISL-NEXT: xxsel v2, v3, v2, v4
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test20:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: vcmpequw v4, v4, v5
; CHECK-LE-NEXT: xxsel v2, v3, v2, v4
; CHECK-LE-NEXT: blr
entry:
%m = icmp eq <4 x i32> %c, %d
%v = select <4 x i1> %m, <4 x i32> %a, <4 x i32> %b
ret <4 x i32> %v
}
define <4 x float> @test21(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d) {
; CHECK-LABEL: test21:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvcmpeqsp vs0, v4, v5
; CHECK-NEXT: xxsel v2, v3, v2, vs0
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test21:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xvcmpeqsp vs0, v4, v5
; CHECK-REG-NEXT: xxsel v2, v3, v2, vs0
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test21:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xvcmpeqsp vs0, v4, v5
; CHECK-FISL-NEXT: xxsel v2, v3, v2, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test21:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvcmpeqsp vs0, v4, v5
; CHECK-LE-NEXT: xxsel v2, v3, v2, vs0
; CHECK-LE-NEXT: blr
entry:
%m = fcmp oeq <4 x float> %c, %d
%v = select <4 x i1> %m, <4 x float> %a, <4 x float> %b
ret <4 x float> %v
}
define <4 x float> @test22(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d) {
; CHECK-LABEL: test22:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvcmpeqsp vs0, v5, v5
; CHECK-NEXT: xvcmpeqsp vs1, v4, v4
; CHECK-NEXT: xvcmpeqsp vs2, v4, v5
; CHECK-NEXT: xxlnor vs0, vs0, vs0
; CHECK-NEXT: xxlnor vs1, vs1, vs1
; CHECK-NEXT: xxlor vs0, vs1, vs0
; CHECK-NEXT: xxlor vs0, vs2, vs0
; CHECK-NEXT: xxsel v2, v3, v2, vs0
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test22:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xvcmpeqsp vs0, v5, v5
; CHECK-REG-NEXT: xvcmpeqsp vs1, v4, v4
; CHECK-REG-NEXT: xvcmpeqsp vs2, v4, v5
; CHECK-REG-NEXT: xxlnor vs0, vs0, vs0
; CHECK-REG-NEXT: xxlnor vs1, vs1, vs1
; CHECK-REG-NEXT: xxlor vs0, vs1, vs0
; CHECK-REG-NEXT: xxlor vs0, vs2, vs0
; CHECK-REG-NEXT: xxsel v2, v3, v2, vs0
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test22:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xvcmpeqsp vs0, v4, v5
; CHECK-FISL-NEXT: xvcmpeqsp vs1, v5, v5
; CHECK-FISL-NEXT: xxlnor vs1, vs1, vs1
; CHECK-FISL-NEXT: xvcmpeqsp vs2, v4, v4
; CHECK-FISL-NEXT: xxlnor vs2, vs2, vs2
; CHECK-FISL-NEXT: xxlor vs1, vs2, vs1
; CHECK-FISL-NEXT: xxlor vs0, vs0, vs1
; CHECK-FISL-NEXT: xxsel v2, v3, v2, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test22:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvcmpeqsp vs0, v5, v5
; CHECK-LE-NEXT: xvcmpeqsp vs1, v4, v4
; CHECK-LE-NEXT: xvcmpeqsp vs2, v4, v5
; CHECK-LE-NEXT: xxlnor vs0, vs0, vs0
; CHECK-LE-NEXT: xxlnor vs1, vs1, vs1
; CHECK-LE-NEXT: xxlor vs0, vs1, vs0
; CHECK-LE-NEXT: xxlor vs0, vs2, vs0
; CHECK-LE-NEXT: xxsel v2, v3, v2, vs0
; CHECK-LE-NEXT: blr
entry:
%m = fcmp ueq <4 x float> %c, %d
%v = select <4 x i1> %m, <4 x float> %a, <4 x float> %b
ret <4 x float> %v
}
define <8 x i16> @test23(<8 x i16> %a, <8 x i16> %b, <8 x i16> %c, <8 x i16> %d) {
; CHECK-LABEL: test23:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vcmpequh v4, v4, v5
; CHECK-NEXT: xxsel v2, v3, v2, v4
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test23:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: vcmpequh v4, v4, v5
; CHECK-REG-NEXT: xxsel v2, v3, v2, v4
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test23:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: vcmpequh v4, v4, v5
; CHECK-FISL-NEXT: xxsel vs0, v3, v2, v4
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test23:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: vcmpequh v4, v4, v5
; CHECK-LE-NEXT: xxsel v2, v3, v2, v4
; CHECK-LE-NEXT: blr
entry:
%m = icmp eq <8 x i16> %c, %d
%v = select <8 x i1> %m, <8 x i16> %a, <8 x i16> %b
ret <8 x i16> %v
}
define <16 x i8> @test24(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) {
; CHECK-LABEL: test24:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vcmpequb v4, v4, v5
; CHECK-NEXT: xxsel v2, v3, v2, v4
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test24:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: vcmpequb v4, v4, v5
; CHECK-REG-NEXT: xxsel v2, v3, v2, v4
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test24:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: vcmpequb v4, v4, v5
; CHECK-FISL-NEXT: xxsel vs0, v3, v2, v4
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test24:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: vcmpequb v4, v4, v5
; CHECK-LE-NEXT: xxsel v2, v3, v2, v4
; CHECK-LE-NEXT: blr
entry:
%m = icmp eq <16 x i8> %c, %d
%v = select <16 x i1> %m, <16 x i8> %a, <16 x i8> %b
ret <16 x i8> %v
}
define <2 x double> @test25(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %d) {
; CHECK-LABEL: test25:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvcmpeqdp vs0, v4, v5
; CHECK-NEXT: xxsel v2, v3, v2, vs0
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test25:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xvcmpeqdp vs0, v4, v5
; CHECK-REG-NEXT: xxsel v2, v3, v2, vs0
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test25:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xvcmpeqdp vs0, v4, v5
; CHECK-FISL-NEXT: xxsel v2, v3, v2, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test25:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvcmpeqdp v4, v4, v5
; CHECK-LE-NEXT: xxsel v2, v3, v2, v4
; CHECK-LE-NEXT: blr
entry:
%m = fcmp oeq <2 x double> %c, %d
%v = select <2 x i1> %m, <2 x double> %a, <2 x double> %b
ret <2 x double> %v
}
define <2 x i64> @test26(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test26:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: addi r4, r1, -48
; CHECK-NEXT: stxvd2x v3, 0, r3
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: add r3, r4, r3
; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: add r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test26:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: addi r4, r1, -48
; CHECK-REG-NEXT: stxvd2x v3, 0, r3
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: add r3, r4, r3
; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: add r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test26:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v3, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: ld r3, -24(r1)
; CHECK-FISL-NEXT: ld r4, -40(r1)
; CHECK-FISL-NEXT: add r3, r4, r3
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: ld r3, -32(r1)
; CHECK-FISL-NEXT: ld r4, -48(r1)
; CHECK-FISL-NEXT: add r3, r4, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test26:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vaddudm v2, v2, v3
; CHECK-LE-NEXT: blr
%v = add <2 x i64> %a, %b
ret <2 x i64> %v
; Make sure we use only two stores (one for each operand).
; FIXME: The code quality here is not good; just make sure we do something for now.
}
define <2 x i64> @test27(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test27:
; CHECK: # %bb.0:
; CHECK-NEXT: xxland v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test27:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxland v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test27:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxland vs0, v2, v3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test27:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxland v2, v2, v3
; CHECK-LE-NEXT: blr
%v = and <2 x i64> %a, %b
ret <2 x i64> %v
}
define <2 x double> @test28(<2 x double>* %a) {
; CHECK-LABEL: test28:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test28:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test28:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvd2x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test28:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: xxswapd v2, vs0
; CHECK-LE-NEXT: blr
%v = load <2 x double>, <2 x double>* %a, align 16
ret <2 x double> %v
}
define void @test29(<2 x double>* %a, <2 x double> %b) {
; CHECK-LABEL: test29:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test29:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test29:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test29:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: stxvd2x vs0, 0, r3
; CHECK-LE-NEXT: blr
store <2 x double> %b, <2 x double>* %a, align 16
ret void
}
define <2 x double> @test28u(<2 x double>* %a) {
; CHECK-LABEL: test28u:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test28u:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test28u:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvd2x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test28u:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: xxswapd v2, vs0
; CHECK-LE-NEXT: blr
%v = load <2 x double>, <2 x double>* %a, align 8
ret <2 x double> %v
}
define void @test29u(<2 x double>* %a, <2 x double> %b) {
; CHECK-LABEL: test29u:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test29u:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test29u:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test29u:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: stxvd2x vs0, 0, r3
; CHECK-LE-NEXT: blr
store <2 x double> %b, <2 x double>* %a, align 8
ret void
}
define <2 x i64> @test30(<2 x i64>* %a) {
; CHECK-LABEL: test30:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test30:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test30:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test30:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: xxswapd v2, vs0
; CHECK-LE-NEXT: blr
%v = load <2 x i64>, <2 x i64>* %a, align 16
ret <2 x i64> %v
}
define void @test31(<2 x i64>* %a, <2 x i64> %b) {
; CHECK-LABEL: test31:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test31:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test31:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test31:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: stxvd2x vs0, 0, r3
; CHECK-LE-NEXT: blr
store <2 x i64> %b, <2 x i64>* %a, align 16
ret void
}
define <4 x float> @test32(<4 x float>* %a) {
; CHECK-LABEL: test32:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvw4x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test32:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test32:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvw4x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test32:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lvx v2, 0, r3
; CHECK-LE-NEXT: blr
%v = load <4 x float>, <4 x float>* %a, align 16
ret <4 x float> %v
}
define void @test33(<4 x float>* %a, <4 x float> %b) {
; CHECK-LABEL: test33:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvw4x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test33:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvw4x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test33:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvw4x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test33:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: stvx v2, 0, r3
; CHECK-LE-NEXT: blr
store <4 x float> %b, <4 x float>* %a, align 16
ret void
}
define <4 x float> @test32u(<4 x float>* %a) {
; CHECK-LABEL: test32u:
; CHECK: # %bb.0:
; CHECK-NEXT: li r4, 15
; CHECK-NEXT: lvsl v3, 0, r3
; CHECK-NEXT: lvx v2, r3, r4
; CHECK-NEXT: lvx v4, 0, r3
; CHECK-NEXT: vperm v2, v4, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test32u:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: li r4, 15
; CHECK-REG-NEXT: lvsl v3, 0, r3
; CHECK-REG-NEXT: lvx v2, r3, r4
; CHECK-REG-NEXT: lvx v4, 0, r3
; CHECK-REG-NEXT: vperm v2, v4, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test32u:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: li r4, 15
; CHECK-FISL-NEXT: lvx v2, r3, r4
; CHECK-FISL-NEXT: lvsl v3, 0, r3
; CHECK-FISL-NEXT: lvx v4, 0, r3
; CHECK-FISL-NEXT: vperm v2, v4, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test32u:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: xxswapd v2, vs0
; CHECK-LE-NEXT: blr
%v = load <4 x float>, <4 x float>* %a, align 8
ret <4 x float> %v
}
define void @test33u(<4 x float>* %a, <4 x float> %b) {
