From: Chinmay Rath <rathc@linux.ibm.com>
To: qemu-ppc@nongnu.org
Cc: qemu-devel@nongnu.org, npiggin@gmail.com, danielhb413@gmail.com,
richard.henderson@linaro.org, harshpb@linux.ibm.com
Subject: [PATCH 4/4] target/ppc: Move VSX fp compare insns to decodetree.
Date: Fri, 7 Jun 2024 20:19:21 +0530 [thread overview]
Message-ID: <20240607144921.726730-5-rathc@linux.ibm.com> (raw)
In-Reply-To: <20240607144921.726730-1-rathc@linux.ibm.com>
Moving the following instructions to decodetree specification:
xvcmp{eq, gt, ge, ne}{s, d}p : XX3-form
The changes were verified by validating that the tcg-ops generated for those
instructions remain the same which were captured using the '-d in_asm,op' flag.
Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
---
target/ppc/helper.h | 16 ++++-----
target/ppc/insn32.decode | 12 +++++++
target/ppc/fpu_helper.c | 16 ++++-----
target/ppc/translate/vsx-impl.c.inc | 50 ++++++++++++++---------------
target/ppc/translate/vsx-ops.c.inc | 18 -----------
5 files changed, 52 insertions(+), 60 deletions(-)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 510ce76524..3fd849628a 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -473,10 +473,10 @@ DEF_HELPER_5(xvnmadddp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_5(xvnmsubdp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(XVMAXDP, void, env, vsr, vsr, vsr)
DEF_HELPER_4(XVMINDP, void, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpgedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpgtdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpnedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPEQDP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPGEDP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPGTDP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPNEDP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_3(xvcvdpsp, void, env, vsr, vsr)
DEF_HELPER_3(xvcvdpsxds, void, env, vsr, vsr)
DEF_HELPER_3(xvcvdpsxws, void, env, vsr, vsr)
@@ -507,10 +507,10 @@ DEF_HELPER_5(xvnmaddsp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_5(xvnmsubsp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(XVMAXSP, void, env, vsr, vsr, vsr)
DEF_HELPER_4(XVMINSP, void, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpgesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpgtsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_FLAGS_4(xvcmpnesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPEQSP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPGESP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPGTSP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(XVCMPNESP, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_3(xvcvspdp, void, env, vsr, vsr)
DEF_HELPER_3(xvcvsphp, void, env, vsr, vsr)
DEF_HELPER_3(xvcvhpsp, void, env, vsr, vsr)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 3d31ef52f8..bcaf03f24c 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -217,6 +217,9 @@
&XX3 xt xa xb
@XX3 ...... ..... ..... ..... ........ ... &XX3 xt=%xx_xt xa=%xx_xa xb=%xx_xb
+&XX3_rc xt xa xb rc:bool
+@XX3_rc ...... ..... ..... ..... rc:1 ....... ... &XX3_rc xt=%xx_xt xa=%xx_xa xb=%xx_xb
+
# 32 bit GER instructions have all mask bits considered 1
&MMIRR_XX3 xa xb xt pmsk xmsk ymsk
%xx_at 23:3
@@ -923,6 +926,15 @@ XSCMPEQQP 111111 ..... ..... ..... 0001000100 - @X
XSCMPGEQP 111111 ..... ..... ..... 0011000100 - @X
XSCMPGTQP 111111 ..... ..... ..... 0011100100 - @X
+XVCMPEQSP 111100 ..... ..... ..... . 1000011 ... @XX3_rc
+XVCMPGTSP 111100 ..... ..... ..... . 1001011 ... @XX3_rc
+XVCMPGESP 111100 ..... ..... ..... . 1010011 ... @XX3_rc
+XVCMPNESP 111100 ..... ..... ..... . 1011011 ... @XX3_rc
+XVCMPEQDP 111100 ..... ..... ..... . 1100011 ... @XX3_rc
+XVCMPGTDP 111100 ..... ..... ..... . 1101011 ... @XX3_rc
