[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-ppc] [PULL 21/32] Add VSX Scalar Move Instructions
From: |
Alexander Graf |
Subject: |
[Qemu-ppc] [PULL 21/32] Add VSX Scalar Move Instructions |
Date: |
Fri, 20 Dec 2013 02:00:43 +0100 |
From: Tom Musta <address@hidden>
This patch adds the VSX scalar move instructions:
- xsabsdp (Scalar Absolute Value Double-Precision)
- xsnabspd (Scalar Negative Absolute Value Double-Precision)
- xsnegdp (Scalar Negate Double-Precision)
- xscpsgndp (Scalar Copy Sign Double-Precision)
A common generator macro (VSX_SCALAR_MOVE) is added since these
instructions vary only slightly from each other.
Macros to support VSX XX2 and XX3 form opcodes are also added.
These macros handle the overloading of "opcode 2" space (instruction
bits 26:30) caused by AX and BX bits (29 and 30, respectively).
V3: Per feedback from Paolo Bonzini, moved the sign mask into a
temporary and used andc.
Signed-off-by: Tom Musta <address@hidden>
Signed-off-by: Alexander Graf <address@hidden>
---
target-ppc/translate.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 70 insertions(+)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 5c5de4b..446484a 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7153,6 +7153,59 @@ static void gen_xxpermdi(DisasContext *ctx)
}
}
+#define OP_ABS 1
+#define OP_NABS 2
+#define OP_NEG 3
+#define OP_CPSGN 4
+#define SGN_MASK_DP 0x8000000000000000ul
+#define SGN_MASK_SP 0x8000000080000000ul
+
+#define VSX_SCALAR_MOVE(name, op, sgn_mask) \
+static void glue(gen_, name)(DisasContext * ctx) \
+ { \
+ TCGv_i64 xb, sgm; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ xb = tcg_temp_new(); \
+ sgm = tcg_temp_new(); \
+ tcg_gen_mov_i64(xb, cpu_vsrh(xB(ctx->opcode))); \
+ tcg_gen_movi_i64(sgm, sgn_mask); \
+ switch (op) { \
+ case OP_ABS: { \
+ tcg_gen_andc_i64(xb, xb, sgm); \
+ break; \
+ } \
+ case OP_NABS: { \
+ tcg_gen_or_i64(xb, xb, sgm); \
+ break; \
+ } \
+ case OP_NEG: { \
+ tcg_gen_xor_i64(xb, xb, sgm); \
+ break; \
+ } \
+ case OP_CPSGN: { \
+ TCGv_i64 xa = tcg_temp_new(); \
+ tcg_gen_mov_i64(xa, cpu_vsrh(xA(ctx->opcode))); \
+ tcg_gen_and_i64(xa, xa, sgm); \
+ tcg_gen_andc_i64(xb, xb, sgm); \
+ tcg_gen_or_i64(xb, xb, xa); \
+ tcg_temp_free(xa); \
+ break; \
+ } \
+ } \
+ tcg_gen_mov_i64(cpu_vsrh(xT(ctx->opcode)), xb); \
+ tcg_temp_free(xb); \
+ tcg_temp_free(sgm); \
+ }
+
+VSX_SCALAR_MOVE(xsabsdp, OP_ABS, SGN_MASK_DP)
+VSX_SCALAR_MOVE(xsnabsdp, OP_NABS, SGN_MASK_DP)
+VSX_SCALAR_MOVE(xsnegdp, OP_NEG, SGN_MASK_DP)
+VSX_SCALAR_MOVE(xscpsgndp, OP_CPSGN, SGN_MASK_DP)
+
+
/*** SPE extension ***/
/* Register moves */
@@ -9610,6 +9663,18 @@ GEN_HANDLER_E(stxsdx, 0x1F, 0xC, 0x16, 0, PPC_NONE,
PPC2_VSX),
GEN_HANDLER_E(stxvd2x, 0x1F, 0xC, 0x1E, 0, PPC_NONE, PPC2_VSX),
GEN_HANDLER_E(stxvw4x, 0x1F, 0xC, 0x1C, 0, PPC_NONE, PPC2_VSX),
+#undef GEN_XX2FORM
+#define GEN_XX2FORM(name, opc2, opc3, fl2) \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2)
+
+#undef GEN_XX3FORM
+#define GEN_XX3FORM(name, opc2, opc3, fl2) \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
+
#undef GEN_XX3FORM_DM
#define GEN_XX3FORM_DM(name, opc2, opc3) \
GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x00, opc3|0x00, 0, PPC_NONE,
PPC2_VSX),\
@@ -9629,6 +9694,11 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x01, opc3|0x0C,
0, PPC_NONE, PPC2_VSX),\
GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x02, opc3|0x0C, 0, PPC_NONE,
PPC2_VSX),\
GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x03, opc3|0x0C, 0, PPC_NONE, PPC2_VSX)
+GEN_XX2FORM(xsabsdp, 0x12, 0x15, PPC2_VSX),
+GEN_XX2FORM(xsnabsdp, 0x12, 0x16, PPC2_VSX),
+GEN_XX2FORM(xsnegdp, 0x12, 0x17, PPC2_VSX),
+GEN_XX3FORM(xscpsgndp, 0x00, 0x16, PPC2_VSX),
+
GEN_XX3FORM_DM(xxpermdi, 0x08, 0x01),
#undef GEN_SPE
--
1.8.1.4
- [Qemu-ppc] [PULL 18/32] PPC: Use default pci bus name for grackle and heathrow, (continued)
- [Qemu-ppc] [PULL 18/32] PPC: Use default pci bus name for grackle and heathrow, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 26/32] Add xxspltw, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 28/32] PPC: Add VSX to hflags, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 16/32] spapr-rtas: replace return code constants with macros, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 32/32] spapr: limit numa memory regions by ram size, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 29/32] device_tree: s/qemu_devtree/qemu_fdt globally, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 25/32] Add xxsel, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 27/32] Add xxsldwi, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 21/32] Add VSX Scalar Move Instructions,
Alexander Graf <=
- [Qemu-ppc] [PULL 30/32] device_tree: qemu_fdt_setprop: Rename val_array arg, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 22/32] Add VSX Vector Move Instructions, Alexander Graf, 2013/12/19
- [Qemu-ppc] [PULL 20/32] roms: Flush icache when writing roms to guest memory, Alexander Graf, 2013/12/19
- Re: [Qemu-ppc] [Qemu-devel] [PULL 00/32] ppc patch queue 2013-12-20, Andreas Färber, 2013/12/23