RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2026-07-22 03:35:35 -04:00
Code Issues Packages Projects Releases 10 Wiki Activity
Files
testing
llvm/test/CodeGen/X86/vselect-constants.ll
T
Sanjay Patel c8f9cf9e26 [DAG] convert vector select-of-constants to logic/math 
This goes back to a discussion about IR canonicalization. We'd like to preserve and convert
more IR to 'select' than we currently do because that's likely the best choice in IR:
http://lists.llvm.org/pipermail/llvm-dev/2016-September/105335.html
...but that's often not true for codegen, so we need to account for this pattern coming in
to the backend and transform it to better DAG ops.

Steps in this patch:

  1. Add an EVT param to the existing convertSelectOfConstantsToMath() TLI hook to more finely
     enable this transform. Other targets will probably want that anyway to distinguish scalars
     from vectors. We're using that here to exclude AVX512 targets, but it may not be necessary.

  2. Convert a vselect to ext+add. This eliminates a constant load/materialization, and the
     vector ext is often free.

Implementing a more general fold using xor+and can be a follow-up for targets that don't have
a legal vselect. It's also possible that we can remove the TLI hook for the special case fold
implemented here because we're eliminating a constant, but it needs to be tested on other
targets.

Differential Revision: https://reviews.llvm.org/D36840



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@311731 91177308-0d34-0410-b5e6-96231b3b80d8
2017-08-24 23:24:43 +00:00

259 lines
8.8 KiB
LLVM
Raw Permalink 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 --check-prefix=ALL --check-prefix=SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX
; First, check the generic pattern for any 2 vector constants. Then, check special cases where
; the constants are all off-by-one. Finally, check the extra special cases where the constants
; include 0 or -1.
; Each minimal select test is repeated with a more typical pattern that includes a compare to
; generate the condition value.
; TODO: If we don't have blendv, this can definitely be improved. There's also a selection of
; chips where it makes sense to transform the general case blendv to 2 bit-ops. That should be
; a uarch-specfic transform. At some point (Ryzen?), the implementation should catch up to the
; architecture, so blendv is as fast as a single bit-op.
define <4 x i32> @sel_C1_or_C2_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_C1_or_C2_vec:
; SSE: # BB#0:
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: pandn {{.*}}(%rip), %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_C1_or_C2_vec:
; AVX: # BB#0:
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vmovaps {{.*#+}} xmm1 = [42,0,4294967294,4294967295]
; AVX-NEXT: vblendvps %xmm0, {{.*}}(%rip), %xmm1, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_C1_or_C2_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_C1_or_C2_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: pandn {{.*}}(%rip), %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_C1_or_C2_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovaps {{.*#+}} xmm1 = [42,0,4294967294,4294967295]
; AVX-NEXT: vblendvps %xmm0, {{.*}}(%rip), %xmm1, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cplus1_or_C_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_Cplus1_or_C_vec:
; SSE: # BB#0:
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: paddd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_Cplus1_or_C_vec:
; AVX: # BB#0:
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cplus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_Cplus1_or_C_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [42,0,4294967294,4294967295]
; SSE-NEXT: psubd %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_Cplus1_or_C_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [42,0,4294967294,4294967295]
; AVX-NEXT: vpsubd %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cminus1_or_C_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_Cminus1_or_C_vec:
; SSE: # BB#0:
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: paddd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_Cminus1_or_C_vec:
; AVX: # BB#0:
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vpsrad $31, %xmm0, %xmm0
; AVX-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cminus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_Cminus1_or_C_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: paddd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_Cminus1_or_C_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @sel_minus1_or_0_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_minus1_or_0_vec:
; SSE: # BB#0:
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_minus1_or_0_vec:
; AVX: # BB#0:
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vpsrad $31, %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_minus1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_minus1_or_0_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_minus1_or_0_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_minus1_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_0_or_minus1_vec:
; SSE: # BB#0:
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: paddd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_0_or_minus1_vec:
; AVX: # BB#0:
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_minus1_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_0_or_minus1_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: pxor %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_0_or_minus1_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_1_or_0_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_1_or_0_vec:
; SSE: # BB#0:
; SSE-NEXT: andps {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_1_or_0_vec:
; AVX: # BB#0:
; AVX-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_1_or_0_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: psrld $31, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_1_or_0_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpsrld $31, %xmm0, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_1_vec(<4 x i1> %cond) {
; SSE-LABEL: sel_0_or_1_vec:
; SSE: # BB#0:
; SSE-NEXT: andnps {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sel_0_or_1_vec:
; AVX: # BB#0:
; AVX-NEXT: vandnps {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_1_vec(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: cmp_sel_0_or_1_vec:
; SSE: # BB#0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pandn {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: cmp_sel_0_or_1_vec:
; AVX: # BB#0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpandn {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
Reference in New Issue View Git Blame Copy Permalink