From: "Lucas Mateus Castro (alqotel)" <lucas.ara...@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.ara...@eldorado.org.br>
---
There's a discrepancy between this implementation and mambo/the
hardware where implementing it with float32_mul then float32_muladd
results in incorrect signal in some 0 or infinite results, but implementing
with a multiplication then muladd using FloatParts64 results in a different
result in operations where an underflow would've ocurred in the first
multiplication if it was rounded to 32 bits. I've not been able to solve this
---
target/ppc/cpu.h | 3 +++
target/ppc/fpu_helper.c | 1 +
target/ppc/helper.h | 1 +
target/ppc/insn32.decode | 6 ++++++
target/ppc/insn64.decode | 11 +++++++++++
target/ppc/translate/vsx-impl.c.inc | 12 ++++++++++++
6 files changed, 34 insertions(+)
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 91167f8cc0..10780adf65 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -225,6 +225,7 @@ typedef union _ppc_vsr_t {
int16_t s16[8];
int32_t s32[4];
int64_t s64[2];
+ bfloat16 bf16[8];
float16 f16[8];
float32 f32[4];
float64 f64[2];
@@ -2653,6 +2654,7 @@ static inline bool lsw_reg_in_range(int start, int nregs,
int rx)
#define VsrSW(i) s32[i]
#define VsrD(i) u64[i]
#define VsrSD(i) s64[i]
+#define VsrBF(i) bf16[i]
#define VsrHF(i) f16[i]
#define VsrSF(i) f32[i]
#define VsrDF(i) f64[i]
@@ -2665,6 +2667,7 @@ static inline bool lsw_reg_in_range(int start, int nregs,
int rx)
#define VsrSW(i) s32[3 - (i)]
#define VsrD(i) u64[1 - (i)]
#define VsrSD(i) s64[1 - (i)]
+#define VsrBF(i) bf16[7 - (i)]
#define VsrHF(i) f16[7 - (i)]
#define VsrSF(i) f32[3 - (i)]
#define VsrDF(i) f64[1 - (i)]
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index c3aead642a..9acba0f804 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -3583,6 +3583,7 @@ static inline bool ger_neg_acc_flag(uint32_t flag)
do_float_check_status(env, GETPC()); \
}
+VSXGER16(helper_XVBF16GER2, bfloat16, BF)
VSXGER16(helper_XVF16GER2, float16, HF)
VSXGER(helper_XVF32GER, float32, SF)
VSXGER(helper_XVF64GER, float64, DF)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index cc59a3b71d..68748ecc03 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -540,6 +540,7 @@ DEF_HELPER_5(XXBLENDVD, void, vsr, vsr, vsr, vsr, i32)
DEF_HELPER_6(XVI4GER8, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_6(XVI8GER4, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_6(XVI16GER2, void, env, i32, i32, i32, i32, i32)
+DEF_HELPER_6(XVBF16GER2, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_6(XVF16GER2, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_6(XVF32GER, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_6(XVF64GER, void, env, i32, i32, i32, i32, i32)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index a204730d1d..fff6e406f0 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -736,6 +736,12 @@ 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 bc5e4dfe1a..4cd6219ad5 100644
--- a/target/ppc/insn64.decode
+++ b/target/ppc/insn64.decode
@@ -151,6 +151,17 @@ 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 06f5c1220d..bb5e6f0693 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -2933,6 +2933,12 @@ TRANS64(PMXVI16GER2SPP, do_ger_MMIRR_XX3, GER_SPP,
gen_helper_XVI16GER2)
#define GER_PN ger_pack_flags_xvf(true, false, true)
#define GER_NN ger_pack_flags_xvf(true, true, true)
+TRANS(XVBF16GER2, do_ger_XX3, GER_NOP, gen_helper_XVBF16GER2)
+TRANS(XVBF16GER2PP, do_ger_XX3, GER_PP, gen_helper_XVBF16GER2)
+TRANS(XVBF16GER2PN, do_ger_XX3, GER_PN, gen_helper_XVBF16GER2)
+TRANS(XVBF16GER2NP, do_ger_XX3, GER_NP, gen_helper_XVBF16GER2)
+TRANS(XVBF16GER2NN, do_ger_XX3, GER_NN, gen_helper_XVBF16GER2)
+
TRANS(XVF16GER2, do_ger_XX3, GER_NOP, gen_helper_XVF16GER2)
TRANS(XVF16GER2PP, do_ger_XX3, GER_PP, gen_helper_XVF16GER2)
TRANS(XVF16GER2PN, do_ger_XX3, GER_PN, gen_helper_XVF16GER2)
@@ -2957,6 +2963,12 @@ TRANS64(PMXVF16GER2PN, do_ger_MMIRR_XX3, GER_PN,
gen_helper_XVF16GER2)
TRANS64(PMXVF16GER2NP, do_ger_MMIRR_XX3, GER_NP, gen_helper_XVF16GER2)
TRANS64(PMXVF16GER2NN, do_ger_MMIRR_XX3, GER_NN, gen_helper_XVF16GER2)
+TRANS64(PMXVBF16GER2, do_ger_MMIRR_XX3, GER_NOP, gen_helper_XVBF16GER2)
+TRANS64(PMXVBF16GER2PP, do_ger_MMIRR_XX3, GER_PP, gen_helper_XVBF16GER2)
+TRANS64(PMXVBF16GER2PN, do_ger_MMIRR_XX3, GER_PN, gen_helper_XVBF16GER2)
+TRANS64(PMXVBF16GER2NP, do_ger_MMIRR_XX3, GER_NP, gen_helper_XVBF16GER2)
+TRANS64(PMXVBF16GER2NN, do_ger_MMIRR_XX3, GER_NN, gen_helper_XVBF16GER2)
+
TRANS64(PMXVF32GER, do_ger_MMIRR_XX3_NO_PMSK, GER_NOP, gen_helper_XVF32GER)
TRANS64(PMXVF32GERPP, do_ger_MMIRR_XX3_NO_PMSK, GER_PP, gen_helper_XVF32GER)
TRANS64(PMXVF32GERPN, do_ger_MMIRR_XX3_NO_PMSK, GER_PN, gen_helper_XVF32GER)
--
2.31.1
