From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtpbguseast2.qq.com (smtpbguseast2.qq.com [54.204.34.130]) by sourceware.org (Postfix) with ESMTPS id 705E03858D20 for ; Mon, 26 Jun 2023 06:51:10 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 705E03858D20 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=rivai.ai Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=rivai.ai X-QQ-mid: bizesmtp67t1687762264thacgo2d Received: from server1.localdomain ( [58.60.1.22]) by bizesmtp.qq.com (ESMTP) with id ; Mon, 26 Jun 2023 14:51:03 +0800 (CST) X-QQ-SSF: 01400000000000G0S000000A0000000 X-QQ-FEAT: 3M0okmaRx3j+G7o/5mwqwvx1Sn6ZOpMTiu7p09kDmi7q0xQem/bnWpSLhTrnL xa3evhRgivO09ZRqmlu8bceNJIXoDO/RB2d1EbxrO8NRrOplN2rH6ZWcoZB8Zt+SgC4svuT 3XBJDzH47N/vY+kXUw64sHtKd4hPLK2twNIDxekVDWpQKo2rs9JY28Z6524Enmjx5M+3C3H +Ucoq+/RdF+Q1PvphiYGWrTNi3oPoJCZwbUw+Y3NuLpX2mOM/yn4IS0Q4Ijybw6N5XKTBkh H2m/GmSb51tSGs+AG7k7cTLbP0k9Zx+gGIDT9W2woOMicIIn2F4X55ma2jb3TuOmZR1Kvzp F7F5wjIPYIrwbSgKepsIByoBrFuPupdtfhUJgsOhiFtU9g2Mjretss/v5dyE4bCzp39L1hu KLg2UkcaMu8RlkaNmN+ysw== X-QQ-GoodBg: 2 X-BIZMAIL-ID: 8986735871860452586 From: Juzhe-Zhong To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, kito.cheng@sifive.com, palmer@dabbelt.com, palmer@rivosinc.com, jeffreyalaw@gmail.com, rdapp.gcc@gmail.com, Juzhe-Zhong Subject: [PATCH] RISC-V: Enhance RVV VLA SLP auto-vectorization Date: Mon, 26 Jun 2023 14:51:01 +0800 Message-Id: <20230626065101.75459-1-juzhe.zhong@rivai.ai> X-Mailer: git-send-email 2.36.1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-QQ-SENDSIZE: 520 Feedback-ID: bizesmtp:rivai.ai:qybglogicsvrgz:qybglogicsvrgz7a-one-0 X-Spam-Status: No, score=-10.3 required=5.0 tests=BAYES_00,GIT_PATCH_0,KAM_DMARC_STATUS,KAM_SHORT,RCVD_IN_BARRACUDACENTRAL,RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H4,RCVD_IN_MSPIKE_WL,SPF_HELO_PASS,SPF_PASS,TXREP,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: Currently, we are able to generate step vector with base == 0: { 0, 0, 2, 2, 4, 4, ... } ASM: vid vand However, we do wrong for step vector with base != 0: { 1, 1, 3, 3, 5, 5, ... } Before this patch, such case will run fail. After this patch, we are able to pass the testcase and generate the step vector with asm: vid vand vadd gcc/ChangeLog: * config/riscv/riscv-v.cc (expand_const_vector): Fix stepped vector with base != 0. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/autovec/partial/slp-17.c: New test. * gcc.target/riscv/rvv/autovec/partial/slp-18.c: New test. * gcc.target/riscv/rvv/autovec/partial/slp-19.c: New test. * gcc.target/riscv/rvv/autovec/partial/slp_run-17.c: New test. * gcc.target/riscv/rvv/autovec/partial/slp_run-18.c: New test. * gcc.target/riscv/rvv/autovec/partial/slp_run-19.c: New test. --- gcc/config/riscv/riscv-v.cc | 14 +++- .../riscv/rvv/autovec/partial/slp-17.c | 34 ++++++++ .../riscv/rvv/autovec/partial/slp-18.c | 26 ++++++ .../riscv/rvv/autovec/partial/slp-19.c | 26 ++++++ .../riscv/rvv/autovec/partial/slp_run-17.c | 84 +++++++++++++++++++ .../riscv/rvv/autovec/partial/slp_run-18.c | 69 +++++++++++++++ .../riscv/rvv/autovec/partial/slp_run-19.c | 69 +++++++++++++++ 7 files changed, 320 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-17.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-18.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-19.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-17.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-18.