qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Tom Musta <tommusta@gmail.com>
To: qemu-devel@nongnu.org
Cc: Tom Musta <tommusta@gmail.com>, qemu-ppc@nongnu.org
Subject: [Qemu-devel] [PATCH 23/28] target-ppc: Altivec 2.07: Vector Gather Bits by Bytes
Date: Wed, 12 Feb 2014 15:23:14 -0600	[thread overview]
Message-ID: <1392240199-2454-24-git-send-email-tommusta@gmail.com> (raw)
In-Reply-To: <1392240199-2454-1-git-send-email-tommusta@gmail.com>

This patch adds the Vector Gather Bits by Bytes Doubleword (vgbbd)
instruction which is introduced in Power ISA Version 2.07.

Signed-off-by: Tom Musta <tommusta@gmail.com>
---
 target-ppc/helper.h     |    1 +
 target-ppc/int_helper.c |  276 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/translate.c  |    2 +
 3 files changed, 279 insertions(+), 0 deletions(-)

diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 9613654..aca712f 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -310,6 +310,7 @@ DEF_HELPER_2(vpopcnth, void, avr, avr)
 DEF_HELPER_2(vpopcntw, void, avr, avr)
 DEF_HELPER_2(vpopcntd, void, avr, avr)
 DEF_HELPER_3(vbpermq, void, avr, avr, avr)
+DEF_HELPER_2(vgbbd, void, avr, avr)
 
 DEF_HELPER_2(xsadddp, void, env, i32)
 DEF_HELPER_2(xssubdp, void, env, i32)
diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index 27a34c0..cd0b88a 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -1075,6 +1075,282 @@ void helper_vbpermq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 #undef VBPERMQ_INDEX
 #undef VBPERMQ_DW
 
