RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-23 21:13:02 +02:00
Code Issues Projects Releases Wiki Activity
2112de25ee
llvm-mirror/test/CodeGen/X86/combine-or.ll
Andrea Di Biagio de7985179f [X86] Always prefer to lower a VECTOR_SHUFFLE into a BLENDI instead of SHUFP (or VPERM2X128). 
This patch teaches method 'LowerVECTOR_SHUFFLE' to give higher precedence to
the check for 'isBlendMask'; the idea is that, when possible, we should firstly
check if a shuffle performs a blend, and in case, try to lower it into a BLENDI
instead of selecting a SHUFP or (worse) a VPERM2X128.

In general:
 - AVX VBLENDPS/D always have better latency and throughput than VPERM2F128;
 - BLENDPS/D instructions tend to always have better 'reciprocal throughput'
   than the equivalent SHUFPS/D;
 - Both BLENDPS/D and SHUFPS/D are often decoded into the same number of
   m-ops; however, a m-op obtained from a BLENDPS/D can be scheduled to more
   than one execution port.

This patch:
 - Moves the check for 'isBlendMask' immediately before the check for
   'isSHUFPMask' within method 'LowerVECTOR_SHUFFLE';
 - Updates existing tests for sse/avx shuffle/blend instructions to verify
   that we select (v)blendps/d when possible (instead of (v)shufps/d or
   vperm2f128).

