[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 28/29] target/arm: Simplify SMMLA, SMMLAR, SMMLS, SMM
From: |
Peter Maydell |
Subject: |
[Qemu-devel] [PULL 28/29] target/arm: Simplify SMMLA, SMMLAR, SMMLS, SMMLSR |
Date: |
Fri, 16 Aug 2019 14:17:18 +0100 |
From: Richard Henderson <address@hidden>
All of the inputs to these instructions are 32-bits. Rather than
extend each input to 64-bits and then extract the high 32-bits of
the output, use tcg_gen_muls2_i32 and other 32-bit generator functions.
Signed-off-by: Richard Henderson <address@hidden>
Message-id: address@hidden
Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Peter Maydell <address@hidden>
---
target/arm/translate.c | 72 +++++++++++++++---------------------------
1 file changed, 26 insertions(+), 46 deletions(-)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 2e160646206..9e2853fe76c 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -376,34 +376,6 @@ static void gen_revsh(TCGv_i32 var)
tcg_gen_ext16s_i32(var, var);
}
-/* Return (b << 32) + a. Mark inputs as dead */
-static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv_i32 b)
-{
- TCGv_i64 tmp64 = tcg_temp_new_i64();
-
- tcg_gen_extu_i32_i64(tmp64, b);
- tcg_temp_free_i32(b);
- tcg_gen_shli_i64(tmp64, tmp64, 32);
- tcg_gen_add_i64(a, tmp64, a);
-
- tcg_temp_free_i64(tmp64);
- return a;
-}
-
-/* Return (b << 32) - a. Mark inputs as dead. */
-static TCGv_i64 gen_subq_msw(TCGv_i64 a, TCGv_i32 b)
-{
- TCGv_i64 tmp64 = tcg_temp_new_i64();
-
- tcg_gen_extu_i32_i64(tmp64, b);
- tcg_temp_free_i32(b);
- tcg_gen_shli_i64(tmp64, tmp64, 32);
- tcg_gen_sub_i64(a, tmp64, a);
-
- tcg_temp_free_i64(tmp64);
- return a;
-}
-
/* 32x32->64 multiply. Marks inputs as dead. */
static TCGv_i64 gen_mulu_i64_i32(TCGv_i32 a, TCGv_i32 b)
{
@@ -8857,23 +8829,27 @@ static void disas_arm_insn(DisasContext *s, unsigned
int insn)
(SMMUL, SMMLA, SMMLS) */
tmp = load_reg(s, rm);
tmp2 = load_reg(s, rs);
- tmp64 = gen_muls_i64_i32(tmp, tmp2);
+ tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2);
if (rd != 15) {
- tmp = load_reg(s, rd);
+ tmp3 = load_reg(s, rd);
if (insn & (1 << 6)) {
- tmp64 = gen_subq_msw(tmp64, tmp);
+ tcg_gen_sub_i32(tmp, tmp, tmp3);
} else {
- tmp64 = gen_addq_msw(tmp64, tmp);
+ tcg_gen_add_i32(tmp, tmp, tmp3);
}
+ tcg_temp_free_i32(tmp3);
}
if (insn & (1 << 5)) {
- tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u);
+ /*
+ * Adding 0x80000000 to the 64-bit quantity
+ * means that we have carry in to the high
+ * word when the low word has the high bit set.
+ */
+ tcg_gen_shri_i32(tmp2, tmp2, 31);
+ tcg_gen_add_i32(tmp, tmp, tmp2);
}
- tcg_gen_shri_i64(tmp64, tmp64, 32);
- tmp = tcg_temp_new_i32();
- tcg_gen_extrl_i64_i32(tmp, tmp64);
- tcg_temp_free_i64(tmp64);
+ tcg_temp_free_i32(tmp2);
store_reg(s, rn, tmp);
break;
case 0:
@@ -10099,22 +10075,26 @@ static void disas_thumb2_insn(DisasContext *s,
uint32_t insn)
}
break;
case 5: case 6: /* 32 * 32 -> 32msb (SMMUL, SMMLA, SMMLS) */
- tmp64 = gen_muls_i64_i32(tmp, tmp2);
+ tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2);
if (rs != 15) {
- tmp = load_reg(s, rs);
+ tmp3 = load_reg(s, rs);
if (insn & (1 << 20)) {
- tmp64 = gen_addq_msw(tmp64, tmp);
+ tcg_gen_add_i32(tmp, tmp, tmp3);
} else {
- tmp64 = gen_subq_msw(tmp64, tmp);
+ tcg_gen_sub_i32(tmp, tmp, tmp3);
}
+ tcg_temp_free_i32(tmp3);
}
if (insn & (1 << 4)) {
- tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u);
+ /*
+ * Adding 0x80000000 to the 64-bit quantity
+ * means that we have carry in to the high
+ * word when the low word has the high bit set.
+ */
+ tcg_gen_shri_i32(tmp2, tmp2, 31);
+ tcg_gen_add_i32(tmp, tmp, tmp2);
}
- tcg_gen_shri_i64(tmp64, tmp64, 32);
- tmp = tcg_temp_new_i32();
- tcg_gen_extrl_i64_i32(tmp, tmp64);
- tcg_temp_free_i64(tmp64);
+ tcg_temp_free_i32(tmp2);
break;
case 7: /* Unsigned sum of absolute differences. */
gen_helper_usad8(tmp, tmp, tmp2);
--
2.20.1
- [Qemu-devel] [PULL 12/29] target/arm: Replace offset with pc in gen_exception_insn, (continued)
- [Qemu-devel] [PULL 12/29] target/arm: Replace offset with pc in gen_exception_insn, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 18/29] target/arm/cpu: Ensure we can use the pmu with kvm, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 20/29] target/arm/cpu: Use div-round-up to determine predicate register array size, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 21/29] target/arm/kvm64: Fix error returns, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 24/29] target/arm: Use tcg_gen_deposit_i32 for PKHBT, PKHTB, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 27/29] target/arm: Use tcg_gen_rotri_i32 for gen_swap_half, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 23/29] target/arm: Use tcg_gen_extract_i32 for shifter_out_im, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 25/29] target/arm: Remove redundant shift tests, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 22/29] target/arm/kvm64: Move the get/put of fpsimd registers out, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 26/29] target/arm: Use ror32 instead of open-coding the operation, Peter Maydell, 2019/08/16
- [Qemu-devel] [PULL 28/29] target/arm: Simplify SMMLA, SMMLAR, SMMLS, SMMLSR,
Peter Maydell <=
- [Qemu-devel] [PULL 29/29] target/arm: Use tcg_gen_extrh_i64_i32 to extract the high word, Peter Maydell, 2019/08/16
- Re: [Qemu-devel] [PULL 00/29] target-arm queue, Peter Maydell, 2019/08/16