+uint64_t VGBBD_MASKS[256] = {
+    0x0000000000000000ull, /* 00 */
+    0x0000000000000080ull, /* 01 */
+    0x0000000000008000ull, /* 02 */
+    0x0000000000008080ull, /* 03 */
+    0x0000000000800000ull, /* 04 */
+    0x0000000000800080ull, /* 05 */
+    0x0000000000808000ull, /* 06 */
+    0x0000000000808080ull, /* 07 */
+    0x0000000080000000ull, /* 08 */
+    0x0000000080000080ull, /* 09 */
+    0x0000000080008000ull, /* 0A */
+    0x0000000080008080ull, /* 0B */
+    0x0000000080800000ull, /* 0C */
+    0x0000000080800080ull, /* 0D */
+    0x0000000080808000ull, /* 0E */
+    0x0000000080808080ull, /* 0F */
+    0x0000008000000000ull, /* 10 */
+    0x0000008000000080ull, /* 11 */
+    0x0000008000008000ull, /* 12 */
+    0x0000008000008080ull, /* 13 */
+    0x0000008000800000ull, /* 14 */
+    0x0000008000800080ull, /* 15 */
+    0x0000008000808000ull, /* 16 */
+    0x0000008000808080ull, /* 17 */
+    0x0000008080000000ull, /* 18 */
+    0x0000008080000080ull, /* 19 */
+    0x0000008080008000ull, /* 1A */
+    0x0000008080008080ull, /* 1B */
+    0x0000008080800000ull, /* 1C */
+    0x0000008080800080ull, /* 1D */
+    0x0000008080808000ull, /* 1E */
+    0x0000008080808080ull, /* 1F */
+    0x0000800000000000ull, /* 20 */
+    0x0000800000000080ull, /* 21 */
+    0x0000800000008000ull, /* 22 */
+    0x0000800000008080ull, /* 23 */
+    0x0000800000800000ull, /* 24 */
+    0x0000800000800080ull, /* 25 */
+    0x0000800000808000ull, /* 26 */
+    0x0000800000808080ull, /* 27 */
+    0x0000800080000000ull, /* 28 */
+    0x0000800080000080ull, /* 29 */
+    0x0000800080008000ull, /* 2A */
+    0x0000800080008080ull, /* 2B */
+    0x0000800080800000ull, /* 2C */
+    0x0000800080800080ull, /* 2D */
+    0x0000800080808000ull, /* 2E */
+    0x0000800080808080ull, /* 2F */
+    0x0000808000000000ull, /* 30 */
+    0x0000808000000080ull, /* 31 */
+    0x0000808000008000ull, /* 32 */
+    0x0000808000008080ull, /* 33 */
+    0x0000808000800000ull, /* 34 */
+    0x0000808000800080ull, /* 35 */
+    0x0000808000808000ull, /* 36 */
+    0x0000808000808080ull, /* 37 */
+    0x0000808080000000ull, /* 38 */
+    0x0000808080000080ull, /* 39 */
+    0x0000808080008000ull, /* 3A */
+    0x0000808080008080ull, /* 3B */
+    0x0000808080800000ull, /* 3C */
+    0x0000808080800080ull, /* 3D */
+    0x0000808080808000ull, /* 3E */
+    0x0000808080808080ull, /* 3F */
+    0x0080000000000000ull, /* 40 */
+    0x0080000000000080ull, /* 41 */
+    0x0080000000008000ull, /* 42 */
+    0x0080000000008080ull, /* 43 */
+    0x0080000000800000ull, /* 44 */
+    0x0080000000800080ull, /* 45 */
+    0x0080000000808000ull, /* 46 */
+    0x0080000000808080ull, /* 47 */
+    0x0080000080000000ull, /* 48 */
+    0x0080000080000080ull, /* 49 */
+    0x0080000080008000ull, /* 4A */
+    0x0080000080008080ull, /* 4B */
+    0x0080000080800000ull, /* 4C */
+    0x0080000080800080ull, /* 4D */
+    0x0080000080808000ull, /* 4E */
+    0x0080000080808080ull, /* 4F */
+    0x0080008000000000ull, /* 50 */
+    0x0080008000000080ull, /* 51 */
+    0x0080008000008000ull, /* 52 */
+    0x0080008000008080ull, /* 53 */
+    0x0080008000800000ull, /* 54 */
+    0x0080008000800080ull, /* 55 */
+    0x0080008000808000ull, /* 56 */
+    0x0080008000808080ull, /* 57 */
+    0x0080008080000000ull, /* 58 */
+    0x0080008080000080ull, /* 59 */
+    0x0080008080008000ull, /* 5A */
+    0x0080008080008080ull, /* 5B */