; CHECK-LABEL: test33u:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvw4x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test33u:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvw4x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test33u:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvw4x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test33u:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: stxvd2x vs0, 0, r3
; CHECK-LE-NEXT: blr
store <4 x float> %b, <4 x float>* %a, align 8
ret void
}
define <4 x i32> @test34(<4 x i32>* %a) {
; CHECK-LABEL: test34:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvw4x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test34:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test34:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvw4x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test34:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lvx v2, 0, r3
; CHECK-LE-NEXT: blr
%v = load <4 x i32>, <4 x i32>* %a, align 16
ret <4 x i32> %v
}
define void @test35(<4 x i32>* %a, <4 x i32> %b) {
; CHECK-LABEL: test35:
; CHECK: # %bb.0:
; CHECK-NEXT: stxvw4x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test35:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: stxvw4x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test35:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: stxvw4x v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test35:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: stvx v2, 0, r3
; CHECK-LE-NEXT: blr
store <4 x i32> %b, <4 x i32>* %a, align 16
ret void
}
define <2 x double> @test40(<2 x i64> %a) {
; CHECK-LABEL: test40:
; CHECK: # %bb.0:
; CHECK-NEXT: xvcvuxddp v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test40:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xvcvuxddp v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test40:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xvcvuxddp v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test40:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xvcvuxddp v2, v2
; CHECK-LE-NEXT: blr
%v = uitofp <2 x i64> %a to <2 x double>
ret <2 x double> %v
}
define <2 x double> @test41(<2 x i64> %a) {
; CHECK-LABEL: test41:
; CHECK: # %bb.0:
; CHECK-NEXT: xvcvsxddp v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test41:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xvcvsxddp v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test41:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xvcvsxddp v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test41:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xvcvsxddp v2, v2
; CHECK-LE-NEXT: blr
%v = sitofp <2 x i64> %a to <2 x double>
ret <2 x double> %v
}
define <2 x i64> @test42(<2 x double> %a) {
; CHECK-LABEL: test42:
; CHECK: # %bb.0:
; CHECK-NEXT: xvcvdpuxds v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test42:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xvcvdpuxds v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test42:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xvcvdpuxds v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test42:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xvcvdpuxds v2, v2
; CHECK-LE-NEXT: blr
%v = fptoui <2 x double> %a to <2 x i64>
ret <2 x i64> %v
}
define <2 x i64> @test43(<2 x double> %a) {
; CHECK-LABEL: test43:
; CHECK: # %bb.0:
; CHECK-NEXT: xvcvdpsxds v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test43:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xvcvdpsxds v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test43:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xvcvdpsxds v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test43:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xvcvdpsxds v2, v2
; CHECK-LE-NEXT: blr
%v = fptosi <2 x double> %a to <2 x i64>
ret <2 x i64> %v
}
define <2 x float> @test44(<2 x i64> %a) {
; CHECK-LABEL: test44:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: addi r4, r1, -64
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: ld r3, -8(r1)
; CHECK-NEXT: std r3, -24(r1)
; CHECK-NEXT: ld r3, -16(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: lfd f0, -24(r1)
; CHECK-NEXT: fcfidus f0, f0
; CHECK-NEXT: stfs f0, -48(r1)
; CHECK-NEXT: lfd f0, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfidus f0, f0
; CHECK-NEXT: stfs f0, -64(r1)
; CHECK-NEXT: lxvw4x v2, 0, r3
; CHECK-NEXT: lxvw4x v3, 0, r4
; CHECK-NEXT: vmrghw v2, v3, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test44:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: addi r4, r1, -64
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: ld r3, -8(r1)
; CHECK-REG-NEXT: std r3, -24(r1)
; CHECK-REG-NEXT: ld r3, -16(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: lfd f0, -24(r1)
; CHECK-REG-NEXT: fcfidus f0, f0
; CHECK-REG-NEXT: stfs f0, -48(r1)
; CHECK-REG-NEXT: lfd f0, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfidus f0, f0
; CHECK-REG-NEXT: stfs f0, -64(r1)
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
; CHECK-REG-NEXT: lxvw4x v3, 0, r4
; CHECK-REG-NEXT: vmrghw v2, v3, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test44:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: ld r3, -8(r1)
; CHECK-FISL-NEXT: std r3, -24(r1)
; CHECK-FISL-NEXT: ld r3, -16(r1)
; CHECK-FISL-NEXT: std r3, -32(r1)
; CHECK-FISL-NEXT: lfd f0, -24(r1)
; CHECK-FISL-NEXT: fcfidus f0, f0
; CHECK-FISL-NEXT: stfs f0, -48(r1)
; CHECK-FISL-NEXT: lfd f0, -32(r1)
; CHECK-FISL-NEXT: fcfidus f0, f0
; CHECK-FISL-NEXT: stfs f0, -64(r1)
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: lxvw4x v2, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -64
; CHECK-FISL-NEXT: lxvw4x v3, 0, r3
; CHECK-FISL-NEXT: vmrghw v2, v3, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test44:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: xxlor vs1, v2, v2
; CHECK-LE-NEXT: xscvuxdsp f1, f1
; CHECK-LE-NEXT: xscvuxdsp f0, f0
; CHECK-LE-NEXT: xscvdpspn vs1, f1
; CHECK-LE-NEXT: xscvdpspn vs0, f0
; CHECK-LE-NEXT: xxsldwi v3, vs1, vs1, 3
; CHECK-LE-NEXT: xxsldwi v2, vs0, vs0, 3
; CHECK-LE-NEXT: vmrghw v2, v3, v2
; CHECK-LE-NEXT: blr
%v = uitofp <2 x i64> %a to <2 x float>
ret <2 x float> %v
; FIXME: The code quality here looks pretty bad.
