[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [RFC PATCH v4 50/75] target/i386: introduce SSSE3 vector in
From: |
Jan Bobek |
Subject: |
[Qemu-devel] [RFC PATCH v4 50/75] target/i386: introduce SSSE3 vector instructions to sse-opcode.inc.h |
Date: |
Wed, 21 Aug 2019 13:29:26 -0400 |
Add all the SSSE3 vector instruction entries to sse-opcode.inc.h.
Signed-off-by: Jan Bobek <address@hidden>
---
target/i386/sse-opcode.inc.h | 67 ++++++++++++++++++++++++++++++++++++
1 file changed, 67 insertions(+)
diff --git a/target/i386/sse-opcode.inc.h b/target/i386/sse-opcode.inc.h
index 84785a4e04..d8ea71aa6c 100644
--- a/target/i386/sse-opcode.inc.h
+++ b/target/i386/sse-opcode.inc.h
@@ -354,6 +354,41 @@
* 66 0F 7D /r HSUBPD xmm1, xmm2/m128
* F2 0F D0 /r ADDSUBPS xmm1, xmm2/m128
* 66 0F D0 /r ADDSUBPD xmm1, xmm2/m128
+ *
+ * SSSE3 Instructions
+ * -------------------
+ * NP 0F 38 01 /r PHADDW mm1, mm2/m64
+ * 66 0F 38 01 /r PHADDW xmm1, xmm2/m128
+ * NP 0F 38 02 /r PHADDD mm1, mm2/m64
+ * 66 0F 38 02 /r PHADDD xmm1, xmm2/m128
+ * NP 0F 38 03 /r PHADDSW mm1, mm2/m64
+ * 66 0F 38 03 /r PHADDSW xmm1, xmm2/m128
+ * NP 0F 38 05 /r PHSUBW mm1, mm2/m64
+ * 66 0F 38 05 /r PHSUBW xmm1, xmm2/m128
+ * NP 0F 38 06 /r PHSUBD mm1, mm2/m64
+ * 66 0F 38 06 /r PHSUBD xmm1, xmm2/m128
+ * NP 0F 38 07 /r PHSUBSW mm1, mm2/m64
+ * 66 0F 38 07 /r PHSUBSW xmm1, xmm2/m128
+ * NP 0F 38 0B /r PMULHRSW mm1, mm2/m64
+ * 66 0F 38 0B /r PMULHRSW xmm1, xmm2/m128
+ * NP 0F 38 04 /r PMADDUBSW mm1, mm2/m64
+ * 66 0F 38 04 /r PMADDUBSW xmm1, xmm2/m128
+ * NP 0F 38 1C /r PABSB mm1, mm2/m64
+ * 66 0F 38 1C /r PABSB xmm1, xmm2/m128
+ * NP 0F 38 1D /r PABSW mm1, mm2/m64
+ * 66 0F 38 1D /r PABSW xmm1, xmm2/m128
+ * NP 0F 38 1E /r PABSD mm1, mm2/m64
+ * 66 0F 38 1E /r PABSD xmm1, xmm2/m128
+ * NP 0F 38 08 /r PSIGNB mm1, mm2/m64
+ * 66 0F 38 08 /r PSIGNB xmm1, xmm2/m128
+ * NP 0F 38 09 /r PSIGNW mm1, mm2/m64
+ * 66 0F 38 09 /r PSIGNW xmm1, xmm2/m128
+ * NP 0F 38 0A /r PSIGND mm1, mm2/m64
+ * 66 0F 38 0A /r PSIGND xmm1, xmm2/m128
+ * NP 0F 3A 0F /r ib PALIGNR mm1, mm2/m64, imm8
+ * 66 0F 3A 0F /r ib PALIGNR xmm1, xmm2/m128, imm8
+ * NP 0F 38 00 /r PSHUFB mm1, mm2/m64
+ * 66 0F 38 00 /r PSHUFB xmm1, xmm2/m128
*/
OPCODE(movd, LEG(NP, 0F, 0, 0x6e), MMX, WR, Pq, Ed)
@@ -426,6 +461,12 @@ OPCODE(addps, LEG(NP, 0F, 0, 0x58), SSE, WRR, Vdq, Vdq,
Wdq)
OPCODE(addpd, LEG(66, 0F, 0, 0x58), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(addss, LEG(F3, 0F, 0, 0x58), SSE, WRR, Vd, Vd, Wd)
OPCODE(addsd, LEG(F2, 0F, 0, 0x58), SSE2, WRR, Vq, Vq, Wq)
+OPCODE(phaddw, LEG(NP, 0F38, 0, 0x01), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phaddw, LEG(66, 0F38, 0, 0x01), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(phaddd, LEG(NP, 0F38, 0, 0x02), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phaddd, LEG(66, 0F38, 0, 0x02), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(phaddsw, LEG(NP, 0F38, 0, 0x03), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phaddsw, LEG(66, 0F38, 0, 0x03), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(haddps, LEG(F2, 0F, 0, 0x7c), SSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(haddpd, LEG(66, 0F, 0, 0x7c), SSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(psubb, LEG(NP, 0F, 0, 0xf8), MMX, WRR, Pq, Pq, Qq)
@@ -448,6 +489,12 @@ OPCODE(subps, LEG(NP, 0F, 0, 0x5c), SSE, WRR, Vdq, Vdq,
Wdq)
OPCODE(subpd, LEG(66, 0F, 0, 0x5c), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(subss, LEG(F3, 0F, 0, 0x5c), SSE, WRR, Vd, Vd, Wd)
