From patchwork Fri Jan 4 22:31:11 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 154804 Delivered-To: patch@linaro.org Received: by 2002:a2e:299d:0:0:0:0:0 with SMTP id p29-v6csp1093681ljp; Fri, 4 Jan 2019 14:36:49 -0800 (PST) X-Google-Smtp-Source: ALg8bN4nigtIYhtMztf2mkBD/y+hvlCnkOxMV75XLi48tevdqHuY+TIgaguPjODXl3aAN5QwollH X-Received: by 2002:a1c:dd04:: with SMTP id u4mr2570146wmg.84.1546641409880; Fri, 04 Jan 2019 14:36:49 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1546641409; cv=none; d=google.com; s=arc-20160816; b=GZAE3P4pHZgQERR/86CsqhGv8Sd594qDffMN3z7ya9qhAuToVkXaAuUxfsDrfReEVZ bTE8ukSEtxUfkPwj5qV759kyO+IhcWY7qY0TaIk+kMTHOMPlu4aDKAxT2oW4Bj8JHsfY iCP9WziP7nu20JBWtcZskr3XZnegOGgaJ+ILzJslwKOG3dEuNjCzOt5WxM5QNZYG/Bj3 qkX7a2Day1qGnSW0EYifWiJjtTv8RBIl6LCBuB7jh7fZwwIgM4zzAhkf8fJ/JMiBFmud 564JWOqKppZI2zLWUrMDqMQfn7JYGZGwoPEoHurdmwUTgnQ+vtaYiF2sa8z+kS++XP2Y Cnaw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:to:from:dkim-signature; bh=oc2/ydQBmZXr7b3KRnpHwkAcfEDqqil/zgo+zZnn/do=; b=XgrTpPOtbQ7Y5o68rD8KDPJA3bwWDdiy4ia0IV+fCpdqHzGOH4aEoU5f5iBXwHa0MF BvZMZyph96U/Yfi91GxplTORn+zgyy9c76AYLS0F+zqLSA7BaX+q7WK+Uq3+LxHw02j7 cDhIlm/gqBCDxCDGzprseINaIS9fwfYkKVQtIJkuRBEOrRUEGOMnS/dxsUEq493vgTyp COy3RP18yLI2tTroVcFjuRHaNQ8kE7tlWLtvBc4qpfEyOnuN279eOjtkMAv7npB98u6I 2at1uiVkzNx1ZoTeTN5o7lx4z/j46gqdYCwVeu1u88vMNVP2H6ludiCoPNr1GNi6JlIU IUnQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b="j/4dtI7H"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from listsout.gnu.org (listsout.gnu.org. [208.118.235.17]) by mx.google.com with ESMTPS id w15si32536076wrn.103.2019.01.04.14.36.49 for (version=TLS1 cipher=AES128-SHA bits=128/128); Fri, 04 Jan 2019 14:36:49 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b="j/4dtI7H"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([127.0.0.1]:57545 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gfY5A-0000VE-KI for patch@linaro.org; Fri, 04 Jan 2019 17:36:48 -0500 Received: from eggsout.gnu.org ([209.51.188.92]:54877 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gfY0F-0002oD-4a for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:45 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gfY0D-0001to-4b for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:43 -0500 Received: from mail-io1-xd44.google.com ([2607:f8b0:4864:20::d44]:36634) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1gfY0C-0001r7-UR for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:41 -0500 Received: by mail-io1-xd44.google.com with SMTP id m19so30707930ioh.3 for ; Fri, 04 Jan 2019 14:31:40 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references; bh=oc2/ydQBmZXr7b3KRnpHwkAcfEDqqil/zgo+zZnn/do=; b=j/4dtI7Hgf6ABlYoR0XjnUC1FiGsRJsH2Fc3d/VgAGgDjtogw2QJKAR0tAbTdN+m+X EvZ9+GCUuoXvtckifrRiTHF5DRHSlYS+9+N8jkIwukeEBRhfuWi4DRvl0/8zCQ9gZ+aN YKwQ3vGKNaVP143HsCTgRwdXjXleJgMGzKr+g= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=oc2/ydQBmZXr7b3KRnpHwkAcfEDqqil/zgo+zZnn/do=; b=DmhaekliemdY2R0XYYoRpnH2v06+wJP67pqcsryc4JiBhYlunDPYC5z5dmta5CakVp kqSo+A8wtkKnRsWZTTk+k3ZzDPkArKO9MD/G9wBCgj/6iGGOmvAwwghYHSXnegx1od5p RiSM2nuObif+XshWfGjaMWGtzzU7lP7p6U45LRBUCqabNbWrbqJfW9YJffkflCmAZhZD MWJzpdFzu2QHL5V4q+7lClf5aQgCVbqCvNG1ZSRT9DpPTTootcql821jP6BQXHp2JmI/ r/ClgzNNgxN1OVBuRwJODjQPVlCKs9pOuiVsyHMebWL61mkFErBTZyDgau/Q6bstwkxE Uobw== X-Gm-Message-State: AJcUukcRsBnax7rFJEMnK0qepBWjfMgUu9028u0fBxzxqz17HTgNpufj YlBkfnHAcmSypQaG+nbErBTy0Yun3Ro= X-Received: by 2002:a6b:d803:: with SMTP id y3mr39385073iob.247.1546641099522; Fri, 04 Jan 2019 14:31:39 -0800 (PST) Received: from cloudburst.twiddle.net ([172.56.12.23]) by smtp.gmail.com with ESMTPSA id t6sm27793259ioc.87.2019.01.04.14.31.36 for (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Fri, 04 Jan 2019 14:31:38 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Sat, 5 Jan 2019 08:31:11 +1000 Message-Id: <20190104223116.14037-6-richard.henderson@linaro.org> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20190104223116.14037-1-richard.henderson@linaro.org> References: <20190104223116.14037-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::d44 Subject: [Qemu-devel] [PATCH v2 05/10] tcg: Add opcodes for vector minmax arithmetic X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" Signed-off-by: Richard Henderson --- accel/tcg/tcg-runtime.h | 20 ++++ tcg/aarch64/tcg-target.h | 1 + tcg/i386/tcg-target.h | 1 + tcg/tcg-op-gvec.h | 10 ++ tcg/tcg-op.h | 4 + tcg/tcg-opc.h | 4 + tcg/tcg.h | 1 + accel/tcg/tcg-runtime-gvec.c | 224 +++++++++++++++++++++++++++++++++++ tcg/tcg-op-gvec.c | 108 +++++++++++++++++ tcg/tcg-op-vec.c | 20 ++++ tcg/tcg.c | 5 + 11 files changed, 398 insertions(+) -- 2.17.2 diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index 835ddfebb2..dfe325625c 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -200,6 +200,26 @@ DEF_HELPER_FLAGS_4(gvec_ussub16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ussub32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ussub64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smin8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smin16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smin32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smin64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_smax8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smax16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smax32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smax64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_umin8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umin16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umin32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umin64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_umax8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umax16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umax32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umax64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(gvec_neg8, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_neg16, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_neg32, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h index 98556bcf22..545a6eec75 100644 --- a/tcg/aarch64/tcg-target.h +++ b/tcg/aarch64/tcg-target.h @@ -136,6 +136,7 @@ typedef enum { #define TCG_TARGET_HAS_cmp_vec 1 #define TCG_TARGET_HAS_mul_vec 1 #define TCG_TARGET_HAS_sat_vec 0 +#define TCG_TARGET_HAS_minmax_vec 0 #define TCG_TARGET_DEFAULT_MO (0) #define TCG_TARGET_HAS_MEMORY_BSWAP 1 diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 44381062e6..7bd7eae672 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -186,6 +186,7 @@ extern bool have_avx2; #define TCG_TARGET_HAS_cmp_vec 1 #define TCG_TARGET_HAS_mul_vec 1 #define TCG_TARGET_HAS_sat_vec 0 +#define TCG_TARGET_HAS_minmax_vec 0 #define TCG_TARGET_deposit_i32_valid(ofs, len) \ (((ofs) == 0 && (len) == 8) || ((ofs) == 8 && (len) == 8) || \ diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h index 2cb447112e..4734eef7de 100644 --- a/tcg/tcg-op-gvec.h +++ b/tcg/tcg-op-gvec.h @@ -234,6 +234,16 @@ void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +/* Min/max. */ +void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_umax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz); + void tcg_gen_gvec_and(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz); void tcg_gen_gvec_or(unsigned vece, uint32_t dofs, uint32_t aofs, diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h index 4a93d730e8..2d98868d8f 100644 --- a/tcg/tcg-op.h +++ b/tcg/tcg-op.h @@ -971,6 +971,10 @@ void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_smin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_umin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_smax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); +void tcg_gen_umax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b); void tcg_gen_shli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); void tcg_gen_shri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i); diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h index 94b2ed80af..4e0238ad1a 100644 --- a/tcg/tcg-opc.h +++ b/tcg/tcg-opc.h @@ -226,6 +226,10 @@ DEF(ssadd_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_sat_vec)) DEF(usadd_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_sat_vec)) DEF(sssub_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_sat_vec)) DEF(ussub_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_sat_vec)) +DEF(smin_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_minmax_vec)) +DEF(umin_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_minmax_vec)) +DEF(smax_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_minmax_vec)) +DEF(umax_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_minmax_vec)) DEF(and_vec, 