}
define <2 x float> @test45(<2 x i64> %a) {
; CHECK-LABEL: test45:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: addi r4, r1, -64
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: ld r3, -8(r1)
; CHECK-NEXT: std r3, -24(r1)
; CHECK-NEXT: ld r3, -16(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: lfd f0, -24(r1)
; CHECK-NEXT: fcfids f0, f0
; CHECK-NEXT: stfs f0, -48(r1)
; CHECK-NEXT: lfd f0, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfids f0, f0
; CHECK-NEXT: stfs f0, -64(r1)
; CHECK-NEXT: lxvw4x v2, 0, r3
; CHECK-NEXT: lxvw4x v3, 0, r4
; CHECK-NEXT: vmrghw v2, v3, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test45:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: addi r4, r1, -64
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: ld r3, -8(r1)
; CHECK-REG-NEXT: std r3, -24(r1)
; CHECK-REG-NEXT: ld r3, -16(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: lfd f0, -24(r1)
; CHECK-REG-NEXT: fcfids f0, f0
; CHECK-REG-NEXT: stfs f0, -48(r1)
; CHECK-REG-NEXT: lfd f0, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfids f0, f0
; CHECK-REG-NEXT: stfs f0, -64(r1)
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
; CHECK-REG-NEXT: lxvw4x v3, 0, r4
; CHECK-REG-NEXT: vmrghw v2, v3, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test45:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: ld r3, -8(r1)
; CHECK-FISL-NEXT: std r3, -24(r1)
; CHECK-FISL-NEXT: ld r3, -16(r1)
; CHECK-FISL-NEXT: std r3, -32(r1)
; CHECK-FISL-NEXT: lfd f0, -24(r1)
; CHECK-FISL-NEXT: fcfids f0, f0
; CHECK-FISL-NEXT: stfs f0, -48(r1)
; CHECK-FISL-NEXT: lfd f0, -32(r1)
; CHECK-FISL-NEXT: fcfids f0, f0
; CHECK-FISL-NEXT: stfs f0, -64(r1)
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: lxvw4x v2, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -64
; CHECK-FISL-NEXT: lxvw4x v3, 0, r3
; CHECK-FISL-NEXT: vmrghw v2, v3, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test45:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs0, v2
; CHECK-LE-NEXT: xxlor vs1, v2, v2
; CHECK-LE-NEXT: xscvsxdsp f1, f1
; CHECK-LE-NEXT: xscvsxdsp f0, f0
; CHECK-LE-NEXT: xscvdpspn vs1, f1
; CHECK-LE-NEXT: xscvdpspn vs0, f0
; CHECK-LE-NEXT: xxsldwi v3, vs1, vs1, 3
; CHECK-LE-NEXT: xxsldwi v2, vs0, vs0, 3
; CHECK-LE-NEXT: vmrghw v2, v3, v2
; CHECK-LE-NEXT: blr
%v = sitofp <2 x i64> %a to <2 x float>
ret <2 x float> %v
; FIXME: The code quality here looks pretty bad.
}
define <2 x i64> @test46(<2 x float> %a) {
; CHECK-LABEL: test46:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: stxvw4x v2, 0, r3
; CHECK-NEXT: lfs f0, -44(r1)
; CHECK-NEXT: xscvdpuxds f0, f0
; CHECK-NEXT: stfd f0, -32(r1)
; CHECK-NEXT: lfs f0, -48(r1)
; CHECK-NEXT: xscvdpuxds f0, f0
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test46:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: stxvw4x v2, 0, r3
; CHECK-REG-NEXT: lfs f0, -44(r1)
; CHECK-REG-NEXT: xscvdpuxds f0, f0
; CHECK-REG-NEXT: stfd f0, -32(r1)
; CHECK-REG-NEXT: lfs f0, -48(r1)
; CHECK-REG-NEXT: xscvdpuxds f0, f0
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test46:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvw4x v2, 0, r3
; CHECK-FISL-NEXT: lfs f0, -44(r1)
; CHECK-FISL-NEXT: xscvdpuxds f0, f0
; CHECK-FISL-NEXT: stfd f0, -32(r1)
; CHECK-FISL-NEXT: lfs f0, -48(r1)
; CHECK-FISL-NEXT: xscvdpuxds f0, f0
; CHECK-FISL-NEXT: stfd f0, -24(r1)
; CHECK-FISL-NEXT: ld r3, -32(r1)
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: ld r3, -24(r1)
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test46:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrglw vs0, v2, v2
; CHECK-LE-NEXT: xvcvspdp vs0, vs0
; CHECK-LE-NEXT: xvcvdpuxds v2, vs0
; CHECK-LE-NEXT: blr
%v = fptoui <2 x float> %a to <2 x i64>
ret <2 x i64> %v
; FIXME: The code quality here looks pretty bad.