+XVCMPGEDP 111100 ..... ..... ..... . 1110011 ... @XX3_rc
+XVCMPNEDP 111100 ..... ..... ..... . 1111011 ... @XX3_rc
+
XSMAXDP 111100 ..... ..... ..... 10100000 ... @XX3
XSMINDP 111100 ..... ..... ..... 10101000 ... @XX3
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index a013160644..5a300a3c86 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2624,14 +2624,14 @@ uint32_t helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
return crf6; \
}
-VSX_CMP(xvcmpeqdp, 2, float64, VsrD(i), eq, 0, 1)
-VSX_CMP(xvcmpgedp, 2, float64, VsrD(i), le, 1, 1)
-VSX_CMP(xvcmpgtdp, 2, float64, VsrD(i), lt, 1, 1)
-VSX_CMP(xvcmpnedp, 2, float64, VsrD(i), eq, 0, 0)
-VSX_CMP(xvcmpeqsp, 4, float32, VsrW(i), eq, 0, 1)
-VSX_CMP(xvcmpgesp, 4, float32, VsrW(i), le, 1, 1)
-VSX_CMP(xvcmpgtsp, 4, float32, VsrW(i), lt, 1, 1)
-VSX_CMP(xvcmpnesp, 4, float32, VsrW(i), eq, 0, 0)
+VSX_CMP(XVCMPEQDP, 2, float64, VsrD(i), eq, 0, 1)
+VSX_CMP(XVCMPGEDP, 2, float64, VsrD(i), le, 1, 1)
+VSX_CMP(XVCMPGTDP, 2, float64, VsrD(i), lt, 1, 1)
+VSX_CMP(XVCMPNEDP, 2, float64, VsrD(i), eq, 0, 0)
+VSX_CMP(XVCMPEQSP, 4, float32, VsrW(i), eq, 0, 1)
+VSX_CMP(XVCMPGESP, 4, float32, VsrW(i), le, 1, 1)
+VSX_CMP(XVCMPGTSP, 4, float32, VsrW(i), lt, 1, 1)
+VSX_CMP(XVCMPNESP, 4, float32, VsrW(i), eq, 0, 0)
/*
* VSX_CVT_FP_TO_FP - VSX floating point/floating point conversion
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 739b5ad915..84cd144632 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -802,34 +802,32 @@ static bool do_xvcpsgn(DisasContext *ctx, arg_XX3 *a, unsigned vece)
TRANS(XVCPSGNSP, do_xvcpsgn, MO_32)
TRANS(XVCPSGNDP, do_xvcpsgn, MO_64)
-#define VSX_CMP(name, op1, op2, inval, type) \
-static void gen_##name(DisasContext *ctx) \
-{ \
- TCGv_i32 ignored; \
- TCGv_ptr xt, xa, xb; \
- if (unlikely(!ctx->vsx_enabled)) { \
- gen_exception(ctx, POWERPC_EXCP_VSXU); \
- return; \
- } \
- xt = gen_vsr_ptr(xT(ctx->opcode)); \
- xa = gen_vsr_ptr(xA(ctx->opcode)); \
- xb = gen_vsr_ptr(xB(ctx->opcode)); \
- if ((ctx->opcode >> (31 - 21)) & 1) { \
- gen_helper_##name(cpu_crf[6], tcg_env, xt, xa, xb); \
- } else { \
- ignored = tcg_temp_new_i32(); \
- gen_helper_##name(ignored, tcg_env, xt, xa, xb); \
- } \
+static bool do_cmp(DisasContext *ctx, arg_XX3_rc *a,
+ void (*helper)(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr))
+{
+ TCGv_i32 ignored;
+ TCGv_ptr xt, xa, xb;
+ REQUIRE_VSX(ctx);
+ xt = gen_vsr_ptr(a->xt);
+ xa = gen_vsr_ptr(a->xa);
+ xb = gen_vsr_ptr(a->xb);
+ if (a->rc) {
+ helper(cpu_crf[6], tcg_env, xt, xa, xb);
+ } else {
+ ignored = tcg_temp_new_i32();
+ helper(ignored, tcg_env, xt, xa, xb);
+ }
+ return true;
}
-VSX_CMP(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
-VSX_CMP(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
-VSX_CMP(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
-VSX_CMP(xvcmpnedp, 0x0C, 0x0F, 0, PPC2_ISA300)
-VSX_CMP(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
-VSX_CMP(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
-VSX_CMP(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
-VSX_CMP(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
+TRANS_FLAGS2(VSX, XVCMPEQSP, do_cmp, gen_helper_XVCMPEQSP);
+TRANS_FLAGS2(VSX, XVCMPGTSP, do_cmp, gen_helper_XVCMPGTSP);
+TRANS_FLAGS2(VSX, XVCMPGESP, do_cmp, gen_helper_XVCMPGESP);
+TRANS_FLAGS2(ISA300, XVCMPNESP, do_cmp, gen_helper_XVCMPNESP);
+TRANS_FLAGS2(VSX, XVCMPEQDP, do_cmp, gen_helper_XVCMPEQDP);
+TRANS_FLAGS2(VSX, XVCMPGTDP, do_cmp, gen_helper_XVCMPGTDP);
+TRANS_FLAGS2(VSX, XVCMPGEDP, do_cmp, gen_helper_XVCMPGEDP);
+TRANS_FLAGS2(ISA300, XVCMPNEDP, do_cmp, gen_helper_XVCMPNEDP);
static bool trans_XSCVQPDP(DisasContext *ctx, arg_X_tb_rc *a)
{
diff --git a/target/ppc/translate/vsx-ops.c.inc b/target/ppc/translate/vsx-ops.c.inc
