2016-08-04 02:17:35 +08:00
|
|
|
; RUN: llc -verify-machineinstrs < %s -mcpu=a2q | FileCheck %s
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
|
|
|
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
|
|
|
|
|
target triple = "powerpc64-bgq-linux"
|
|
|
|
|
|
|
|
|
|
define <4 x double> @foo(double %f1, double %f2, double %f3, double %f4) {
|
|
|
|
|
%v1 = insertelement <4 x double> undef, double %f1, i32 0
|
|
|
|
|
%v2 = insertelement <4 x double> %v1, double %f2, i32 1
|
|
|
|
|
%v3 = insertelement <4 x double> %v2, double %f3, i32 2
|
|
|
|
|
%v4 = insertelement <4 x double> %v3, double %f4, i32 3
|
|
|
|
|
ret <4 x double> %v4
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @foo
|
|
|
|
|
; CHECK: qvgpci [[REG1:[0-9]+]], 275
|
|
|
|
|
; CHECK-DAG: qvgpci [[REG2:[0-9]+]], 101
|
|
|
|
|
; CHECK-DAG: qvfperm [[REG3:[0-9]+]], 3, 4, [[REG1]]
|
|
|
|
|
; CHECK-DAG: qvfperm [[REG4:[0-9]+]], 1, 2, [[REG1]]
|
|
|
|
|
; CHECK-DAG: qvfperm 1, [[REG4]], [[REG3]], [[REG2]]
|
|
|
|
|
; CHECK: blr
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <4 x float> @goo(float %f1, float %f2, float %f3, float %f4) {
|
|
|
|
|
%v1 = insertelement <4 x float> undef, float %f1, i32 0
|
|
|
|
|
%v2 = insertelement <4 x float> %v1, float %f2, i32 1
|
|
|
|
|
%v3 = insertelement <4 x float> %v2, float %f3, i32 2
|
|
|
|
|
%v4 = insertelement <4 x float> %v3, float %f4, i32 3
|
|
|
|
|
ret <4 x float> %v4
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @goo
|
|
|
|
|
; CHECK: qvgpci [[REG1:[0-9]+]], 275
|
|
|
|
|
; CHECK-DAG: qvgpci [[REG2:[0-9]+]], 101
|
|
|
|
|
; CHECK-DAG: qvfperm [[REG3:[0-9]+]], 3, 4, [[REG1]]
|
|
|
|
|
; CHECK-DAG: qvfperm [[REG4:[0-9]+]], 1, 2, [[REG1]]
|
|
|
|
|
; CHECK-DAG: qvfperm 1, [[REG4]], [[REG3]], [[REG2]]
|
|
|
|
|
; CHECK: blr
|
|
|
|
|
}
|
|
|
|
|
|