+    0x0080008080800000ull, /* 5C */
+    0x0080008080800080ull, /* 5D */
+    0x0080008080808000ull, /* 5E */
+    0x0080008080808080ull, /* 5F */
+    0x0080800000000000ull, /* 60 */
+    0x0080800000000080ull, /* 61 */
+    0x0080800000008000ull, /* 62 */
+    0x0080800000008080ull, /* 63 */
+    0x0080800000800000ull, /* 64 */
+    0x0080800000800080ull, /* 65 */
+    0x0080800000808000ull, /* 66 */
+    0x0080800000808080ull, /* 67 */
+    0x0080800080000000ull, /* 68 */
+    0x0080800080000080ull, /* 69 */
+    0x0080800080008000ull, /* 6A */
+    0x0080800080008080ull, /* 6B */
+    0x0080800080800000ull, /* 6C */
+    0x0080800080800080ull, /* 6D */
+    0x0080800080808000ull, /* 6E */
+    0x0080800080808080ull, /* 6F */
+    0x0080808000000000ull, /* 70 */
+    0x0080808000000080ull, /* 71 */
+    0x0080808000008000ull, /* 72 */
+    0x0080808000008080ull, /* 73 */
+    0x0080808000800000ull, /* 74 */
+    0x0080808000800080ull, /* 75 */
+    0x0080808000808000ull, /* 76 */
+    0x0080808000808080ull, /* 77 */
+    0x0080808080000000ull, /* 78 */
+    0x0080808080000080ull, /* 79 */
+    0x0080808080008000ull, /* 7A */
+    0x0080808080008080ull, /* 7B */
+    0x0080808080800000ull, /* 7C */
+    0x0080808080800080ull, /* 7D */
+    0x0080808080808000ull, /* 7E */
+    0x0080808080808080ull, /* 7F */
+    0x8000000000000000ull, /* 80 */
+    0x8000000000000080ull, /* 81 */
+    0x8000000000008000ull, /* 82 */
+    0x8000000000008080ull, /* 83 */
+    0x8000000000800000ull, /* 84 */
+    0x8000000000800080ull, /* 85 */
+    0x8000000000808000ull, /* 86 */
+    0x8000000000808080ull, /* 87 */
+    0x8000000080000000ull, /* 88 */
+    0x8000000080000080ull, /* 89 */
+    0x8000000080008000ull, /* 8A */
+    0x8000000080008080ull, /* 8B */
+    0x8000000080800000ull, /* 8C */
+    0x8000000080800080ull, /* 8D */
+    0x8000000080808000ull, /* 8E */
+    0x8000000080808080ull, /* 8F */
+    0x8000008000000000ull, /* 90 */
+    0x8000008000000080ull, /* 91 */
+    0x8000008000008000ull, /* 92 */
+    0x8000008000008080ull, /* 93 */
+    0x8000008000800000ull, /* 94 */
+    0x8000008000800080ull, /* 95 */
+    0x8000008000808000ull, /* 96 */
+    0x8000008000808080ull, /* 97 */
+    0x8000008080000000ull, /* 98 */
+    0x8000008080000080ull, /* 99 */
+    0x8000008080008000ull, /* 9A */
+    0x8000008080008080ull, /* 9B */
+    0x8000008080800000ull, /* 9C */
+    0x8000008080800080ull, /* 9D */
+    0x8000008080808000ull, /* 9E */
+    0x8000008080808080ull, /* 9F */
+    0x8000800000000000ull, /* A0 */
+    0x8000800000000080ull, /* A1 */
+    0x8000800000008000ull, /* A2 */
+    0x8000800000008080ull, /* A3 */
+    0x8000800000800000ull, /* A4 */
+    0x8000800000800080ull, /* A5 */
+    0x8000800000808000ull, /* A6 */
+    0x8000800000808080ull, /* A7 */
+    0x8000800080000000ull, /* A8 */
+    0x8000800080000080ull, /* A9 */
+    0x8000800080008000ull, /* AA */
+    0x8000800080008080ull, /* AB */
+    0x8000800080800000ull, /* AC */
+    0x8000800080800080ull, /* AD */
+    0x8000800080808000ull, /* AE */
+    0x8000800080808080ull, /* AF */
+    0x8000808000000000ull, /* B0 */
+    0x8000808000000080ull, /* B1 */
+    0x8000808000008000ull, /* B2 */
+    0x8000808000008080ull, /* B3 */
+    0x8000808000800000ull, /* B4 */
+    0x8000808000800080ull, /* B5 */
+    0x8000808000808000ull, /* B6 */
+    0x8000808000808080ull, /* B7 */
+    0x8000808080000000ull, /* B8 */