1, 2, 0, IMPLVEC) DEF(or_vec, 1, 2, 0, IMPLVEC) diff --git a/tcg/tcg.h b/tcg/tcg.h index df24afa425..1c3579077d 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -184,6 +184,7 @@ typedef uint64_t TCGRegSet; #define TCG_TARGET_HAS_shv_vec 0 #define TCG_TARGET_HAS_mul_vec 0 #define TCG_TARGET_HAS_sat_vec 0 +#define TCG_TARGET_HAS_minmax_vec 0 #else #define TCG_TARGET_MAYBE_vec 1 #endif diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index d1802467d5..9358749741 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -1028,3 +1028,227 @@ void HELPER(gvec_ussub64)(void *d, void *a, void *b, uint32_t desc) } clear_high(d, oprsz, desc); } + +void HELPER(gvec_smin8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int8_t)) { + int8_t aa = *(int8_t *)(a + i); + int8_t bb = *(int8_t *)(b + i); + int8_t dd = aa < bb ? aa : bb; + *(int8_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smin16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int16_t)) { + int16_t aa = *(int16_t *)(a + i); + int16_t bb = *(int16_t *)(b + i); + int16_t dd = aa < bb ? aa : bb; + *(int16_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smin32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int32_t)) { + int32_t aa = *(int32_t *)(a + i); + int32_t bb = *(int32_t *)(b + i); + int32_t dd = aa < bb ? aa : bb; + *(int32_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smin64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int64_t)) { + int64_t aa = *(int64_t *)(a + i); + int64_t bb = *(int64_t *)(b + i); + int64_t dd = aa < bb ? aa : bb; + *(int64_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smax8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int8_t)) { + int8_t aa = *(int8_t *)(a + i); + int8_t bb = *(int8_t *)(b + i); + int8_t dd = aa > bb ? aa : bb; + *(int8_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smax16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int16_t)) { + int16_t aa = *(int16_t *)(a + i); + int16_t bb = *(int16_t *)(b + i); + int16_t dd = aa > bb ? aa : bb; + *(int16_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smax32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int32_t)) { + int32_t aa = *(int32_t *)(a + i); + int32_t bb = *(int32_t *)(b + i); + int32_t dd = aa > bb ? aa : bb; + *(int32_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_smax64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int64_t)) { + int64_t aa = *(int64_t *)(a + i); + int64_t bb = *(int64_t *)(b + i); + int64_t dd = aa > bb ? aa : bb; + *(int64_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umin8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + uint8_t aa = *(uint8_t *)(a + i); + uint8_t bb = *(uint8_t *)(b + i); + uint8_t dd = aa < bb ? aa : bb; + *(uint8_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umin16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint16_t)) { + uint16_t aa = *(uint16_t *)(a + i); + uint16_t bb = *(uint16_t *)(b + i); + uint16_t dd = aa < bb ? aa : bb; + *(uint16_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umin32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint32_t)) { + uint32_t aa = *(uint32_t *)(a + i); + uint32_t bb = *(uint32_t *)(b + i); + uint32_t dd = aa < bb ? aa : bb; + *(uint32_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umin64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint64_t)) { + uint64_t aa = *(uint64_t *)(a + i); + uint64_t bb = *(uint64_t *)(b + i); + uint64_t dd = aa < bb ? aa : bb; + *(uint64_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umax8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + uint8_t aa = *(uint8_t *)(a + i); + uint8_t bb = *(uint8_t *)(b + i); + uint8_t dd = aa > bb ? aa : bb; + *(uint8_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umax16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint16_t)) { + uint16_t aa = *(uint16_t *)(a + i); + uint16_t bb = *(uint16_t *)(b + i); + uint16_t dd = aa > bb ? aa : bb; + *(uint16_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umax32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint32_t)) { + uint32_t aa = *(uint32_t *)(a + i); + uint32_t bb = *(uint32_t *)(b + i); + uint32_t dd = aa > bb ? aa : bb; + *(uint32_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_umax64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint64_t)) { + uint64_t aa = *(uint64_t *)(a + i); + uint64_t bb = *(uint64_t *)(b + i); + uint64_t dd = aa > bb ? aa : bb; + *(uint64_t *)(d + i) = dd; + } + clear_high(d, oprsz, desc); +} diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index 0a33f51065..3ee44fcb75 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -1810,6 +1810,114 @@ void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); } +void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fniv = tcg_gen_smin_vec, + .fno = gen_helper_gvec_smin8, + .opc = INDEX_op_smin_vec, + .vece = MO_8 }, + { .fniv = tcg_gen_smin_vec, + .fno = gen_helper_gvec_smin16, + .opc = INDEX_op_smin_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_smin_i32, + .fniv = tcg_gen_smin_vec, + .fno = gen_helper_gvec_smin32, + .opc = INDEX_op_smin_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_smin_i64, + .fniv = tcg_gen_smin_vec, + .fno = gen_helper_gvec_smin64, + .opc = INDEX_op_smin_vec, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); +} + +void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fniv = tcg_gen_umin_vec, + .fno = gen_helper_gvec_umin8, + .opc = INDEX_op_umin_vec, + .vece = MO_8 }, + { .fniv = tcg_gen_umin_vec, + .fno = gen_helper_gvec_umin16, + .opc = INDEX_op_umin_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_umin_i32, + .fniv = tcg_gen_umin_vec, + .fno = gen_helper_gvec_umin32, + .opc = INDEX_op_umin_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_umin_i64, + .fniv = tcg_gen_umin_vec, + .fno = gen_helper_gvec_umin64, + .opc = INDEX_op_umin_vec, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); +} + +void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fniv = tcg_gen_smax_vec, + .fno = gen_helper_gvec_smax8, + .opc = INDEX_op_smax_vec, + .vece = MO_8 }, + { .fniv = tcg_gen_smax_vec, + .fno = gen_helper_gvec_smax16, + .opc = INDEX_op_smax_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_smax_i32, + .fniv = tcg_gen_smax_vec, + .fno = gen_helper_gvec_smax32, + .opc = INDEX_op_smax_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_smax_i64, + .fniv = tcg_gen_smax_vec, + .fno = gen_helper_gvec_smax64, + .opc = INDEX_op_smax_vec, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); +} + +void tcg_gen_gvec_umax(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fniv = tcg_gen_umax_vec, + .fno = gen_helper_gvec_umax8, + .opc = INDEX_op_umax_vec, + .vece = MO_8 }, + { .fniv = tcg_gen_umax_vec, + .fno = gen_helper_gvec_umax16, + .opc = INDEX_op_umax_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_umax_i32, + .fniv = tcg_gen_umax_vec, + .fno = gen_helper_gvec_umax32, + .opc = INDEX_op_umax_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_umax_i64, + .fniv = tcg_gen_umax_vec, + .fno = gen_helper_gvec_umax64, + .opc = INDEX_op_umax_vec, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); +} + /* Perform a vector negation using normal negation and a mask. Compare gen_subv_mask above. */ static void gen_negv_mask(TCGv_i64 d, TCGv_i64 b, TCGv_i64 m) diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index 675aa09258..36f35022ac 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -433,3 +433,23 @@ void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) { do_op3(vece, r, a, b, INDEX_op_ussub_vec); } + +void tcg_gen_smin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) +{ + do_op3(vece, r, a, b, INDEX_op_smin_vec); +} + +void tcg_gen_umin_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) +{ + do_op3(vece, r, a, b, INDEX_op_umin_vec); +} + +void tcg_gen_smax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) +{ + do_op3(vece, r, a, b, INDEX_op_smax_vec); +} + +void tcg_gen_umax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) +{ + do_op3(vece, r, a, b, INDEX_op_umax_vec); +} diff --git a/tcg/tcg.c b/tcg/tcg.c index 15ed5af007..1ae1e788f6 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -1612,6 +1612,11 @@ bool tcg_op_supported(TCGOpcode op) case INDEX_op_sssub_vec: case INDEX_op_ussub_vec: return have_vec && TCG_TARGET_HAS_sat_vec; + case INDEX_op_smin_vec: + case INDEX_op_umin_vec: + case INDEX_op_smax_vec: + case INDEX_op_umax_vec: + return have_vec && TCG_TARGET_HAS_minmax_vec; default: tcg_debug_assert(op > INDEX_op_last_generic && op < NB_OPS);