6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-23 16:19:52 +00:00
Code Issues Projects Releases Wiki Activity

[X86, AVX] instcombine vperm2 intrinsics with zero inputs into shuffles

Browse Source 
This is the IR optimizer follow-on patch for D8563: the x86 backend patch
that converts this kind of shuffle back into a vperm2.

This is also a continuation of the transform that started in D8486. 
In that patch, Andrea suggested that we could convert vperm2 intrinsics that
use zero masks into a single shuffle. 

This is an implementation of that suggestion.

Differential Revision: http://reviews.llvm.org/D8567



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233110 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel
2015-03-24 20:36:42 +00:00
parent 71be19dff2
commit 5e0ce9d13a
2 changed files with 70 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
test/Transforms/InstCombine/x86-vperm2.ll
View File

@@ -76,7 +76,7 @@ define <4 x double> @perm2pd_0x02(<4 x double> %a0, <4 x double> %a1) {
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x02
; CHECK-NEXT: %1 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
; CHECK-NEXT: %1 = shufflevector <4 x double> %a1, <4 x double> %a0, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double> %1
}
@@ -85,7 +85,7 @@ define <4 x double> @perm2pd_0x03(<4 x double> %a0, <4 x double> %a1) {
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x03
; CHECK-NEXT: %1 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
; CHECK-NEXT: %1 = shufflevector <4 x double> %a1, <4 x double> %a0, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double> %1
}
@@ -111,7 +111,7 @@ define <4 x double> @perm2pd_0x12(<4 x double> %a0, <4 x double> %a1) {
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x12
; CHECK-NEXT: %1 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: %1 = shufflevector <4 x double> %a1, <4 x double> %a0, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: ret <4 x double> %1
}
@@ -120,7 +120,7 @@ define <4 x double> @perm2pd_0x13(<4 x double> %a0, <4 x double> %a1) {
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x13
; CHECK-NEXT: %1 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 6, i32 7, i32 2, i32 3>
; CHECK-NEXT: %1 = shufflevector <4 x double> %a1, <4 x double> %a0, <4 x i32> <i32 2, i32 3, i32 6, i32 7>
; CHECK-NEXT: ret <4 x double> %1
}
@@ -207,26 +207,41 @@ define <8 x float> @perm2ps_0x31(<8 x float> %a0, <8 x float> %a1) {
}
; Confirm that when a single zero mask bit is set, we do nothing.
; Confirm that when a single zero mask bit is set, we replace a source vector with zeros.
define <4 x double> @perm2pd_0x81(<4 x double> %a0, <4 x double> %a1) {
%res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 129)
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x81
; CHECK-NEXT: shufflevector <4 x double> %a0, <4 x double> <double 0.0{{.*}}<4 x i32> <i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double>
}
define <4 x double> @perm2pd_0x83(<4 x double> %a0, <4 x double> %a1) {
%res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 131)
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x83
; CHECK-NEXT: call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 -125)
; CHECK-NEXT: shufflevector <4 x double> %a1, <4 x double> <double 0.0{{.*}}, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double>
}
; Confirm that when the other zero mask bit is set, we do nothing. Also confirm that an ignored bit has no effect.
define <4 x double> @perm2pd_0x48(<4 x double> %a0, <4 x double> %a1) {
%res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 72)
define <4 x double> @perm2pd_0x28(<4 x double> %a0, <4 x double> %a1) {
%res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 40)
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x48
; CHECK-NEXT: call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 72)
; CHECK-LABEL: @perm2pd_0x28
; CHECK-NEXT: shufflevector <4 x double> <double 0.0{{.*}}, <4 x double> %a1, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double>
}
define <4 x double> @perm2pd_0x08(<4 x double> %a0, <4 x double> %a1) {
%res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 8)
ret <4 x double> %res
; CHECK-LABEL: @perm2pd_0x08
; CHECK-NEXT: shufflevector <4 x double> <double 0.0{{.*}}, <4 x double> %a0, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x double>
}