+    0x8000808080000080ull, /* B9 */
+    0x8000808080008000ull, /* BA */
+    0x8000808080008080ull, /* BB */
+    0x8000808080800000ull, /* BC */
+    0x8000808080800080ull, /* BD */
+    0x8000808080808000ull, /* BE */
+    0x8000808080808080ull, /* BF */
+    0x8080000000000000ull, /* C0 */
+    0x8080000000000080ull, /* C1 */
+    0x8080000000008000ull, /* C2 */
+    0x8080000000008080ull, /* C3 */
+    0x8080000000800000ull, /* C4 */
+    0x8080000000800080ull, /* C5 */
+    0x8080000000808000ull, /* C6 */
+    0x8080000000808080ull, /* C7 */
+    0x8080000080000000ull, /* C8 */
+    0x8080000080000080ull, /* C9 */
+    0x8080000080008000ull, /* CA */
+    0x8080000080008080ull, /* CB */
+    0x8080000080800000ull, /* CC */
+    0x8080000080800080ull, /* CD */
+    0x8080000080808000ull, /* CE */
+    0x8080000080808080ull, /* CF */
+    0x8080008000000000ull, /* D0 */
+    0x8080008000000080ull, /* D1 */
+    0x8080008000008000ull, /* D2 */
+    0x8080008000008080ull, /* D3 */
+    0x8080008000800000ull, /* D4 */
+    0x8080008000800080ull, /* D5 */
+    0x8080008000808000ull, /* D6 */
+    0x8080008000808080ull, /* D7 */
+    0x8080008080000000ull, /* D8 */
+    0x8080008080000080ull, /* D9 */
+    0x8080008080008000ull, /* DA */
+    0x8080008080008080ull, /* DB */
+    0x8080008080800000ull, /* DC */
+    0x8080008080800080ull, /* DD */
+    0x8080008080808000ull, /* DE */
+    0x8080008080808080ull, /* DF */
+    0x8080800000000000ull, /* E0 */
+    0x8080800000000080ull, /* E1 */
+    0x8080800000008000ull, /* E2 */
+    0x8080800000008080ull, /* E3 */
+    0x8080800000800000ull, /* E4 */
+    0x8080800000800080ull, /* E5 */
+    0x8080800000808000ull, /* E6 */
+    0x8080800000808080ull, /* E7 */
+    0x8080800080000000ull, /* E8 */
+    0x8080800080000080ull, /* E9 */
+    0x8080800080008000ull, /* EA */
+    0x8080800080008080ull, /* EB */
+    0x8080800080800000ull, /* EC */
+    0x8080800080800080ull, /* ED */
+    0x8080800080808000ull, /* EE */
+    0x8080800080808080ull, /* EF */
+    0x8080808000000000ull, /* F0 */
+    0x8080808000000080ull, /* F1 */
+    0x8080808000008000ull, /* F2 */
+    0x8080808000008080ull, /* F3 */
+    0x8080808000800000ull, /* F4 */
+    0x8080808000800080ull, /* F5 */
+    0x8080808000808000ull, /* F6 */
+    0x8080808000808080ull, /* F7 */
+    0x8080808080000000ull, /* F8 */
+    0x8080808080000080ull, /* F9 */
+    0x8080808080008000ull, /* FA */
+    0x8080808080008080ull, /* FB */
+    0x8080808080800000ull, /* FC */
+    0x8080808080800080ull, /* FD */
+    0x8080808080808000ull, /* FE */
+    0x8080808080808080ull, /* FF */
+};
+
+void helper_vgbbd(ppc_avr_t *r, ppc_avr_t *b)
+{
+    int i;
+    uint64_t t[2] = { 0, 0 };
+
+    VECTOR_FOR_INORDER_I(i, u8) {
+#if defined(HOST_WORDS_BIGENDIAN)
+        t[i>>3] |= VGBBD_MASKS[b->u8[i]] >> (i & 7);
+#else
+        t[i>>3] |= VGBBD_MASKS[b->u8[i]] >> (7-(i & 7));
+#endif
+    }
+
+    r->u64[0] = t[0];
+    r->u64[1] = t[1];
+}
+
 #if defined(HOST_WORDS_BIGENDIAN)
 #define PKBIG 1
 #else
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index f15c21e..86cdfbe 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7369,6 +7369,7 @@ GEN_VXFORM_DUAL(vclzw, PPC_NONE, PPC2_ALTIVEC_207, \
 GEN_VXFORM_DUAL(vclzd, PPC_NONE, PPC2_ALTIVEC_207, \
                 vpopcntd, PPC_NONE, PPC2_ALTIVEC_207)
 GEN_VXFORM(vbpermq, 6, 21);
+GEN_VXFORM_NOA(vgbbd, 6, 20);
 