}
define <2 x i64> @test47(<2 x float> %a) {
; CHECK-LABEL: test47:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: stxvw4x v2, 0, r3
; CHECK-NEXT: lfs f0, -44(r1)
; CHECK-NEXT: xscvdpsxds f0, f0
; CHECK-NEXT: stfd f0, -32(r1)
; CHECK-NEXT: lfs f0, -48(r1)
; CHECK-NEXT: xscvdpsxds f0, f0
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test47:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: stxvw4x v2, 0, r3
; CHECK-REG-NEXT: lfs f0, -44(r1)
; CHECK-REG-NEXT: xscvdpsxds f0, f0
; CHECK-REG-NEXT: stfd f0, -32(r1)
; CHECK-REG-NEXT: lfs f0, -48(r1)
; CHECK-REG-NEXT: xscvdpsxds f0, f0
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test47:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvw4x v2, 0, r3
; CHECK-FISL-NEXT: lfs f0, -44(r1)
; CHECK-FISL-NEXT: xscvdpsxds f0, f0
; CHECK-FISL-NEXT: stfd f0, -32(r1)
; CHECK-FISL-NEXT: lfs f0, -48(r1)
; CHECK-FISL-NEXT: xscvdpsxds f0, f0
; CHECK-FISL-NEXT: stfd f0, -24(r1)
; CHECK-FISL-NEXT: ld r3, -32(r1)
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: ld r3, -24(r1)
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test47:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrglw vs0, v2, v2
; CHECK-LE-NEXT: xvcvspdp vs0, vs0
; CHECK-LE-NEXT: xvcvdpsxds v2, vs0
; CHECK-LE-NEXT: blr
%v = fptosi <2 x float> %a to <2 x i64>
ret <2 x i64> %v
; FIXME: The code quality here looks pretty bad.
}
define <2 x double> @test50(double* %a) {
; CHECK-LABEL: test50:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvdsx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test50:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: lxvdsx v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test50:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: lxvdsx v2, 0, r3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test50:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: lxvdsx v2, 0, r3
; CHECK-LE-NEXT: blr
%v = load double, double* %a, align 8
%w = insertelement <2 x double> undef, double %v, i32 0
%x = insertelement <2 x double> %w, double %v, i32 1
ret <2 x double> %x
}
define <2 x double> @test51(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test51:
; CHECK: # %bb.0:
; CHECK-NEXT: xxspltd v2, v2, 0
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test51:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxspltd v2, v2, 0
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test51:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxspltd v2, v2, 0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test51:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxspltd v2, v2, 1
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 0, i32 0>
ret <2 x double> %v
}
define <2 x double> @test52(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test52:
; CHECK: # %bb.0:
; CHECK-NEXT: xxmrghd v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test52:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxmrghd v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test52:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxmrghd v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test52:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrgld v2, v3, v2
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 0, i32 2>
ret <2 x double> %v
}
define <2 x double> @test53(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test53:
; CHECK: # %bb.0:
; CHECK-NEXT: xxmrghd v2, v3, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test53:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxmrghd v2, v3, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test53:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxmrghd v2, v3, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test53:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrgld v2, v2, v3
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 2, i32 0>
ret <2 x double> %v
}
define <2 x double> @test54(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test54:
; CHECK: # %bb.0:
; CHECK-NEXT: xxpermdi v2, v2, v3, 2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test54:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxpermdi v2, v2, v3, 2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test54:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxpermdi v2, v2, v3, 2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test54:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxpermdi v2, v3, v2, 2
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 1, i32 2>
ret <2 x double> %v
}
define <2 x double> @test55(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test55:
; CHECK: # %bb.0:
; CHECK-NEXT: xxmrgld v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test55:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxmrgld v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test55:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxmrgld v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test55:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrghd v2, v3, v2
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 1, i32 3>
ret <2 x double> %v
}
define <2 x i64> @test56(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test56:
; CHECK: # %bb.0:
; CHECK-NEXT: xxmrgld v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test56:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxmrgld v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test56:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxmrgld v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test56:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrghd v2, v3, v2
; CHECK-LE-NEXT: blr
%v = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 1, i32 3>
ret <2 x i64> %v
}
define <2 x i64> @test60(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test60:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: addi r4, r1, -48
; CHECK-NEXT: stxvd2x v3, 0, r3
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: sld r3, r4, r3
; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
; CHECK-NEXT: sld r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test60:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: addi r4, r1, -48
; CHECK-REG-NEXT: stxvd2x v3, 0, r3
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: sld r3, r4, r3
; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
; CHECK-REG-NEXT: sld r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test60:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v3, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: lwz r3, -20(r1)
; CHECK-FISL-NEXT: ld r4, -40(r1)
; CHECK-FISL-NEXT: sld r3, r4, r3
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: lwz r3, -28(r1)
; CHECK-FISL-NEXT: ld r4, -48(r1)
; CHECK-FISL-NEXT: sld r3, r4, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test60:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vsld v2, v2, v3
; CHECK-LE-NEXT: blr
%v = shl <2 x i64> %a, %b
ret <2 x i64> %v
; This should scalarize, and the current code quality is not good.
}
define <2 x i64> @test61(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test61:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: addi r4, r1, -48
; CHECK-NEXT: stxvd2x v3, 0, r3
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: srd r3, r4, r3
; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
; CHECK-NEXT: srd r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test61:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: addi r4, r1, -48
; CHECK-REG-NEXT: stxvd2x v3, 0, r3
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: srd r3, r4, r3
; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
; CHECK-REG-NEXT: srd r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test61:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v3, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: lwz r3, -20(r1)
; CHECK-FISL-NEXT: ld r4, -40(r1)
; CHECK-FISL-NEXT: srd r3, r4, r3
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: lwz r3, -28(r1)
; CHECK-FISL-NEXT: ld r4, -48(r1)
; CHECK-FISL-NEXT: srd r3, r4, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test61:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vsrd v2, v2, v3
; CHECK-LE-NEXT: blr
%v = lshr <2 x i64> %a, %b
ret <2 x i64> %v
; This should scalarize, and the current code quality is not good.
