Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructi

qemu-devel

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructi

From:	LIU Zhiwei
Subject:	Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructions
Date:	Sat, 28 Mar 2020 23:47:57 +0800
User-agent:	Mozilla/5.0 (Windows NT 10.0; WOW64; rv:68.0) Gecko/20100101 Thunderbird/68.6.0



On 2020/3/28 11:23, Richard Henderson wrote:

On 3/17/20 8:06 AM, LIU Zhiwei wrote:

+    for (i = 0; i < vl; i++) {                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {        \
+            ETYPE s2 = *((ETYPE *)vs2 + H(i));            \
+            *((ETYPE *)vd + H1(i)) = s2;                  \

H1 should be H.

Yes.

+        } else {                                          \
+            *((ETYPE *)vd + H(i)) = (ETYPE)s1;            \
+        }                                                 \

You can also hoist the s2 dereference out of the IF, and let the assignment be
unconditional.

   *((ETYPE *)vd + H(i))
     = (!vm && !vext_elem_mask(v0, mlen, i) ? s2 : s1);

Yes, it's much better.

Zhiwei

r~

[Prev in Thread]

Current Thread

[Next in Thread]

[PATCH v6 37/61] target/riscv: vector floating-point min/max instructions, (continued)
- [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions, LIU Zhiwei, 2020/03/17
  - Re: [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions, Alistair Francis, 2020/03/25
- [PATCH v6 38/61] target/riscv: vector floating-point sign-injection instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 39/61] target/riscv: vector floating-point compare instructions, LIU Zhiwei, 2020/03/17
  - Re: [PATCH v6 39/61] target/riscv: vector floating-point compare instructions, Richard Henderson, 2020/03/27
    - Re: [PATCH v6 39/61] target/riscv: vector floating-point compare instructions, LIU Zhiwei, 2020/03/28
- [PATCH v6 40/61] target/riscv: vector floating-point classify instructions, LIU Zhiwei, 2020/03/17
  - Re: [PATCH v6 40/61] target/riscv: vector floating-point classify instructions, Richard Henderson, 2020/03/27
- [PATCH v6 41/61] target/riscv: vector floating-point merge instructions, LIU Zhiwei, 2020/03/17
  - Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructions, Richard Henderson, 2020/03/27
    - Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructions, LIU Zhiwei <=
- [PATCH v6 42/61] target/riscv: vector floating-point/integer type-convert instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 43/61] target/riscv: widening floating-point/integer type-convert instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 44/61] target/riscv: narrowing floating-point/integer type-convert instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 45/61] target/riscv: vector single-width integer reduction instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 46/61] target/riscv: vector wideing integer reduction instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 47/61] target/riscv: vector single-width floating-point reduction instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 48/61] target/riscv: vector widening floating-point reduction instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 49/61] target/riscv: vector mask-register logical instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 50/61] target/riscv: vector mask population count vmpopc, LIU Zhiwei, 2020/03/17
- [PATCH v6 51/61] target/riscv: vmfirst find-first-set mask bit, LIU Zhiwei, 2020/03/17

Prev by Date: Re: [PATCH v6 18/61] target/riscv: vector single-width integer multiply instructions
Next by Date: [Bug 1868116] Re: QEMU monitor no longer works
Previous by thread: Re: [PATCH v6 41/61] target/riscv: vector floating-point merge instructions
Next by thread: [PATCH v6 42/61] target/riscv: vector floating-point/integer type-convert instructions
Index(es):
- Date
- Thread