maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll

175 lines
7.8 KiB
LLVM
Raw Normal View History

[x86] Begin a significant overhaul of how vector lowering is done in the x86 backend. This sketches out a new code path for vector lowering, hidden behind an off-by-default flag while it is under development. The fundamental idea behind the new code path is to aggressively break down the problem space in ways that ease selecting the odd set of instructions available on x86, and carefully avoid scalarizing code even when forced to use older ISAs. Notably, this starts off restricting itself to SSE2 and implements the complete vector shuffle and blend space for 128-bit vectors in SSE2 without scalarizing. The plan is to layer on top of this ISA extensions where we can bail out of the complex SSE2 lowering and opt for a cheaper, specialized instruction (or set of instructions). It also needs to be generalized to AVX and AVX512 vector widths. Currently, this does a decent but not perfect job for SSE2. There are some specific shortcomings that I plan to address: - We need a peephole combine to fold together shuffles where possible. There are cases where a previous shuffle could be modified slightly to arrange for elements to be in the correct position and a later shuffle eliminated. Doing this eagerly added quite a bit of complexity, and so my plan is to combine away these redundancies afterward. - There are a lot more clever ways to use unpck and pack that need to be added. This is essential for real world shuffles as it turns out... Once SSE2 is polished a bit I should be able to get interesting numbers on performance improvements on benchmarks conducive to vectorization. All of this will be off by default until it is functionally equivalent of course. Differential Revision: http://reviews.llvm.org/D4225 llvm-svn: 211888
2014-06-27 19:23:44 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=CHECK-SSE2
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define <4 x i32> @shuffle_v4i32_0001(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0001
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[0,0,0,1]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0020(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0020
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[0,0,2,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0300(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0300
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[0,3,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_1000(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_1000
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[1,0,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_2200(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_2200
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[2,2,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_3330(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_3330
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[3,3,3,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_3210(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_3210
; CHECK-SSE2: pshufd {{.*}} # xmm0 = xmm0[3,2,1,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x i32> %shuffle
}
define <4 x float> @shuffle_v4f32_0001(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_0001
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[0,0,0,1]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0020(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_0020
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[0,0,2,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0300(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_0300
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[0,3,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_1000(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_1000
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[1,0,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_2200(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_2200
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[2,2,0,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_3330(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_3330
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[3,3,3,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_3210(<4 x float> %a, <4 x float> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4f32_3210
; CHECK-SSE2: shufps {{.*}} # xmm0 = xmm0[3,2,1,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shuffle
}
define <4 x i32> @shuffle_v4i32_0124(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0124
; CHECK-SSE2: shufps {{.*}} # xmm1 = xmm1[0,0],xmm0[2,0]
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm0 = xmm0[0,1],xmm1[2,0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0142(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0142
; CHECK-SSE2: shufps {{.*}} # xmm1 = xmm1[0,0],xmm0[2,0]
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm0 = xmm0[0,1],xmm1[0,2]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 2>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0412(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0412
; CHECK-SSE2: shufps {{.*}} # xmm1 = xmm1[0,0],xmm0[0,0]
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm1 = xmm1[2,0],xmm0[1,2]
; CHECK-SSE2-NEXT: movaps %xmm1, %xmm0
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 2>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_4012(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_4012
; CHECK-SSE2: shufps {{.*}} # xmm1 = xmm1[0,0],xmm0[0,0]
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm1 = xmm1[0,2],xmm0[1,2]
; CHECK-SSE2-NEXT: movaps %xmm1, %xmm0
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 4, i32 0, i32 1, i32 2>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0145(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0145
; CHECK-SSE2: shufpd {{.*}} # xmm0 = xmm0[0],xmm1[0]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_0451(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_0451
; CHECK-SSE2: movaps %xmm0, %xmm2
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm2 = xmm2[0,1],xmm1[0,1]
; FIXME: This is wrong!!! xmm0 = xmm2[0,2],xmm2[3,1] would be correct....
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm0 = xmm0[0,2],xmm2[3,1]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 5, i32 1>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_4501(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_4501
; CHECK-SSE2: shufpd {{.*}} # xmm1 = xmm1[0],xmm0[0]
; CHECK-SSE2-NEXT: movapd %xmm1, %xmm0
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x i32> %shuffle
}
define <4 x i32> @shuffle_v4i32_4015(<4 x i32> %a, <4 x i32> %b) {
; CHECK-SSE2-LABEL: @shuffle_v4i32_4015
; CHECK-SSE2: movaps %xmm0, %xmm2
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm2 = xmm2[0,1],xmm1[0,1]
; FIXME: This is wrong!!! xmm0 = xmm2[0,2],xmm2[3,1] would be correct....
; CHECK-SSE2-NEXT: shufps {{.*}} # xmm0 = xmm0[2,0],xmm2[1,3]
; CHECK-SSE2-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 4, i32 0, i32 1, i32 5>
ret <4 x i32> %shuffle
}