diff mbox series

[v3,5/8] target/ppc: Implemented xvf16ger*

Message ID 20220517183735.110342-6-lucas.araujo@eldorado.org.br
State New
Headers show
Series VSX MMA Implementation | expand

Commit Message

Lucas Mateus Martins Araujo e Castro May 17, 2022, 6:37 p.m. UTC 
From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
xvf16ger2:   VSX Vector 16-bit Floating-Point GER (rank-2 update)
xvf16ger2nn: VSX Vector 16-bit Floating-Point GER (rank-2 update) Negative
multiply, Negative accumulate
xvf16ger2np: VSX Vector 16-bit Floating-Point GER (rank-2 update) Negative
multiply, Positive accumulate
xvf16ger2pn: VSX Vector 16-bit Floating-Point GER (rank-2 update) Positive
multiply, Negative accumulate
xvf16ger2pp: VSX Vector 16-bit Floating-Point GER (rank-2 update) Positive
multiply, Positive accumulate

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
---
 target/ppc/cpu.h                    |  3 +
 target/ppc/fpu_helper.c             | 93 +++++++++++++++++++++++++++++
 target/ppc/helper.h                 |  5 ++
 target/ppc/insn32.decode            |  6 ++
 target/ppc/translate/vsx-impl.c.inc |  6 ++
 5 files changed, 113 insertions(+)

Comments

Richard Henderson May 17, 2022, 7:40 p.m. UTC | #1 
On 5/17/22 11:37, Lucas Mateus Castro(alqotel) wrote:
> +static inline float32 bfp32_negate(float32 a)
> +{
> +    if (unlikely(((a & 0x7f800000) == 0x7f800000) && (a & 0x007fffff))) {

float32_is_any_nan.

> +                    if (neg_mul) {
> +                        msum = bfp32_negate(msum);
> +                    }
> +                    if (neg_acc) {
> +                        at[i].VsrSF(j) = float32_sub(msum, aux_acc, excp_ptr);
> +                    } else {
> +                        at[i].VsrSF(j) = float32_add(msum, aux_acc, excp_ptr);
> +                    }

Hmm.  Since we're using negate once, perhaps just go ahead and use it twice.

Or go all the way with

     if (!neg_mul && !neg_acc) {
         r = float32_add(msum, aux_acc, excp_ptr);
     } else if (!neg_mul) {
         r = float32_sub(msum, aux_acc, excp_ptr);
     } else if (!neg_acc) {
         r = float32_sub(aux_acc, msum, excp_ptr);
     } else {
         r = float32_add(bfp32_neg(msum), bfp32_neg(aux_acc), excp_ptr);
     }

Otherwise, the logic seems sane.


r~
diff mbox series

Patch

diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index bdedf4138e..46769a5647 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -227,6 +227,7 @@  typedef union _ppc_vsr_t {
     int16_t s16[8];
     int32_t s32[4];
     int64_t s64[2];
+    float16 f16[8];
     float32 f32[4];
     float64 f64[2];
     float128 f128;
@@ -2641,6 +2642,7 @@  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 VsrHF(i) f16[i]
 #define VsrSF(i) f32[i]
 #define VsrDF(i) f64[i]
 #else
@@ -2652,6 +2654,7 @@  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 VsrHF(i) f16[7 - (i)]
 #define VsrSF(i) f32[3 - (i)]
 #define VsrDF(i) f64[1 - (i)]
 #endif
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 8451de628b..a13c92df9e 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -36,6 +36,15 @@  static inline float128 float128_snan_to_qnan(float128 x)
 #define float32_snan_to_qnan(x) ((x) | 0x00400000)
 #define float16_snan_to_qnan(x) ((x) | 0x0200)
 
+static inline float32 bfp32_negate(float32 a)
+{
+    if (unlikely(((a & 0x7f800000) == 0x7f800000) && (a & 0x007fffff))) {
+        return a;
+    } else {
+        return float32_chs(a);
+    }
+}
+
 static inline bool fp_exceptions_enabled(CPUPPCState *env)
 {
 #ifdef CONFIG_USER_ONLY
@@ -3502,6 +3511,55 @@  static inline void vsxger_excp(CPUPPCState *env, uintptr_t retaddr)
     do_fpscr_check_status(env, retaddr);
 }
 