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-19.c diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index 5518394be1e..cd3422bf711 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -1258,7 +1258,6 @@ expand_const_vector (rtx target, rtx src) } emit_move_insn (target, tmp); } - return; } else if (CONST_VECTOR_STEPPED_P (src)) { @@ -1287,9 +1286,20 @@ expand_const_vector (rtx target, rtx src) */ rtx imm = gen_int_mode (-builder.npatterns (), builder.inner_mode ()); - rtx and_ops[] = {target, vid, imm}; + rtx tmp = gen_reg_rtx (builder.mode ()); + rtx and_ops[] = {tmp, vid, imm}; icode = code_for_pred_scalar (AND, builder.mode ()); emit_vlmax_insn (icode, RVV_BINOP, and_ops); + HOST_WIDE_INT init_val = INTVAL (builder.elt (0)); + if (init_val == 0) + emit_move_insn (target, tmp); + else + { + rtx dup = gen_const_vector_dup (builder.mode (), init_val); + rtx add_ops[] = {target, tmp, dup}; + icode = code_for_pred (PLUS, builder.mode ()); + emit_vlmax_insn (icode, RVV_BINOP, add_ops); + } } else { diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-17.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-17.c new file mode 100644 index 00000000000..2f2c3d11c2a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-17.c @@ -0,0 +1,34 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param riscv-autovec-preference=scalable -fdump-tree-optimized-details" } */ + +#include + +void +f (uint8_t *restrict a, uint8_t *restrict b, + uint8_t *restrict c, uint8_t *restrict d, + int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 8] = c[i * 8] + d[i * 8]; + a[i * 8 + 1] = c[i * 8] + d[i * 8 + 1]; + a[i * 8 + 2] = c[i * 8 + 2] + d[i * 8 + 2]; + a[i * 8 + 3] = c[i * 8 + 2] + d[i * 8 + 3]; + a[i * 8 + 4] = c[i * 8 + 4] + d[i * 8 + 4]; + a[i * 8 + 5] = c[i * 8 + 4] + d[i * 8 + 5]; + a[i * 8 + 6] = c[i * 8 + 6] + d[i * 8 + 6]; + a[i * 8 + 7] = c[i * 8 + 6] + d[i * 8 + 7]; + b[i * 8] = c[i * 8 + 1] + d[i * 8]; + b[i * 8 + 1] = c[i * 8 + 1] + d[i * 8 + 1]; + b[i * 8 + 2] = c[i * 8 + 3] + d[i * 8 + 2]; + b[i * 8 + 3] = c[i * 8 + 3] + d[i * 8 + 3]; + b[i * 8 + 4] = c[i * 8 + 5] + d[i * 8 + 4]; + b[i * 8 + 5] = c[i * 8 + 5] + d[i * 8 + 5]; + b[i * 8 + 6] = c[i * 8 + 7] + d[i * 8 + 6]; + b[i * 8 + 7] = c[i * 8 + 7] + d[i * 8 + 7]; + } +} + +/* { dg-final { scan-tree-dump-times "\.VEC_PERM" 2 "optimized" } } */ +/* { dg-final { scan-assembler {\tvid\.v} } } */ +/* { dg-final { scan-assembler-not {\tvmul} } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-18.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-18.c new file mode 100644 index 00000000000..72103314b1a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-18.c @@ -0,0 +1,26 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param riscv-autovec-preference=scalable -fdump-tree-optimized-details" } */ + +#include + +void +f (float *restrict a, float *restrict b, + float *restrict c, float *restrict d, + int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 4] = c[i * 4] + d[i * 4]; + a[i * 4 + 1] = c[i * 4] + d[i * 4 + 1]; + a[i * 4 + 2] = c[i * 4 + 2] + d[i * 4 + 2]; + a[i * 4 + 3] = c[i * 4 + 2] + d[i * 4 + 3]; + b[i * 4] = c[i * 4 + 1] + d[i * 4]; + b[i * 4 + 1] = c[i * 4 + 1] + d[i * 4 + 1]; + b[i * 4 + 2] = c[i * 4 + 3] + d[i * 4 + 2]; + b[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + } +} + +/* { dg-final { scan-tree-dump "\.VEC_PERM" "optimized" } } */ +/* { dg-final { scan-assembler {\tvid\.v} } } */ +/* { dg-final { scan-assembler-not {\tvmul} } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-19.