OPCODE(subsd, LEG(F2, 0F, 0, 0x5c), SSE2, WRR, Vq, Vq, Wq)
+OPCODE(phsubw, LEG(NP, 0F38, 0, 0x05), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phsubw, LEG(66, 0F38, 0, 0x05), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(phsubd, LEG(NP, 0F38, 0, 0x06), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phsubd, LEG(66, 0F38, 0, 0x06), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(phsubsw, LEG(NP, 0F38, 0, 0x07), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(phsubsw, LEG(66, 0F38, 0, 0x07), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(hsubps, LEG(F2, 0F, 0, 0x7d), SSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(hsubpd, LEG(66, 0F, 0, 0x7d), SSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(addsubps, LEG(F2, 0F, 0, 0xd0), SSE3, WRR, Vdq, Vdq, Wdq)
@@ -460,12 +507,16 @@ OPCODE(pmulhuw, LEG(NP, 0F, 0, 0xe4), SSE, WRR, Pq, Pq,
Qq)
OPCODE(pmulhuw, LEG(66, 0F, 0, 0xe4), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(pmuludq, LEG(NP, 0F, 0, 0xf4), SSE2, WRR, Pq, Pq, Qq)
OPCODE(pmuludq, LEG(66, 0F, 0, 0xf4), SSE2, WRR, Vdq, Vdq, Wdq)
+OPCODE(pmulhrsw, LEG(NP, 0F38, 0, 0x0b), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(pmulhrsw, LEG(66, 0F38, 0, 0x0b), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(mulps, LEG(NP, 0F, 0, 0x59), SSE, WRR, Vdq, Vdq, Wdq)
OPCODE(mulpd, LEG(66, 0F, 0, 0x59), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(mulss, LEG(F3, 0F, 0, 0x59), SSE, WRR, Vd, Vd, Wd)
OPCODE(mulsd, LEG(F2, 0F, 0, 0x59), SSE2, WRR, Vq, Vq, Wq)
OPCODE(pmaddwd, LEG(NP, 0F, 0, 0xf5), MMX, WRR, Pq, Pq, Qq)
OPCODE(pmaddwd, LEG(66, 0F, 0, 0xf5), SSE2, WRR, Vdq, Vdq, Wdq)
+OPCODE(pmaddubsw, LEG(NP, 0F38, 0, 0x04), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(pmaddubsw, LEG(66, 0F38, 0, 0x04), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(divps, LEG(NP, 0F, 0, 0x5e), SSE, WRR, Vdq, Vdq, Wdq)
OPCODE(divpd, LEG(66, 0F, 0, 0x5e), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(divss, LEG(F3, 0F, 0, 0x5e), SSE, WRR, Vd, Vd, Wd)
@@ -500,6 +551,18 @@ OPCODE(pavgw, LEG(NP, 0F, 0, 0xe3), SSE, WRR, Pq, Pq, Qq)
OPCODE(pavgw, LEG(66, 0F, 0, 0xe3), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(psadbw, LEG(NP, 0F, 0, 0xf6), SSE, WRR, Pq, Pq, Qq)
OPCODE(psadbw, LEG(66, 0F, 0, 0xf6), SSE2, WRR, Vdq, Vdq, Wdq)
+OPCODE(pabsb, LEG(NP, 0F38, 0, 0x1c), SSSE3, WR, Pq, Qq)
+OPCODE(pabsb, LEG(66, 0F38, 0, 0x1c), SSSE3, WR, Vdq, Wdq)
+OPCODE(pabsw, LEG(NP, 0F38, 0, 0x1d), SSSE3, WR, Pq, Qq)
+OPCODE(pabsw, LEG(66, 0F38, 0, 0x1d), SSSE3, WR, Vdq, Wdq)
+OPCODE(pabsd, LEG(NP, 0F38, 0, 0x1e), SSSE3, WR, Pq, Qq)
+OPCODE(pabsd, LEG(66, 0F38, 0, 0x1e), SSSE3, WR, Vdq, Wdq)
+OPCODE(psignb, LEG(NP, 0F38, 0, 0x08), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(psignb, LEG(66, 0F38, 0, 0x08), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(psignw, LEG(NP, 0F38, 0, 0x09), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(psignw, LEG(66, 0F38, 0, 0x09), SSSE3, WRR, Vdq, Vdq, Wdq)
+OPCODE(psignd, LEG(NP, 0F38, 0, 0x0a), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(psignd, LEG(66, 0F38, 0, 0x0a), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(pcmpeqb, LEG(NP, 0F, 0, 0x74), MMX, WRR, Pq, Pq, Qq)
OPCODE(pcmpeqb, LEG(66, 0F, 0, 0x74), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(pcmpeqw, LEG(NP, 0F, 0, 0x75), MMX, WRR, Pq, Pq, Qq)
