maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Fix ARM vcvt encoding when the number of fractional bits is zero. 

The instruction to convert between floating point and fixed point representations
takes an immediate operand for the number of fractional bits of the fixed point
value. ARMARM specifies that when that number of bits is zero, the assembler
should encode floating point/integer conversion instructions. 

This patch adds the necessary instruction aliases to achieve this behaviour.

llvm-svn: 189009
This commit is contained in:
Mihai Popa 2013-08-22 13:16:07 +00:00
parent 3bf14cebee
commit 5500c0ff89
2 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
llvm/lib/Target/ARM/ARMInstrNEON.td
View File

@ -5461,6 +5461,25 @@ def VCVTxu2fq : N2VCvtQ<1, 1, 0b1110, 0, 1, "vcvt", "f32.u32",
v4f32, v4i32, int_arm_neon_vcvtfxu2fp>;
}
def : NEONInstAlias<"vcvt${p}.s32.f32 $Dd, $Dm, #0",
(VCVTf2sd DPR:$Dd, DPR:$Dm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.u32.f32 $Dd, $Dm, #0",
(VCVTf2ud DPR:$Dd, DPR:$Dm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.f32.s32 $Dd, $Dm, #0",
(VCVTs2fd DPR:$Dd, DPR:$Dm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.f32.u32 $Dd, $Dm, #0",
(VCVTu2fd DPR:$Dd, DPR:$Dm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.s32.f32 $Qd, $Qm, #0",
(VCVTf2sq QPR:$Qd, QPR:$Qm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.u32.f32 $Qd, $Qm, #0",
(VCVTf2uq QPR:$Qd, QPR:$Qm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.f32.s32 $Qd, $Qm, #0",
(VCVTs2fq QPR:$Qd, QPR:$Qm, pred:$p)>;
def : NEONInstAlias<"vcvt${p}.f32.u32 $Qd, $Qm, #0",
(VCVTu2fq QPR:$Qd, QPR:$Qm, pred:$p)>;
// VCVT : Vector Convert Between Half-Precision and Single-Precision.
def VCVTf2h : N2VNInt<0b11, 0b11, 0b01, 0b10, 0b01100, 0, 0,
IIC_VUNAQ, "vcvt", "f16.f32",

16
llvm/test/MC/ARM/neon-convert-encoding.s
View File

@ -18,20 +18,36 @@
vcvt.f32.u32 q8, q8
@ CHECK: vcvt.s32.f32 d16, d16, #1 @ encoding: [0x30,0x0f,0xff,0xf2]
vcvt.s32.f32 d16, d16, #1
@ CHECK: vcvt.s32.f32 d16, d16 @ encoding: [0x20,0x07,0xfb,0xf3]
vcvt.s32.f32 d16, d16, #0
@ CHECK: vcvt.u32.f32 d16, d16, #1 @ encoding: [0x30,0x0f,0xff,0xf3]
vcvt.u32.f32 d16, d16, #1
@ CHECK: vcvt.u32.f32 d16, d16 @ encoding: [0xa0,0x07,0xfb,0xf3]
vcvt.u32.f32 d16, d16, #0
@ CHECK: vcvt.f32.s32 d16, d16, #1 @ encoding: [0x30,0x0e,0xff,0xf2]
vcvt.f32.s32 d16, d16, #1
@ CHECK: vcvt.f32.s32 d16, d16 @ encoding: [0x20,0x06,0xfb,0xf3]
vcvt.f32.s32 d16, d16, #0
@ CHECK: vcvt.f32.u32 d16, d16, #1 @ encoding: [0x30,0x0e,0xff,0xf3]
vcvt.f32.u32 d16, d16, #1
@ CHECK: vcvt.f32.u32 d16, d16 @ encoding: [0xa0,0x06,0xfb,0xf3]
vcvt.f32.u32 d16, d16, #0
@ CHECK: vcvt.s32.f32 q8, q8, #1 @ encoding: [0x70,0x0f,0xff,0xf2]
vcvt.s32.f32 q8, q8, #1
@ CHECK: vcvt.s32.f32 q8, q8 @ encoding: [0x60,0x07,0xfb,0xf3]
vcvt.s32.f32 q8, q8, #0
@ CHECK: vcvt.u32.f32 q8, q8, #1 @ encoding: [0x70,0x0f,0xff,0xf3]
vcvt.u32.f32 q8, q8, #1
@ CHECK: vcvt.u32.f32 q8, q8 @ encoding: [0xe0,0x07,0xfb,0xf3]
vcvt.u32.f32 q8, q8, #0
@ CHECK: vcvt.f32.s32 q8, q8, #1 @ encoding: [0x70,0x0e,0xff,0xf2]
vcvt.f32.s32 q8, q8, #1
@ CHECK: vcvt.f32.s32 q8, q8 @ encoding: [0x60,0x06,0xfb,0xf3]
vcvt.f32.s32 q8, q8, #0
@ CHECK: vcvt.f32.u32 q8, q8, #1 @ encoding: [0x70,0x0e,0xff,0xf3]
vcvt.f32.u32 q8, q8, #1
@ CHECK: vcvt.f32.u32 q8, q8 @ encoding: [0xe0,0x06,0xfb,0xf3]
vcvt.f32.u32 q8, q8, #0
@ CHECK: vcvt.f32.f16 q8, d16 @ encoding: [0x20,0x07,0xf6,0xf3]
vcvt.f32.f16 q8, d16
@ CHECK: vcvt.f16.f32 d16, q8 @ encoding: [0x20,0x06,0xf6,0xf3]