CPU (A64): Add Pmull_V Inst. with Clmul fast path for the "1/2D -> 1Q" variant & Sse fast path and slow path for both the "8/16B -> 8H" and "1/2D -> 1Q" variants; with Test. (#1817)

* Add Pmull_V Sse fast path only, both "8/16B -> 8H" and "1/2D -> 1Q" variants; with Test.

* Add Clmul fast path for the 128 bits variant.

* Small optimisation (save 60 instructions) for the Sse fast path about the 128 bits variant.

* Add slow path, both variants. Fix V128 Shl/Shr when shift = 0.

* A32: Add Vmull_I P64 variant (slow path); not tested.

* A32: Add Vmull_I_P8_P64 Test and fix P64 variant.
This commit is contained in:
LDj3SNuD 2021-01-04 23:45:54 +01:00 committed by GitHub
parent a03ab0c4a0
commit 430ba6da65
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 264 additions and 25 deletions

View file

@ -413,6 +413,8 @@ namespace ARMeilleure.Decoders
SetA64("0x001110101xxxxx000111xxxxxxxxxx", InstName.Orr_V, InstEmit.Orr_V, OpCodeSimdReg.Create);
SetA64("0x00111100000xxx0xx101xxxxxxxxxx", InstName.Orr_Vi, InstEmit.Orr_Vi, OpCodeSimdImm.Create);
SetA64("0x00111100000xxx10x101xxxxxxxxxx", InstName.Orr_Vi, InstEmit.Orr_Vi, OpCodeSimdImm.Create);
SetA64("0x001110001xxxxx111000xxxxxxxxxx", InstName.Pmull_V, InstEmit.Pmull_V, OpCodeSimdReg.Create);
SetA64("0x001110111xxxxx111000xxxxxxxxxx", InstName.Pmull_V, InstEmit.Pmull_V, OpCodeSimdReg.Create);
SetA64("0x101110<<1xxxxx010000xxxxxxxxxx", InstName.Raddhn_V, InstEmit.Raddhn_V, OpCodeSimdReg.Create);
SetA64("0x10111001100000010110xxxxxxxxxx", InstName.Rbit_V, InstEmit.Rbit_V, OpCodeSimd.Create);
SetA64("0x00111000100000000110xxxxxxxxxx", InstName.Rev16_V, InstEmit.Rev16_V, OpCodeSimd.Create);
@ -886,7 +888,7 @@ namespace ARMeilleure.Decoders
SetA32("111100110x00xxxxxxxx1101xxx1xxxx", InstName.Vmul, InstEmit32.Vmul_V, OpCode32SimdReg.Create);
SetA32("1111001x1x<<xxxxxxx01010x1x0xxxx", InstName.Vmull, InstEmit32.Vmull_1, OpCode32SimdRegElemLong.Create);
SetA32("1111001x1x<<xxxxxxx01100x0x0xxxx", InstName.Vmull, InstEmit32.Vmull_I, OpCode32SimdRegLong.Create);
SetA32("111100101x00xxxxxxx01110x0x0xxxx", InstName.Vmull, InstEmit32.Vmull_I, OpCode32SimdRegLong.Create); // Polynomial
SetA32("111100101xx0xxxxxxx01110x0x0xxxx", InstName.Vmull, InstEmit32.Vmull_I, OpCode32SimdRegLong.Create); // P8/P64
SetA32("111100111x110000xxxx01011xx0xxxx", InstName.Vmvn, InstEmit32.Vmvn_I, OpCode32SimdBinary.Create);
SetA32("1111001x1x000xxxxxxx0xx00x11xxxx", InstName.Vmvn, InstEmit32.Vmvn_II, OpCode32SimdImm.Create); // D/Q vector I32.
SetA32("1111001x1x000xxxxxxx10x00x11xxxx", InstName.Vmvn, InstEmit32.Vmvn_II, OpCode32SimdImm.Create);