mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-14 11:32:34 +00:00
f8d179ba76
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. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230413 91177308-0d34-0410-b5e6-96231b3b80d8
38 lines
1.4 KiB
LLVM
38 lines
1.4 KiB
LLVM
; RUN: llc < %s -mcpu=a2q | FileCheck %s
|
|
|
|
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
|
|
}
|
|
|