RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 13:33:37 +02:00
Code Issues Projects Releases Wiki Activity
30b976334f
llvm-mirror/test/CodeGen/X86/vec_ctbits.ll
Simon Pilgrim f59c806c0f [VectorLegalizer] Expansion of CTLZ using CTPOP when possible 
This patch avoids scalarization of CTLZ by instead expanding to use CTPOP (ref: "Hacker's Delight") when the necessary operations are available.

This also adds the necessary cost models for X86 SSE2 targets (the main beneficiary) to ensure vectorization only happens when its useful.

Differential Revision: https://reviews.llvm.org/D25910

llvm-svn: 286233
2016-11-08 14:10:28 +00:00

211 lines
7.2 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s
declare <2 x i64> @llvm.cttz.v2i64(<2 x i64>, i1)
declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>, i1)
declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>)
define <2 x i64> @footz(<2 x i64> %a) nounwind {
; CHECK-LABEL: footz:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pxor %xmm2, %xmm2
; CHECK-NEXT: psubq %xmm0, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: psubq {{.*}}(%rip), %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $1, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psubq %xmm0, %xmm2
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm2, %xmm3
; CHECK-NEXT: pand %xmm0, %xmm3
; CHECK-NEXT: psrlq $2, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: paddq %xmm3, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $4, %xmm0
; CHECK-NEXT: paddq %xmm2, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> %a, i1 true)
ret <2 x i64> %c
}
define <2 x i64> @foolz(<2 x i64> %a) nounwind {
; CHECK-LABEL: foolz:
; CHECK: # BB#0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $1, %xmm1
; CHECK-NEXT: por %xmm0, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: psrlq $2, %xmm0
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $4, %xmm1
; CHECK-NEXT: por %xmm0, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: psrlq $8, %xmm0
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $16, %xmm1
; CHECK-NEXT: por %xmm0, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: psrlq $32, %xmm0
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: pxor %xmm0, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: psrlq $1, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psubq %xmm0, %xmm1
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm1, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: psrlq $2, %xmm1
; CHECK-NEXT: pand %xmm0, %xmm1
; CHECK-NEXT: paddq %xmm2, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm2
; CHECK-NEXT: psrlq $4, %xmm2
; CHECK-NEXT: paddq %xmm1, %xmm2
; CHECK-NEXT: pand {{.*}}(%rip), %xmm2
; CHECK-NEXT: pxor %xmm0, %xmm0
; CHECK-NEXT: psadbw %xmm2, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> %a, i1 true)
ret <2 x i64> %c
}
define <2 x i64> @foopop(<2 x i64> %a) nounwind {
; CHECK-LABEL: foopop:
; CHECK: # BB#0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $1, %xmm1
; CHECK-NEXT: pand {{.*}}(%rip), %xmm1
; CHECK-NEXT: psubq %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlq $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddq %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $4, %xmm1
; CHECK-NEXT: paddq %xmm0, %xmm1
; CHECK-NEXT: pand {{.*}}(%rip), %xmm1
; CHECK-NEXT: pxor %xmm0, %xmm0
; CHECK-NEXT: psadbw %xmm0, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %a)
ret <2 x i64> %c
}
declare <2 x i32> @llvm.cttz.v2i32(<2 x i32>, i1)
declare <2 x i32> @llvm.ctlz.v2i32(<2 x i32>, i1)
declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>)
define <2 x i32> @promtz(<2 x i32> %a) nounwind {
; CHECK-LABEL: promtz:
; CHECK: # BB#0:
; CHECK-NEXT: por {{.*}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pxor %xmm2, %xmm2
; CHECK-NEXT: psubq %xmm0, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: psubq {{.*}}(%rip), %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $1, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psubq %xmm0, %xmm2
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm2, %xmm3
; CHECK-NEXT: pand %xmm0, %xmm3
; CHECK-NEXT: psrlq $2, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: paddq %xmm3, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $4, %xmm0
; CHECK-NEXT: paddq %xmm2, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> %a, i1 false)
ret <2 x i32> %c
}
define <2 x i32> @promlz(<2 x i32> %a) nounwind {
; CHECK-LABEL: promlz:
; CHECK: # BB#0:
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: psrlq $1, %xmm2
; CHECK-NEXT: por %xmm0, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $2, %xmm0
; CHECK-NEXT: por %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: psrlq $4, %xmm2
; CHECK-NEXT: por %xmm0, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $8, %xmm0
; CHECK-NEXT: por %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: psrlq $16, %xmm2
; CHECK-NEXT: por %xmm0, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $32, %xmm0
; CHECK-NEXT: por %xmm2, %xmm0
; CHECK-NEXT: pcmpeqd %xmm2, %xmm2
; CHECK-NEXT: pxor %xmm0, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $1, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psubq %xmm0, %xmm2
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm2, %xmm3
; CHECK-NEXT: pand %xmm0, %xmm3
; CHECK-NEXT: psrlq $2, %xmm2
; CHECK-NEXT: pand %xmm0, %xmm2
; CHECK-NEXT: paddq %xmm3, %xmm2
; CHECK-NEXT: movdqa %xmm2, %xmm0
; CHECK-NEXT: psrlq $4, %xmm0
; CHECK-NEXT: paddq %xmm2, %xmm0
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: psubq {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> %a, i1 false)
ret <2 x i32> %c
}
define <2 x i32> @prompop(<2 x i32> %a) nounwind {
; CHECK-LABEL: prompop:
; CHECK: # BB#0:
; CHECK-NEXT: pand {{.*}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm2, %xmm2
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $1, %xmm1
; CHECK-NEXT: pand {{.*}}(%rip), %xmm1
; CHECK-NEXT: psubq %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [3689348814741910323,3689348814741910323]
; CHECK-NEXT: movdqa %xmm0, %xmm3
; CHECK-NEXT: pand %xmm1, %xmm3
; CHECK-NEXT: psrlq $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddq %xmm3, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $4, %xmm1
; CHECK-NEXT: paddq %xmm0, %xmm1
; CHECK-NEXT: pand {{.*}}(%rip), %xmm1
; CHECK-NEXT: psadbw %xmm2, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %a)
ret <2 x i32> %c
}
Reference in New Issue View Git Blame Copy Permalink