+typedef float64 extract_f16(float16, float_status *);
+
+static float64 extract_hf16(float16 in, float_status *fp_status)
+{
+    return float16_to_float64(in, true, 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)
+{
+    float32 msum, aux_acc;
+    float64 psum, va, vb, vc, vd;
+    int i, j, xmsk_bit, ymsk_bit;
+    uint8_t pmsk = FIELD_EX32(mask, GER_MSK, PMSK),
+            xmsk = FIELD_EX32(mask, GER_MSK, XMSK),
+            ymsk = FIELD_EX32(mask, GER_MSK, YMSK);
+    float_status *excp_ptr = &env->fp_status;
+    for (i = 0, xmsk_bit = 1 << 3; i < 4; i++, xmsk_bit >>= 1) {
+        for (j = 0, ymsk_bit = 1 << 3; j < 4; j++, ymsk_bit >>= 1) {
+            if ((xmsk_bit & xmsk) && (ymsk_bit & ymsk)) {
+                va = !(pmsk & 2) ? float64_zero : extract(a->VsrHF(2 * i), excp_ptr);
+                vb = !(pmsk & 2) ? float64_zero : extract(b->VsrHF(2 * j), excp_ptr);
+                vc = !(pmsk & 1) ? float64_zero : extract(a->VsrHF(2 * i + 1), excp_ptr);
+                vd = !(pmsk & 1) ? float64_zero : extract(b->VsrHF(2 * j + 1), excp_ptr);
+                psum = float64_mul(va, vb, excp_ptr);
+                psum = float64r32_muladd(vc, vd, psum, 0, excp_ptr);
+                msum = float64_to_float32(psum, excp_ptr);
+                if (acc) {
+                    aux_acc = at[i].VsrSF(j);
+                    if (neg_mul) {
+                        msum = bfp32_negate(msum);
+                    }
+                    if (neg_acc) {
+                        at[i].VsrSF(j) = float32_sub(msum, aux_acc, excp_ptr);
+                    } else {
+                        at[i].VsrSF(j) = float32_add(msum, aux_acc, excp_ptr);
+                    }
+                } else {
+                    at[i].VsrSF(j) = msum;
+                }
+            } else {
+                at[i].VsrSF(j) = float32_zero;
+            }
+        }
+    }
+    vsxger_excp(env, GETPC());
+}
+
 typedef void vsxger_zero(ppc_vsr_t *at, int, int);
 
 typedef void vsxger_muladd_f(ppc_vsr_t *, ppc_vsr_t *, ppc_vsr_t *, int, int,
@@ -3579,6 +3637,41 @@  static void vsxger(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, ppc_acc_t  *at,
     vsxger_excp(env, GETPC());
 }
 
+QEMU_FLATTEN
+void helper_XVF16GER2(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_hf16);
+}
+
+QEMU_FLATTEN
+void helper_XVF16GER2PP(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_hf16);
+}
+
+QEMU_FLATTEN
+void helper_XVF16GER2PN(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_hf16);
+}
+
+QEMU_FLATTEN
+void helper_XVF16GER2NP(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_hf16);
+}
+
+QEMU_FLATTEN
+void helper_XVF16GER2NN(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_hf16);
+}
+
 QEMU_FLATTEN
 void helper_XVF32GER(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 054d25f3b0..7ab5ac8ee7 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -550,6 +550,11 @@  DEF_HELPER_5(XVI16GER2, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVI16GER2S, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVI16GER2PP, void, env, vsr, vsr, acc, i32)
 DEF_HELPER_5(XVI16GER2SPP, void, env, vsr, vsr, acc, i32)
+DEF_HELPER_5(XVF16GER2, void, env, vsr, vsr, acc, i32)
+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(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 c561a17c7d..c774227d8c 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -739,6 +739,12 @@  XVI8GER4SPP     111011 ... -- ..... ..... 01100011 ..-  @XX3_at xa=%xx_xa
 XVI16GER2S      111011 ... -- ..... ..... 00101011 ..-  @XX3_at xa=%xx_xa
 XVI16GER2SPP    111011 ... -- ..... ..... 00101010 ..-  @XX3_at xa=%xx_xa
 
+XVF16GER2       111011 ... -- ..... ..... 00010011 ..-  @XX3_at xa=%xx_xa
+XVF16GER2PP     111011 ... -- ..... ..... 00010010 ..-  @XX3_at xa=%xx_xa
+XVF16GER2PN     111011 ... -- ..... ..... 10010010 ..-  @XX3_at xa=%xx_xa
+XVF16GER2NP     111011 ... -- ..... ..... 01010010 ..-  @XX3_at xa=%xx_xa
+XVF16GER2NN     111011 ... -- ..... ..... 11010010 ..-  @XX3_at xa=%xx_xa
+
 XVF32GER        111011 ... -- ..... ..... 00011011 ..-  @XX3_at xa=%xx_xa
 XVF32GERPP      111011 ... -- ..... ..... 00011010 ..-  @XX3_at xa=%xx_xa
 XVF32GERPN      111011 ... -- ..... ..... 10011010 ..-  @XX3_at xa=%xx_xa
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 76747956bb..232a4d881e 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -2869,6 +2869,12 @@  TRANS64(PMXVI16GER2PP, do_ger, gen_helper_XVI16GER2PP)
 TRANS64(PMXVI16GER2S, do_ger, gen_helper_XVI16GER2S)
 TRANS64(PMXVI16GER2SPP, do_ger, gen_helper_XVI16GER2SPP)
 
+TRANS(XVF16GER2, do_ger, gen_helper_XVF16GER2)
+TRANS(XVF16GER2PP, do_ger, gen_helper_XVF16GER2PP)
+TRANS(XVF16GER2PN, do_ger, gen_helper_XVF16GER2PN)
+TRANS(XVF16GER2NP, do_ger, gen_helper_XVF16GER2NP)
+TRANS(XVF16GER2NN, do_ger, gen_helper_XVF16GER2NN)
+
 TRANS(XVF32GER, do_ger, gen_helper_XVF32GER)
 TRANS(XVF32GERPP, do_ger, gen_helper_XVF32GERPP)
 TRANS(XVF32GERPN, do_ger, gen_helper_XVF32GERPN)