All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Henrique Barboza <danielhb413@gmail.com>
To: qemu-devel@nongnu.org
Cc: qemu-ppc@nongnu.org, danielhb413@gmail.com,
	peter.maydell@linaro.org, richard.henderson@linaro.org,
	"Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>
Subject: [PULL 33/34] target/ppc: Implemented [pm]xvbf16ger2*
Date: Thu, 26 May 2022 18:38:14 -0300	[thread overview]
Message-ID: <20220526213815.92701-34-danielhb413@gmail.com> (raw)
In-Reply-To: <20220526213815.92701-1-danielhb413@gmail.com>

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
xvbf16ger2:   VSX Vector bfloat16 GER (rank-2 update)
xvbf16ger2nn: VSX Vector bfloat16 GER (rank-2 update) Negative multiply,
Negative accumulate
xvbf16ger2np: VSX Vector bfloat16 GER (rank-2 update) Negative multiply,
Positive accumulate
xvbf16ger2pn: VSX Vector bfloat16 GER (rank-2 update) Positive multiply,
Negative accumulate
xvbf16ger2pp: VSX Vector bfloat16 GER (rank-2 update) Positive multiply,
Positive accumulate
pmxvbf16ger2:   Prefixed Masked VSX Vector bfloat16 GER (rank-2 update)
pmxvbf16ger2nn: Prefixed Masked VSX Vector bfloat16 GER (rank-2 update)
Negative multiply, Negative accumulate
pmxvbf16ger2np: Prefixed Masked VSX Vector bfloat16 GER (rank-2 update)
Negative multiply, Positive accumulate
pmxvbf16ger2pn: Prefixed Masked VSX Vector bfloat16 GER (rank-2 update)
Positive multiply, Negative accumulate
pmxvbf16ger2pp: Prefixed Masked VSX Vector bfloat16 GER (rank-2 update)
Positive multiply, Positive accumulate

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220524140537.27451-8-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
---
 target/ppc/fpu_helper.c             | 40 +++++++++++++++++++++++++++++
 target/ppc/helper.h                 |  5 ++++
 target/ppc/insn32.decode            |  6 +++++
 target/ppc/insn64.decode            | 11 ++++++++
 target/ppc/translate/vsx-impl.c.inc | 12 +++++++++
 5 files changed, 74 insertions(+)

diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index a9b2ef370f..fed0ce420a 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -3517,6 +3517,11 @@ static float64 extract_hf16(float16 in, float_status *fp_status)
     return float16_to_float64(in, true, fp_status);
 }
 
+static float64 extract_bf16(bfloat16 in, float_status *fp_status)
+{
+    return bfloat16_to_float64(in, fp_status);
+}
+
 static void vsxger16(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
                      ppc_acc_t  *at, uint32_t mask, bool acc,
                      bool neg_mul, bool neg_acc, extract_f16 extract)
@@ -3639,6 +3644,41 @@ static void vsxger(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
     vsxger_excp(env, GETPC());
 }
 
+QEMU_FLATTEN
+void helper_XVBF16GER2(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
+                       ppc_acc_t *at, uint32_t mask)
+{
+    vsxger16(env, a, b, at, mask, false, false, false, extract_bf16);
+}
+
+QEMU_FLATTEN
+void helper_XVBF16GER2PP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
+                         ppc_acc_t *at, uint32_t mask)
+{
+    vsxger16(env, a, b, at, mask, true, false, false, extract_bf16);
+}
+
+QEMU_FLATTEN
+void helper_XVBF16GER2PN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
+                         ppc_acc_t *at, uint32_t mask)
+{
+    vsxger16(env, a, b, at, mask, true, false, true, extract_bf16);
+}
+
+QEMU_FLATTEN
+void helper_XVBF16GER2NP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
+                         ppc_acc_t *at, uint32_t mask)
+{
+    vsxger16(env, a, b, at, mask, true, true, false, extract_bf16);
+}
+
+QEMU_FLATTEN
+void helper_XVBF16GER2NN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
+                         ppc_acc_t *at, uint32_t mask)
+{
+    vsxger16(env, a, b, at, mask, true, true, true, extract_bf16);
+}
+
 QEMU_FLATTEN
 void helper_XVF16GER2(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b,
                      ppc_acc_t *at, uint32_t mask)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 4070c0891c..6233e28d85 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -555,6 +555,11 @@ DEF_HELPER_5(XVF16GER2PP, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF16GER2PN, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF16GER2NP, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF16GER2NN, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVBF16GER2, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVBF16GER2PP, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVBF16GER2PN, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVBF16GER2NP, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVBF16GER2NN, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF32GER, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF32GERPP, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVF32GERPN, void, env, vsr, vsr, acc, i32)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index b8e317159c..18a94fa3b5 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -763,6 +763,12 @@ XVI8GER4SPP     111011 ... -- ..... ..... 01100011 ..-  @XX3_at xa=%xx_xa
 XVI16GER2S      111011 ... -- ..... ..... 00101011 ..-  @XX3_at xa=%xx_xa
 XVI16GER2SPP    111011 ... -- ..... ..... 00101010 ..-  @XX3_at xa=%xx_xa
 