index 91cde088bc..e553b5b8fa 100644
--- a/target/ppc/translate/vsx-ops.c.inc
+++ b/target/ppc/translate/vsx-ops.c.inc
@@ -43,16 +43,6 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 1, PPC_NONE, fl2), \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 2, opc3, 1, PPC_NONE, fl2), \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 3, opc3, 1, PPC_NONE, fl2)
-#define GEN_XX3_RC_FORM(name, opc2, opc3, fl2) \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x00, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x00, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x00, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x00, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x10, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x10, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x10, 0, PPC_NONE, fl2), \
-GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x10, 0, PPC_NONE, fl2)
-
#define GEN_XX3FORM_DM(name, opc2, opc3) \
GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x00, opc3|0x00, 0, PPC_NONE, PPC2_VSX),\
GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x01, opc3|0x00, 0, PPC_NONE, PPC2_VSX),\
@@ -175,10 +165,6 @@ GEN_XX3FORM_NAME(xvnmadddp, "xvnmaddadp", 0x04, 0x1C, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmadddp, "xvnmaddmdp", 0x04, 0x1D, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmsubdp, "xvnmsubadp", 0x04, 0x1E, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmsubdp, "xvnmsubmdp", 0x04, 0x1F, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpeqdp, 0x0C, 0x0C, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpgtdp, 0x0C, 0x0D, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpgedp, 0x0C, 0x0E, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpnedp, 0x0C, 0x0F, PPC2_ISA300),
GEN_XX2FORM(xvcvdpsp, 0x12, 0x18, PPC2_VSX),
GEN_XX2FORM(xvcvdpsxds, 0x10, 0x1D, PPC2_VSX),
GEN_XX2FORM(xvcvdpsxws, 0x10, 0x0D, PPC2_VSX),
@@ -207,10 +193,6 @@ GEN_XX3FORM_NAME(xvnmaddsp, "xvnmaddasp", 0x04, 0x18, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmaddsp, "xvnmaddmsp", 0x04, 0x19, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmsubsp, "xvnmsubasp", 0x04, 0x1A, PPC2_VSX),
GEN_XX3FORM_NAME(xvnmsubsp, "xvnmsubmsp", 0x04, 0x1B, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpeqsp, 0x0C, 0x08, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpgtsp, 0x0C, 0x09, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpgesp, 0x0C, 0x0A, PPC2_VSX),
-GEN_XX3_RC_FORM(xvcmpnesp, 0x0C, 0x0B, PPC2_ISA300),
GEN_XX2FORM(xvcvspdp, 0x12, 0x1C, PPC2_VSX),
GEN_XX2FORM(xvcvspsxds, 0x10, 0x19, PPC2_VSX),
GEN_XX2FORM(xvcvspsxws, 0x10, 0x09, PPC2_VSX),
--
2.39.3
next prev parent reply other threads:[~2024-06-07 23:40 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-07 14:49 [PATCH 0/4] target/ppc: Move VSX storage access and compare Chinmay Rath
2024-06-07 14:49 ` [PATCH 1/4] target/ppc: Moving VSX scalar storage access insns to decodetree Chinmay Rath
2024-06-07 15:42 ` Richard Henderson
2024-06-07 14:49 ` [PATCH 2/4] target/ppc: Move VSX vector with length " Chinmay Rath
2024-06-07 15:41 ` Richard Henderson
2024-06-09 18:11 ` Chinmay Rath
2024-06-09 18:20 ` Richard Henderson
2024-06-07 14:49 ` [PATCH 3/4] target/ppc: Move VSX vector " Chinmay Rath
2024-06-07 15:46 ` Richard Henderson
2024-06-09 18:25 ` Chinmay Rath
2024-06-09 18:36 ` Chinmay Rath
2024-06-07 14:49 ` Chinmay Rath [this message]
2024-06-07 15:55 ` [PATCH 4/4] target/ppc: Move VSX fp compare " Richard Henderson
2024-06-09 18:26 ` Chinmay Rath
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=20240607144921.726730-5-rathc@linux.ibm.com \
--to=rathc@linux.ibm.com \
--cc=danielhb413@gmail.com \
--cc=harshpb@linux.ibm.com \
--cc=npiggin@gmail.com \
--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.