[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 10/42] target/ppc: Optimize emulation of vclzd instru
From: |
David Gibson |
Subject: |
[Qemu-devel] [PULL 10/42] target/ppc: Optimize emulation of vclzd instruction |
Date: |
Wed, 21 Aug 2019 17:25:10 +1000 |
From: Stefan Brankovic <address@hidden>
Optimize Altivec instruction vclzd (Vector Count Leading Zeros Doubleword).
This instruction counts the number of leading zeros of each doubleword element
in source register and places result in the appropriate doubleword element of
destination register.
Using tcg-s count leading zeros instruction two times(once for each
doubleword element of source register vB) and placing result in
appropriate doubleword element of destination register vD.
Signed-off-by: Stefan Brankovic <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
Message-Id: <address@hidden>
Signed-off-by: David Gibson <address@hidden>
---
target/ppc/helper.h | 1 -
target/ppc/int_helper.c | 3 ---
target/ppc/translate/vmx-impl.inc.c | 28 +++++++++++++++++++++++++++-
3 files changed, 27 insertions(+), 5 deletions(-)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 9b486a0c37..e203f76bf1 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -311,7 +311,6 @@ DEF_HELPER_4(vctsxs, void, env, avr, avr, i32)
DEF_HELPER_2(vclzb, void, avr, avr)
DEF_HELPER_2(vclzh, void, avr, avr)
DEF_HELPER_2(vclzw, void, avr, avr)
-DEF_HELPER_2(vclzd, void, avr, avr)
DEF_HELPER_2(vctzb, void, avr, avr)
DEF_HELPER_2(vctzh, void, avr, avr)
DEF_HELPER_2(vctzw, void, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index a265cb07c5..b82765db33 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1820,17 +1820,14 @@ VUPK(lsw, s64, s32, UPKLO)
#define clzb(v) ((v) ? clz32((uint32_t)(v) << 24) : 8)
#define clzh(v) ((v) ? clz32((uint32_t)(v) << 16) : 16)
#define clzw(v) clz32((v))
-#define clzd(v) clz64((v))
VGENERIC_DO(clzb, u8)
VGENERIC_DO(clzh, u16)
VGENERIC_DO(clzw, u32)
-VGENERIC_DO(clzd, u64)
#undef clzb
#undef clzh
#undef clzw
-#undef clzd
#define ctzb(v) ((v) ? ctz32(v) : 8)
#define ctzh(v) ((v) ? ctz32(v) : 16)
diff --git a/target/ppc/translate/vmx-impl.inc.c
b/target/ppc/translate/vmx-impl.inc.c
index 13153352e4..3372c2c3d3 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -742,6 +742,32 @@ static void trans_vgbbd(DisasContext *ctx)
tcg_temp_free_i64(avr[1]);
}
+/*
+ * vclzd VRT,VRB - Vector Count Leading Zeros Doubleword
+ *
+ * Counting the number of leading zero bits of each doubleword element in
source
+ * register and placing result in appropriate doubleword element of destination
+ * register.
+ */
+static void trans_vclzd(DisasContext *ctx)
+{
+ int VT = rD(ctx->opcode);
+ int VB = rB(ctx->opcode);
+ TCGv_i64 avr = tcg_temp_new_i64();
+
+ /* high doubleword */
+ get_avr64(avr, VB, true);
+ tcg_gen_clzi_i64(avr, avr, 64);
+ set_avr64(VT, avr, true);
+
+ /* low doubleword */
+ get_avr64(avr, VB, false);
+ tcg_gen_clzi_i64(avr, avr, 64);
+ set_avr64(VT, avr, false);
+
+ tcg_temp_free_i64(avr);
+}
+
GEN_VXFORM(vmuloub, 4, 0);
GEN_VXFORM(vmulouh, 4, 1);
GEN_VXFORM(vmulouw, 4, 2);
@@ -1258,7 +1284,7 @@ GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23)
GEN_VXFORM_NOA(vclzb, 1, 28)
GEN_VXFORM_NOA(vclzh, 1, 29)
GEN_VXFORM_NOA(vclzw, 1, 30)
-GEN_VXFORM_NOA(vclzd, 1, 31)
+GEN_VXFORM_TRANS(vclzd, 1, 31)
GEN_VXFORM_NOA_2(vnegw, 1, 24, 6)
GEN_VXFORM_NOA_2(vnegd, 1, 24, 7)
GEN_VXFORM_NOA_2(vextsb2w, 1, 24, 16)
--
2.21.0
- [Qemu-devel] [PULL 00/42] ppc-for-4.2 queue 20190821, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 04/42] spapr_pci: Allow 2MiB and 16MiB IOMMU pagesizes by default, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 05/42] migration: Do not re-read the clock on pre_save in case of paused guest, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 02/42] spapr_iommu: Fix xlate trace to print translated address, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 01/42] spapr: quantify error messages regarding capability settings, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 11/42] target/ppc: Optimize emulation of vclzw instruction, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 10/42] target/ppc: Optimize emulation of vclzd instruction,
David Gibson <=
- [Qemu-devel] [PULL 03/42] hw: add compat machines for 4.2, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 06/42] target/ppc: Optimize emulation of lvsl and lvsr instructions, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 09/42] target/ppc: Optimize emulation of vgbbd instruction, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 08/42] target/ppc: move opcode decode tables to PowerPCCPU, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 19/42] docs/specs: initial spec summary for Ultravisor-related hcalls, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 07/42] target/ppc: Optimize emulation of vsl and vsr instructions, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 16/42] spapr: Implement H_PROD, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 15/42] spapr: Implement dispatch tracking for tcg, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 12/42] ppc: fix memory leak in spapr_caps_add_properties, David Gibson, 2019/08/21
- [Qemu-devel] [PULL 13/42] ppc: fix memory leak in spapr_dt_drc(), David Gibson, 2019/08/21