+XVBF16GER2      111011 ... -- ..... ..... 00110011 ..-  @XX3_at xa=%xx_xa
+XVBF16GER2PP    111011 ... -- ..... ..... 00110010 ..-  @XX3_at xa=%xx_xa
+XVBF16GER2PN    111011 ... -- ..... ..... 10110010 ..-  @XX3_at xa=%xx_xa
+XVBF16GER2NP    111011 ... -- ..... ..... 01110010 ..-  @XX3_at xa=%xx_xa
+XVBF16GER2NN    111011 ... -- ..... ..... 11110010 ..-  @XX3_at xa=%xx_xa
+
 XVF16GER2       111011 ... -- ..... ..... 00010011 ..-  @XX3_at xa=%xx_xa
 XVF16GER2PP     111011 ... -- ..... ..... 00010010 ..-  @XX3_at xa=%xx_xa
 XVF16GER2PN     111011 ... -- ..... ..... 10010010 ..-  @XX3_at xa=%xx_xa
diff --git a/target/ppc/insn64.decode b/target/ppc/insn64.decode
index 5ecc5c85bf..de115c1943 100644
--- a/target/ppc/insn64.decode
+++ b/target/ppc/insn64.decode
@@ -150,6 +150,17 @@ PMXVI16GER2S    000001 11 1001 -- - - pmsk:2 ------ ........       \
 PMXVI16GER2SPP  000001 11 1001 -- - - pmsk:2 ------ ........       \
                 111011 ... -- ..... ..... 00101010 ..-  @MMIRR_XX3
 
+PMXVBF16GER2    000001 11 1001 -- - - pmsk:2 ------ ........ \
+                111011 ... -- ..... ..... 00110011 ..-  @MMIRR_XX3
+PMXVBF16GER2PP  000001 11 1001 -- - - pmsk:2 ------ ........ \
+                111011 ... -- ..... ..... 00110010 ..-  @MMIRR_XX3
+PMXVBF16GER2PN  000001 11 1001 -- - - pmsk:2 ------ ........ \
+                111011 ... -- ..... ..... 10110010 ..-  @MMIRR_XX3
+PMXVBF16GER2NP  000001 11 1001 -- - - pmsk:2 ------ ........ \
+                111011 ... -- ..... ..... 01110010 ..-  @MMIRR_XX3
+PMXVBF16GER2NN  000001 11 1001 -- - - pmsk:2 ------ ........ \
+                111011 ... -- ..... ..... 11110010 ..-  @MMIRR_XX3
+
 PMXVF16GER2     000001 11 1001 -- - - pmsk:2 ------ ........ \
                 111011 ... -- ..... ..... 00010011 ..-  @MMIRR_XX3
 PMXVF16GER2PP   000001 11 1001 -- - - pmsk:2 ------ ........ \
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index e79752899a..7acdbceec4 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -2898,6 +2898,12 @@ TRANS64(PMXVI16GER2PP, do_ger, gen_helper_XVI16GER2PP)
 TRANS64(PMXVI16GER2S, do_ger, gen_helper_XVI16GER2S)
 TRANS64(PMXVI16GER2SPP, do_ger, gen_helper_XVI16GER2SPP)
 
+TRANS(XVBF16GER2, do_ger, gen_helper_XVBF16GER2)
+TRANS(XVBF16GER2PP, do_ger, gen_helper_XVBF16GER2PP)
+TRANS(XVBF16GER2PN, do_ger, gen_helper_XVBF16GER2PN)
+TRANS(XVBF16GER2NP, do_ger, gen_helper_XVBF16GER2NP)
+TRANS(XVBF16GER2NN, do_ger, gen_helper_XVBF16GER2NN)
+
 TRANS(XVF16GER2, do_ger, gen_helper_XVF16GER2)
 TRANS(XVF16GER2PP, do_ger, gen_helper_XVF16GER2PP)
 TRANS(XVF16GER2PN, do_ger, gen_helper_XVF16GER2PN)
@@ -2916,6 +2922,12 @@ TRANS(XVF64GERPN, do_ger, gen_helper_XVF64GERPN)
 TRANS(XVF64GERNP, do_ger, gen_helper_XVF64GERNP)
 TRANS(XVF64GERNN, do_ger, gen_helper_XVF64GERNN)
 