llvm-svn: 211720
2014-06-25 17:41:58 +00:00

270 lines
7.9 KiB
LLVM
Raw Blame History

; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 | FileCheck %s
; Verify that each of the following test cases is folded into a single
; instruction which performs a blend operation.
define <2 x i64> @test1(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 1>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test1
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK-NOT: orps
; CHECK: ret
define <4 x i32> @test2(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 4, i32 2, i32 3>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 1, i32 4, i32 4>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test2
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK: ret
define <2 x i64> @test3(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 1>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test3
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK-NEXT: ret
define <4 x i32> @test4(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 4, i32 4, i32 4>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 1, i32 2, i32 3>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test4
; CHECK-NOT: xorps
; CHECK: movss
; CHECK-NOT: orps
; CHECK: ret
define <4 x i32> @test5(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 1, i32 2, i32 3>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 4, i32 4, i32 4>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test5
; CHECK-NOT: xorps
; CHECK: movss
; CHECK-NEXT: ret
define <4 x i32> @test6(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 1, i32 4, i32 4>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 4, i32 2, i32 3>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test6
; CHECK-NOT: xorps
; CHECK: blendps $12
; CHECK-NEXT: ret
define <4 x i32> @test7(<4 x i32> %a, <4 x i32> %b) {
%and1 = and <4 x i32> %a, <i32 -1, i32 -1, i32 0, i32 0>
%and2 = and <4 x i32> %b, <i32 0, i32 0, i32 -1, i32 -1>
%or = or <4 x i32> %and1, %and2
ret <4 x i32> %or
}
; CHECK-LABEL: test7
; CHECK-NOT: xorps
; CHECK: blendps $12
; CHECK-NEXT: ret
define <2 x i64> @test8(<2 x i64> %a, <2 x i64> %b) {
%and1 = and <2 x i64> %a, <i64 -1, i64 0>
%and2 = and <2 x i64> %b, <i64 0, i64 -1>
%or = or <2 x i64> %and1, %and2
ret <2 x i64> %or
}
; CHECK-LABEL: test8
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK-NOT: orps
; CHECK: ret
define <4 x i32> @test9(<4 x i32> %a, <4 x i32> %b) {
%and1 = and <4 x i32> %a, <i32 0, i32 0, i32 -1, i32 -1>
%and2 = and <4 x i32> %b, <i32 -1, i32 -1, i32 0, i32 0>
%or = or <4 x i32> %and1, %and2
ret <4 x i32> %or
}
; CHECK-LABEL: test9
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK: ret
define <2 x i64> @test10(<2 x i64> %a, <2 x i64> %b) {
%and1 = and <2 x i64> %a, <i64 0, i64 -1>
%and2 = and <2 x i64> %b, <i64 -1, i64 0>
%or = or <2 x i64> %and1, %and2
ret <2 x i64> %or
}
; CHECK-LABEL: test10
; CHECK-NOT: xorps
; CHECK: movsd
; CHECK-NEXT: ret
define <4 x i32> @test11(<4 x i32> %a, <4 x i32> %b) {
%and1 = and <4 x i32> %a, <i32 -1, i32 0, i32 0, i32 0>
%and2 = and <4 x i32> %b, <i32 0, i32 -1, i32 -1, i32 -1>
%or = or <4 x i32> %and1, %and2
ret <4 x i32> %or
}
; CHECK-LABEL: test11
; CHECK-NOT: xorps
; CHECK: movss
; CHECK-NOT: orps
; CHECK: ret
define <4 x i32> @test12(<4 x i32> %a, <4 x i32> %b) {
%and1 = and <4 x i32> %a, <i32 0, i32 -1, i32 -1, i32 -1>
%and2 = and <4 x i32> %b, <i32 -1, i32 0, i32 0, i32 0>
%or = or <4 x i32> %and1, %and2
ret <4 x i32> %or
}
; CHECK-LABEL: test12
; CHECK-NOT: xorps
; CHECK: movss
; CHECK-NEXT: ret
; Verify that the following test cases are folded into single shuffles.
define <4 x i32> @test13(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 1, i32 1, i32 4, i32 4>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 4, i32 2, i32 3>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test13
; CHECK-NOT: xorps
; CHECK: shufps
; CHECK-NEXT: ret
define <2 x i64> @test14(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 0>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test14
; CHECK-NOT: pslldq
; CHECK-NOT: por
; CHECK: punpcklqdq
; CHECK-NEXT: ret
define <4 x i32> @test15(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 4, i32 2, i32 1>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 2, i32 1, i32 4, i32 4>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test15
; CHECK-NOT: xorps
; CHECK: shufps
; CHECK-NOT: shufps
; CHECK-NOT: orps
; CHECK: ret
define <2 x i64> @test16(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 0>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test16
; CHECK-NOT: pslldq
; CHECK-NOT: por
; CHECK: punpcklqdq
; CHECK: ret
; Verify that the dag-combiner does not fold a OR of two shuffles into a single
; shuffle instruction when the shuffle indexes are not compatible.
define <4 x i32> @test17(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 0, i32 4, i32 2>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 1, i32 4, i32 4>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test17
; CHECK: por
; CHECK-NEXT: ret
define <4 x i32> @test18(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 0, i32 4, i32 4>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 4, i32 4, i32 4>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test18
; CHECK: orps
; CHECK: ret
define <4 x i32> @test19(<4 x i32> %a, <4 x i32> %b) {
%shuf1 = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32><i32 4, i32 0, i32 4, i32 3>
%shuf2 = shufflevector <4 x i32> %b, <4 x i32> zeroinitializer, <4 x i32><i32 0, i32 4, i32 2, i32 2>
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; CHECK-LABEL: test19
; CHECK: por
; CHECK-NEXT: ret
define <2 x i64> @test20(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test20
; CHECK-NOT: xorps
; CHECK: orps
; CHECK-NEXT: movq
; CHECK-NEXT: ret
define <2 x i64> @test21(<2 x i64> %a, <2 x i64> %b) {
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 0>
%shuf2 = shufflevector <2 x i64> %b, <2 x i64> zeroinitializer, <2 x i32><i32 2, i32 0>
%or = or <2 x i64> %shuf1, %shuf2
ret <2 x i64> %or
}
; CHECK-LABEL: test21
; CHECK: por
; CHECK-NEXT: pslldq
; CHECK-NEXT: ret
Reference in New Issue View Git Blame Copy Permalink