 /***                           VSX extension                               ***/
 
@@ -10594,6 +10595,7 @@ GEN_VXFORM_DUAL(vclzw, vpopcntw, 1, 30, PPC_NONE, PPC2_ALTIVEC_207),
 GEN_VXFORM_DUAL(vclzd, vpopcntd, 1, 31, PPC_NONE, PPC2_ALTIVEC_207),
 
 GEN_VXFORM_207(vbpermq, 6, 21),
+GEN_VXFORM_207(vgbbd, 6, 20),
 
 GEN_HANDLER_E(lxsdx, 0x1F, 0x0C, 0x12, 0, PPC_NONE, PPC2_VSX),
 GEN_HANDLER_E(lxsiwax, 0x1F, 0x0C, 0x02, 0, PPC_NONE, PPC2_VSX207),
-- 
1.7.1

  parent reply	other threads:[~2014-02-12 21:24 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-12 21:22 [Qemu-devel] [PATCH 00/28] target-ppc: Altivec 2.07 Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 01/28] target-ppc: Altivec 2.07: Add Instruction Flag Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 02/28] target-ppc: Altivec 2.07: Update AVR Structure Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 03/28] target-ppc: Altivec 2.07: Add GEN_VXFORM3 Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 04/28] target-ppc: Altivec 2.07: Add Support for Dual Altivec Instructions Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 05/28] target-ppc: Altivec 2.07: Add Opcode Macro for VX Form Instructions Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 06/28] target-ppc: Altivec 2.07: Add Support for R-Form Dual Instructions Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 07/28] target-ppc: Altivec 2.07: Vector Logical Instructions Tom Musta
2014-02-12 21:22 ` [Qemu-devel] [PATCH 08/28] target-ppc: Altivec 2.07: Add/Subtract Unsigned Doubleword Modulo Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 09/28] target-ppc: Altivec 2.07: Change VMUL_DO to Support 64-bit Integers Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 10/28] target-ppc: Altivec 2.07: Multiply Even/Odd Word Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 11/28] target-ppc: Altivec 2.07: vmuluw Instruction Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 12/28] target-ppc: Altivec 2.07: Add Vector Count Leading Zeroes Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 13/28] target-ppc: Altivec 2.07: Vector Population Count Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 14/28] target-ppc: Altivec 2.07: Vector Min/Max Doubleword Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 15/28] target-ppc: Altivec 2.07: Pack " Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 16/28] target-ppc: Altivec 2.07: Unpack Signed Word Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 17/28] target-ppc: Altivec 2.07: Vector Merge Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 18/28] target-ppc: Altivec 2.07: Change Bit Masks to Support 64-bit Rotates and Shifts Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 19/28] target-ppc: Altivec 2.07: Vector Doubleword Rotate and Shift Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 20/28] target-ppc: Altivec 2.07: Quadword Addition and Subtracation Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 21/28] target-ppc: Altivec 2.07: vbpermq Instruction Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 22/28] target-ppc: Altivec 2.07: Doubleword Compares Tom Musta
2014-02-12 21:23 ` Tom Musta [this message]
2014-02-24 17:16   ` [Qemu-devel] [PATCH 23/28] target-ppc: Altivec 2.07: Vector Gather Bits by Bytes Richard Henderson
2014-02-12 21:23 ` [Qemu-devel] [PATCH 24/28] target-ppc: Altivec 2.07: Vector Polynomial Multiply Sum Tom Musta
2014-02-24 18:11   ` Richard Henderson
2014-02-12 21:23 ` [Qemu-devel] [PATCH 25/28] target-ppc: Altivec 2.07: Binary Coded Decimal Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 26/28] target-ppc: Altivec 2.07: AES Instructions Tom Musta
2014-02-24 17:59   ` Richard Henderson
2014-02-24 18:11     ` Peter Maydell
2014-02-24 18:22       ` Richard Henderson
2014-02-26 19:22     ` Tom Musta
2014-02-26 22:06       ` Tom Musta
2014-02-26 22:26         ` Richard Henderson
2014-02-12 21:23 ` [Qemu-devel] [PATCH 27/28] target-ppc: Altivec 2.07: Vector SHA Sigma Instructions Tom Musta
2014-02-12 21:23 ` [Qemu-devel] [PATCH 28/28] target-ppc: Altivec 2.07: Vector Permute and Exclusive OR Tom Musta
2014-02-18 18:52 ` [Qemu-devel] [PATCH 00/28] target-ppc: Altivec 2.07 Richard W.M. Jones
2014-02-18 23:27   ` Tom Musta
2014-02-20 10:23     ` Richard W.M. Jones
2014-02-20 12:34       ` Richard W.M. Jones
2014-02-20 12:36         ` [Qemu-devel] [Qemu-ppc] " Alexander Graf
2014-02-20 12:47           ` Richard W.M. Jones
2014-02-21 10:55           ` Aneesh Kumar K.V
2014-02-21 11:21             ` Avik Sil
2014-02-21 11:48               ` Alexander Graf
2014-02-21 11:53                 ` Peter Maydell
2014-02-21 12:04                   ` Alexander Graf
2014-02-21 12:20                     ` Peter Maydell
2014-02-26 11:50                       ` Nikunj A Dadhania
2014-02-26 11:58                         ` Nikunj A Dadhania
2014-02-20 14:44         ` [Qemu-devel] " Thomas Huth
2014-02-20 14:52           ` Richard W.M. Jones
2014-02-24  6:32             ` [Qemu-devel] [Qemu-ppc] " Nikunj A Dadhania
2014-02-20 15:00 ` Alexander Graf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1392240199-2454-24-git-send-email-tommusta@gmail.com \
    --to=tommusta@gmail.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).