}
define <2 x i64> @test62(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test62:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: addi r4, r1, -48
; CHECK-NEXT: stxvd2x v3, 0, r3
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: srad r3, r4, r3
; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
; CHECK-NEXT: srad r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test62:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: addi r4, r1, -48
; CHECK-REG-NEXT: stxvd2x v3, 0, r3
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: srad r3, r4, r3
; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
; CHECK-REG-NEXT: srad r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test62:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v3, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: lwz r3, -20(r1)
; CHECK-FISL-NEXT: ld r4, -40(r1)
; CHECK-FISL-NEXT: srad r3, r4, r3
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: lwz r3, -28(r1)
; CHECK-FISL-NEXT: ld r4, -48(r1)
; CHECK-FISL-NEXT: srad r3, r4, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test62:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vsrad v2, v2, v3
; CHECK-LE-NEXT: blr
%v = ashr <2 x i64> %a, %b
ret <2 x i64> %v
; This should scalarize, and the current code quality is not good.
}
define double @test63(<2 x double> %a) {
; CHECK-LABEL: test63:
; CHECK: # %bb.0:
; CHECK-NEXT: xxlor f1, v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test63:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxlor f1, v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test63:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: # kill: def $vf2 killed $vf2 killed $v2
; CHECK-FISL-NEXT: xxlor f1, v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test63:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxswapd vs1, v2
; CHECK-LE-NEXT: # kill: def $f1 killed $f1 killed $vsl1
; CHECK-LE-NEXT: blr
%v = extractelement <2 x double> %a, i32 0
ret double %v
}
define double @test64(<2 x double> %a) {
; CHECK-LABEL: test64:
; CHECK: # %bb.0:
; CHECK-NEXT: xxswapd vs1, v2
; CHECK-NEXT: # kill: def $f1 killed $f1 killed $vsl1
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test64:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxswapd vs1, v2
; CHECK-REG-NEXT: # kill: def $f1 killed $f1 killed $vsl1
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test64:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxswapd vs0, v2
; CHECK-FISL-NEXT: # kill: def $f0 killed $f0 killed $vsl0
; CHECK-FISL-NEXT: fmr f1, f0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test64:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxlor f1, v2, v2
; CHECK-LE-NEXT: blr
%v = extractelement <2 x double> %a, i32 1
ret double %v
}
define <2 x i1> @test65(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test65:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test65:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: vcmpequw v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test65:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: vcmpequw v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test65:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vcmpequd v2, v2, v3
; CHECK-LE-NEXT: blr
%w = icmp eq <2 x i64> %a, %b
ret <2 x i1> %w
}
define <2 x i1> @test66(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test66:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw v2, v2, v3
; CHECK-NEXT: xxlnor v2, v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test66:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: vcmpequw v2, v2, v3
; CHECK-REG-NEXT: xxlnor v2, v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test66:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: vcmpequw v2, v2, v3
; CHECK-FISL-NEXT: xxlnor vs0, v2, v2
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test66:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vcmpequd v2, v2, v3
; CHECK-LE-NEXT: xxlnor v2, v2, v2
; CHECK-LE-NEXT: blr
%w = icmp ne <2 x i64> %a, %b
ret <2 x i1> %w
}
define <2 x i1> @test67(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test67:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: addi r4, r1, -48
; CHECK-NEXT: stxvd2x v3, 0, r3
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: ld r6, -48(r1)
; CHECK-NEXT: cmpld r4, r3
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: li r4, -1
; CHECK-NEXT: isellt r5, r4, r3
; CHECK-NEXT: std r5, -8(r1)
; CHECK-NEXT: ld r5, -32(r1)
; CHECK-NEXT: cmpld r6, r5
; CHECK-NEXT: isellt r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test67:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: addi r4, r1, -48
; CHECK-REG-NEXT: stxvd2x v3, 0, r3
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: ld r6, -48(r1)
; CHECK-REG-NEXT: cmpld r4, r3
; CHECK-REG-NEXT: li r3, 0
; CHECK-REG-NEXT: li r4, -1
; CHECK-REG-NEXT: isellt r5, r4, r3
; CHECK-REG-NEXT: std r5, -8(r1)
; CHECK-REG-NEXT: ld r5, -32(r1)
; CHECK-REG-NEXT: cmpld r6, r5
; CHECK-REG-NEXT: isellt r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test67:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v3, 0, r3
; CHECK-FISL-NEXT: addi r3, r1, -48
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: ld r3, -24(r1)
; CHECK-FISL-NEXT: ld r4, -40(r1)
; CHECK-FISL-NEXT: cmpld r4, r3
; CHECK-FISL-NEXT: li r3, 0
; CHECK-FISL-NEXT: li r4, -1
; CHECK-FISL-NEXT: isellt r5, r4, r3
; CHECK-FISL-NEXT: std r5, -8(r1)
; CHECK-FISL-NEXT: ld r5, -32(r1)
; CHECK-FISL-NEXT: ld r6, -48(r1)
; CHECK-FISL-NEXT: cmpld r6, r5
; CHECK-FISL-NEXT: isellt r3, r4, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test67:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: vcmpgtud v2, v3, v2
; CHECK-LE-NEXT: blr
%w = icmp ult <2 x i64> %a, %b
ret <2 x i1> %w
; This should scalarize, and the current code quality is not good.