+TRANS64(PMXVBF16GER2, do_ger, gen_helper_XVBF16GER2)
+TRANS64(PMXVBF16GER2PP, do_ger, gen_helper_XVBF16GER2PP)
+TRANS64(PMXVBF16GER2PN, do_ger, gen_helper_XVBF16GER2PN)
+TRANS64(PMXVBF16GER2NP, do_ger, gen_helper_XVBF16GER2NP)
+TRANS64(PMXVBF16GER2NN, do_ger, gen_helper_XVBF16GER2NN)
+
 TRANS64(PMXVF16GER2, do_ger, gen_helper_XVF16GER2)
 TRANS64(PMXVF16GER2PP, do_ger, gen_helper_XVF16GER2PP)
 TRANS64(PMXVF16GER2PN, do_ger, gen_helper_XVF16GER2PN)
-- 
2.36.1



  parent reply	other threads:[~2022-05-26 22:22 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-26 21:37 [PULL 00/34] ppc queue Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 01/34] pseries: allow setting stdout-path even on machines with a VGA Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 02/34] hw/ppc/e500: Remove unused BINARY_DEVICE_TREE_FILE Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 03/34] spapr: Use address from elf parser for kernel address Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 04/34] spapr/docs: Add a few words about x-vof Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 05/34] mos6522: fix linking error when CONFIG_MOS6522 is not set Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 06/34] target/ppc: Fix tlbie Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 07/34] target/ppc: Fix FPSCR.FI bit being cleared when it shouldn't Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 08/34] target/ppc: Fix FPSCR.FI changing in float_overflow_excp() Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 09/34] target/ppc: Rename sfprf to sfifprf where it's also used as set fi flag Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 10/34] pnv/xive2: Don't overwrite PC registers when writing TCTXT registers Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 11/34] target/ppc: declare darn32/darn64 helpers with TCG_CALL_NO_RWG Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 12/34] target/ppc: use TCG_CALL_NO_RWG in vector helpers without env Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 13/34] target/ppc: use TCG_CALL_NO_RWG in BCD helpers Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 14/34] target/ppc: use TCG_CALL_NO_RWG in VSX helpers without env Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 15/34] target/ppc: Use TCG_CALL_NO_RWG_SE in fsel helper Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 16/34] target/ppc: declare xscvspdpn helper with call flags Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 17/34] target/ppc: declare xvxsigsp " Daniel Henrique Barboza
2022-05-26 21:37 ` [PULL 18/34] target/ppc: declare xxextractuw and xxinsertw helpers " Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 19/34] target/ppc: introduce do_va_helper Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 20/34] target/ppc: declare vmsum[um]bm helpers with call flags Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 21/34] target/ppc: declare vmsumuh[ms] helper " Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 22/34] target/ppc: declare vmsumsh[ms] " Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 23/34] target/ppc: Fix eieio memory ordering semantics Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 24/34] tcg/ppc: ST_ST memory ordering is not provided with eieio Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 25/34] tcg/ppc: Optimize memory ordering generation with lwsync Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 26/34] target/ppc: Implement lwsync with weaker memory ordering Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 27/34] target/ppc: Implement xxm[tf]acc and xxsetaccz Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 28/34] target/ppc: Implemented xvi*ger* instructions Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 29/34] target/ppc: Implemented pmxvi*ger* instructions Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 30/34] target/ppc: Implemented xvf*ger* Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 31/34] target/ppc: Implemented xvf16ger* Daniel Henrique Barboza
2022-05-26 21:38 ` [PULL 32/34] target/ppc: Implemented pmxvf*ger* Daniel Henrique Barboza
2022-05-26 21:38 ` Daniel Henrique Barboza [this message]
2022-05-26 21:38 ` [PULL 34/34] linux-user: Add PowerPC ISA 3.1 and MMA to hwcap Daniel Henrique Barboza
2022-05-27 15:19 ` [PULL 00/34] ppc queue Richard Henderson

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=20220526213815.92701-34-danielhb413@gmail.com \
    --to=danielhb413@gmail.com \
    --cc=lucas.araujo@eldorado.org.br \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    --cc=richard.henderson@linaro.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.