@@ -552,6 +615,8 @@ OPCODE(psraw, LEG(NP, 0F, 0, 0xe1), MMX, WRR, Pq, Pq, Qq)
OPCODE(psraw, LEG(66, 0F, 0, 0xe1), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(psrad, LEG(NP, 0F, 0, 0xe2), MMX, WRR, Pq, Pq, Qq)
OPCODE(psrad, LEG(66, 0F, 0, 0xe2), SSE2, WRR, Vdq, Vdq, Wdq)
+OPCODE(palignr, LEG(NP, 0F3A, 0, 0x0f), SSSE3, WRRR, Pq, Pq, Qq, Ib)
+OPCODE(palignr, LEG(66, 0F3A, 0, 0x0f), SSSE3, WRRR, Vdq, Vdq, Wdq, Ib)
OPCODE(packsswb, LEG(NP, 0F, 0, 0x63), MMX, WRR, Pq, Pq, Qq)
OPCODE(packsswb, LEG(66, 0F, 0, 0x63), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(packssdw, LEG(NP, 0F, 0, 0x6b), MMX, WRR, Pq, Pq, Qq)
@@ -576,6 +641,8 @@ OPCODE(unpcklps, LEG(NP, 0F, 0, 0x14), SSE, WRR, Vdq, Vdq,
Wdq)
OPCODE(unpcklpd, LEG(66, 0F, 0, 0x14), SSE2, WRR, Vdq, Vdq, Wdq)
OPCODE(unpckhps, LEG(NP, 0F, 0, 0x15), SSE, WRR, Vdq, Vdq, Wdq)
OPCODE(unpckhpd, LEG(66, 0F, 0, 0x15), SSE2, WRR, Vdq, Vdq, Wdq)
+OPCODE(pshufb, LEG(NP, 0F38, 0, 0x00), SSSE3, WRR, Pq, Pq, Qq)
+OPCODE(pshufb, LEG(66, 0F38, 0, 0x00), SSSE3, WRR, Vdq, Vdq, Wdq)
OPCODE(pshufw, LEG(NP, 0F, 0, 0x70), SSE, WRR, Pq, Qq, Ib)
OPCODE(pshuflw, LEG(F2, 0F, 0, 0x70), SSE2, WRR, Vdq, Wdq, Ib)
OPCODE(pshufhw, LEG(F3, 0F, 0, 0x70), SSE2, WRR, Vdq, Wdq, Ib)
--
2.20.1
- [Qemu-devel] [RFC PATCH v4 44/75] target/i386: introduce SSE2 vector instructions to sse-opcode.inc.h, (continued)
- [Qemu-devel] [RFC PATCH v4 44/75] target/i386: introduce SSE2 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 62/75] target/i386: introduce AVX2 translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 53/75] target/i386: introduce SSE4.1 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 59/75] target/i386: introduce AVX translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 47/75] target/i386: introduce SSE3 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 51/75] target/i386: introduce SSE4.1 translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 66/75] target/i386: cleanup leftovers in ops_sse_header.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 67/75] target/i386: introduce aliases for helper-based tcg_gen_gvec_* functions, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 69/75] target/i386: convert pmullw/pmulhw/pmulhuw helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 43/75] target/i386: introduce SSE2 code generators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 50/75] target/i386: introduce SSSE3 vector instructions to sse-opcode.inc.h,
Jan Bobek <=
- [Qemu-devel] [RFC PATCH v4 55/75] target/i386: introduce SSE4.2 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 57/75] target/i386: introduce AES and PCLMULQDQ code generators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 58/75] target/i386: introduce AES and PCLMULQDQ vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 65/75] target/i386: remove obsoleted helpers, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 49/75] target/i386: introduce SSSE3 code generators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 70/75] target/i386: convert pavgb/pavgw helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 71/75] target/i386: convert pmuludq/pmaddwd helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 73/75] target/i386: remove obsoleted helper_mov(l, q)_mm_T0, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 68/75] target/i386: convert ps((l, r)l(w, d, q), ra(w, d)) to helpers to gvec style, Jan Bobek, 2019/08/21