}
define <2 x double> @test68(<2 x i32> %a) {
; CHECK-LABEL: test68:
; CHECK: # %bb.0:
; CHECK-NEXT: xxmrghw vs0, v2, v2
; CHECK-NEXT: xvcvsxwdp v2, vs0
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test68:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: xxmrghw vs0, v2, v2
; CHECK-REG-NEXT: xvcvsxwdp v2, vs0
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test68:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: xxmrghw vs0, v2, v2
; CHECK-FISL-NEXT: xvcvsxwdp v2, vs0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test68:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: xxmrglw v2, v2, v2
; CHECK-LE-NEXT: xvcvsxwdp v2, v2
; CHECK-LE-NEXT: blr
%w = sitofp <2 x i32> %a to <2 x double>
ret <2 x double> %w
}
; This gets scalarized so the code isn't great
define <2 x double> @test69(<2 x i16> %a) {
; CHECK-LABEL: test69:
; CHECK: # %bb.0:
; CHECK-NEXT: addis r3, r2, .LCPI63_0@toc@ha
; CHECK-NEXT: addi r3, r3, .LCPI63_0@toc@l
; CHECK-NEXT: lxvw4x v3, 0, r3
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: vperm v2, v2, v2, v3
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: lha r3, -18(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lha r3, -26(r1)
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: xvcvsxddp v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test69:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addis r3, r2, .LCPI63_0@toc@ha
; CHECK-REG-NEXT: addi r3, r3, .LCPI63_0@toc@l
; CHECK-REG-NEXT: lxvw4x v3, 0, r3
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: vperm v2, v2, v2, v3
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: lha r3, -18(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lha r3, -26(r1)
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: xvcvsxddp v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test69:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addis r3, r2, .LCPI63_0@toc@ha
; CHECK-FISL-NEXT: addi r3, r3, .LCPI63_0@toc@l
; CHECK-FISL-NEXT: lxvw4x v3, 0, r3
; CHECK-FISL-NEXT: vperm v2, v2, v2, v3
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: lha r3, -18(r1)
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: lha r3, -26(r1)
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: xvcvsxddp v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test69:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: addis r3, r2, .LCPI63_0@toc@ha
; CHECK-LE-NEXT: addi r3, r3, .LCPI63_0@toc@l
; CHECK-LE-NEXT: lvx v3, 0, r3
; CHECK-LE-NEXT: addis r3, r2, .LCPI63_1@toc@ha
; CHECK-LE-NEXT: addi r3, r3, .LCPI63_1@toc@l
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: vperm v2, v2, v2, v3
; CHECK-LE-NEXT: xxswapd v3, vs0
; CHECK-LE-NEXT: vsld v2, v2, v3
; CHECK-LE-NEXT: vsrad v2, v2, v3
; CHECK-LE-NEXT: xvcvsxddp v2, v2
; CHECK-LE-NEXT: blr
%w = sitofp <2 x i16> %a to <2 x double>
ret <2 x double> %w
}
; This gets scalarized so the code isn't great
define <2 x double> @test70(<2 x i8> %a) {
; CHECK-LABEL: test70:
; CHECK: # %bb.0:
; CHECK-NEXT: addis r3, r2, .LCPI64_0@toc@ha
; CHECK-NEXT: addi r3, r3, .LCPI64_0@toc@l
; CHECK-NEXT: lxvw4x v3, 0, r3
; CHECK-NEXT: addi r3, r1, -32
; CHECK-NEXT: vperm v2, v2, v2, v3
; CHECK-NEXT: stxvd2x v2, 0, r3
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: extsb r3, r3
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: extsb r3, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: xvcvsxddp v2, v2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test70:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addis r3, r2, .LCPI64_0@toc@ha
; CHECK-REG-NEXT: addi r3, r3, .LCPI64_0@toc@l
; CHECK-REG-NEXT: lxvw4x v3, 0, r3
; CHECK-REG-NEXT: addi r3, r1, -32
; CHECK-REG-NEXT: vperm v2, v2, v2, v3
; CHECK-REG-NEXT: stxvd2x v2, 0, r3
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: extsb r3, r3
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: extsb r3, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lxvd2x v2, 0, r3
; CHECK-REG-NEXT: xvcvsxddp v2, v2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test70:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: addis r3, r2, .LCPI64_0@toc@ha
; CHECK-FISL-NEXT: addi r3, r3, .LCPI64_0@toc@l
; CHECK-FISL-NEXT: lxvw4x v3, 0, r3
; CHECK-FISL-NEXT: vperm v2, v2, v2, v3
; CHECK-FISL-NEXT: addi r3, r1, -32
; CHECK-FISL-NEXT: stxvd2x v2, 0, r3
; CHECK-FISL-NEXT: ld r3, -24(r1)
; CHECK-FISL-NEXT: extsb r3, r3
; CHECK-FISL-NEXT: std r3, -8(r1)
; CHECK-FISL-NEXT: ld r3, -32(r1)
; CHECK-FISL-NEXT: extsb r3, r3
; CHECK-FISL-NEXT: std r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvd2x vs0, 0, r3
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
; CHECK-FISL-NEXT: xvcvsxddp v2, v2
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test70:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: addis r3, r2, .LCPI64_0@toc@ha
; CHECK-LE-NEXT: addi r3, r3, .LCPI64_0@toc@l
; CHECK-LE-NEXT: lvx v3, 0, r3
; CHECK-LE-NEXT: addis r3, r2, .LCPI64_1@toc@ha
; CHECK-LE-NEXT: addi r3, r3, .LCPI64_1@toc@l
; CHECK-LE-NEXT: lxvd2x vs0, 0, r3
; CHECK-LE-NEXT: vperm v2, v2, v2, v3
; CHECK-LE-NEXT: xxswapd v3, vs0
; CHECK-LE-NEXT: vsld v2, v2, v3
; CHECK-LE-NEXT: vsrad v2, v2, v3
; CHECK-LE-NEXT: xvcvsxddp v2, v2
; CHECK-LE-NEXT: blr
%w = sitofp <2 x i8> %a to <2 x double>
ret <2 x double> %w
}
; This gets scalarized so the code isn't great
define <2 x i32> @test80(i32 %v) {
; CHECK-LABEL: test80:
; CHECK: # %bb.0:
; CHECK-NEXT: addi r4, r1, -16
; CHECK-NEXT: stw r3, -16(r1)
; CHECK-NEXT: addis r3, r2, .LCPI65_0@toc@ha
; CHECK-NEXT: lxvw4x vs0, 0, r4
; CHECK-NEXT: addi r3, r3, .LCPI65_0@toc@l
; CHECK-NEXT: lxvw4x v3, 0, r3
; CHECK-NEXT: xxspltw v2, vs0, 0
; CHECK-NEXT: vadduwm v2, v2, v3
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test80:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: addi r4, r1, -16
; CHECK-REG-NEXT: stw r3, -16(r1)
; CHECK-REG-NEXT: addis r3, r2, .LCPI65_0@toc@ha
; CHECK-REG-NEXT: lxvw4x vs0, 0, r4
; CHECK-REG-NEXT: addi r3, r3, .LCPI65_0@toc@l
; CHECK-REG-NEXT: lxvw4x v3, 0, r3
; CHECK-REG-NEXT: xxspltw v2, vs0, 0
; CHECK-REG-NEXT: vadduwm v2, v2, v3
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test80:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: # kill: def $r3 killed $r3 killed $x3
; CHECK-FISL-NEXT: stw r3, -16(r1)
; CHECK-FISL-NEXT: addi r3, r1, -16
; CHECK-FISL-NEXT: lxvw4x vs0, 0, r3
; CHECK-FISL-NEXT: xxspltw v2, vs0, 0
; CHECK-FISL-NEXT: addis r3, r2, .LCPI65_0@toc@ha
; CHECK-FISL-NEXT: addi r3, r3, .LCPI65_0@toc@l
; CHECK-FISL-NEXT: lxvw4x v3, 0, r3
; CHECK-FISL-NEXT: vadduwm v2, v2, v3
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test80:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: mtfprwz f0, r3
; CHECK-LE-NEXT: addis r4, r2, .LCPI65_0@toc@ha
; CHECK-LE-NEXT: addi r3, r4, .LCPI65_0@toc@l
; CHECK-LE-NEXT: xxspltw v2, vs0, 1
; CHECK-LE-NEXT: lvx v3, 0, r3
; CHECK-LE-NEXT: vadduwm v2, v2, v3
; CHECK-LE-NEXT: blr
%b1 = insertelement <2 x i32> undef, i32 %v, i32 0
%b2 = shufflevector <2 x i32> %b1, <2 x i32> undef, <2 x i32> zeroinitializer
%i = add <2 x i32> %b2, <i32 2, i32 3>
ret <2 x i32> %i
}
define <2 x double> @test81(<4 x float> %b) {
; CHECK-LABEL: test81:
; CHECK: # %bb.0:
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test81:
; CHECK-REG: # %bb.0:
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test81:
; CHECK-FISL: # %bb.0:
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test81:
; CHECK-LE: # %bb.0:
; CHECK-LE-NEXT: blr
%w = bitcast <4 x float> %b to <2 x double>
ret <2 x double> %w
}
define double @test82(double %a, double %b, double %c, double %d) {
; CHECK-LABEL: test82:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscmpudp cr0, f3, f4
; CHECK-NEXT: beqlr cr0
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: fmr f1, f2
; CHECK-NEXT: blr
;
; CHECK-REG-LABEL: test82:
; CHECK-REG: # %bb.0: # %entry
; CHECK-REG-NEXT: xscmpudp cr0, f3, f4
; CHECK-REG-NEXT: beqlr cr0
; CHECK-REG-NEXT: # %bb.1: # %entry
; CHECK-REG-NEXT: fmr f1, f2
; CHECK-REG-NEXT: blr
;
; CHECK-FISL-LABEL: test82:
; CHECK-FISL: # %bb.0: # %entry
; CHECK-FISL-NEXT: xscmpudp cr0, f3, f4
; CHECK-FISL-NEXT: stfd f2, -8(r1) # 8-byte Folded Spill
; CHECK-FISL-NEXT: stfd f1, -16(r1) # 8-byte Folded Spill
; CHECK-FISL-NEXT: beq cr0, .LBB67_2
; CHECK-FISL-NEXT: # %bb.1: # %entry
; CHECK-FISL-NEXT: lfd f0, -8(r1) # 8-byte Folded Reload
; CHECK-FISL-NEXT: stfd f0, -16(r1) # 8-byte Folded Spill
; CHECK-FISL-NEXT: .LBB67_2: # %entry
; CHECK-FISL-NEXT: lfd f0, -16(r1) # 8-byte Folded Reload
; CHECK-FISL-NEXT: fmr f1, f0
; CHECK-FISL-NEXT: blr
;
; CHECK-LE-LABEL: test82:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xscmpudp cr0, f3, f4
; CHECK-LE-NEXT: beqlr cr0
; CHECK-LE-NEXT: # %bb.1: # %entry
; CHECK-LE-NEXT: fmr f1, f2
; CHECK-LE-NEXT: blr
entry:
%m = fcmp oeq double %c, %d
%v = select i1 %m, double %a, double %b
ret double %v
}
Reference in New Issue View Git Blame Copy Permalink