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-19.c new file mode 100644 index 00000000000..41ce0fc5767 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-19.c @@ -0,0 +1,26 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param riscv-autovec-preference=scalable -fdump-tree-optimized-details" } */ + +#include + +void +f (float *restrict a, float *restrict b, + float *restrict c, float *restrict d, + int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 4] = c[i * 4] + d[i * 4]; + a[i * 4 + 1] = c[i * 4] + d[i * 4 + 1]; + a[i * 4 + 2] = c[i * 4 + 2] + d[i * 4 + 2]; + a[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + b[i * 4] = c[i * 4 + 2] + d[i * 4]; + b[i * 4 + 1] = c[i * 4 + 1] + d[i * 4 + 1]; + b[i * 4 + 2] = c[i * 4 + 3] + d[i * 4 + 2]; + b[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + } +} + +/* { dg-final { scan-tree-dump "\.VEC_PERM" "optimized" } } */ +/* { dg-final { scan-assembler {\tvid\.v} } } */ +/* { dg-final { scan-assembler-not {\tvmul} } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-17.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-17.c new file mode 100644 index 00000000000..224db4e3173 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-17.c @@ -0,0 +1,84 @@ +/* { dg-do run { target { riscv_vector } } } */ +/* { dg-additional-options "--param riscv-autovec-preference=scalable" } */ + +#include "slp-17.c" + +#define LIMIT 256 +void __attribute__ ((optimize (0))) +f_golden (uint8_t *restrict a, uint8_t *restrict b, uint8_t *restrict c, + uint8_t *restrict d, int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 8] = c[i * 8] + d[i * 8]; + a[i * 8 + 1] = c[i * 8] + d[i * 8 + 1]; + a[i * 8 + 2] = c[i * 8 + 2] + d[i * 8 + 2]; + a[i * 8 + 3] = c[i * 8 + 2] + d[i * 8 + 3]; + a[i * 8 + 4] = c[i * 8 + 4] + d[i * 8 + 4]; + a[i * 8 + 5] = c[i * 8 + 4] + d[i * 8 + 5]; + a[i * 8 + 6] = c[i * 8 + 6] + d[i * 8 + 6]; + a[i * 8 + 7] = c[i * 8 + 6] + d[i * 8 + 7]; + b[i * 8] = c[i * 8 + 1] + d[i * 8]; + b[i * 8 + 1] = c[i * 8 + 1] + d[i * 8 + 1]; + b[i * 8 + 2] = c[i * 8 + 3] + d[i * 8 + 2]; + b[i * 8 + 3] = c[i * 8 + 3] + d[i * 8 + 3]; + b[i * 8 + 4] = c[i * 8 + 5] + d[i * 8 + 4]; + b[i * 8 + 5] = c[i * 8 + 5] + d[i * 8 + 5]; + b[i * 8 + 6] = c[i * 8 + 7] + d[i * 8 + 6]; + b[i * 8 + 7] = c[i * 8 + 7] + d[i * 8 + 7]; + } +} + +int +main (void) +{ +#define RUN(NUM) \ + uint8_t a_##NUM[NUM * 8 + 8] = {0}; \ + uint8_t a_golden_##NUM[NUM * 8 + 8] = {0}; \ + uint8_t b_##NUM[NUM * 8 + 8] = {0}; \ + uint8_t b_golden_##NUM[NUM * 8 + 8] = {0}; \ + uint8_t c_##NUM[NUM * 8 + 8] = {0}; \ + uint8_t d_##NUM[NUM * 8 + 8] = {0}; \ + for (int i = 0; i < NUM * 8 + 8; i++) \ + { \ + if (i % NUM == 0) \ + c_##NUM[i] = (i + NUM) % LIMIT; \ + else \ + c_##NUM[i] = (i * 3) % LIMIT; \ + if (i % 2 == 0) \ + d_##NUM[i] = i % LIMIT; \ + else \ + d_##NUM[i] = (i * 7) % LIMIT; \ + } \ + f (a_##NUM, b_##NUM, c_##NUM, d_##NUM, NUM); \ + f_golden (a_golden_##NUM, b_golden_##NUM, c_##NUM, d_##NUM, NUM); \ + for (int i = 0; i < NUM * 8 + 8; i++) \ + { \ + if (a_##NUM[i] != a_golden_##NUM[i]) \ + __builtin_abort (); \ + if (b_##NUM[i] != b_golden_##NUM[i]) \ + __builtin_abort (); \ + } + + RUN (3); + RUN (5); + RUN (15); + RUN (16); + RUN (17); + RUN (31); + RUN (32); + RUN (33); + RUN (63); + RUN (64); + RUN (65); + RUN (127); + RUN (128); + RUN (129); + RUN (239); + RUN (359); + RUN (498); + RUN (799); + RUN (977); + RUN (5789); + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-18.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-18.c new file mode 100644 index 00000000000..7d22e1fd88e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-18.c @@ -0,0 +1,69 @@ +/* { dg-do run { target { riscv_vector } } } */ +/* { dg-additional-options "--param riscv-autovec-preference=scalable" } */ + +#include "slp-18.c" + +void __attribute__ ((optimize (0))) +f_golden (float *restrict a, float *restrict b, float *restrict c, + float *restrict d, int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 4] = c[i * 4] + d[i * 4]; + a[i * 4 + 1] = c[i * 4] + d[i * 4 + 1]; + a[i * 4 + 2] = c[i * 4 + 2] + d[i * 4 + 2]; + a[i * 4 + 3] = c[i * 4 + 2] + d[i * 4 + 3]; + b[i * 4] = c[i * 4 + 1] + d[i * 4]; + b[i * 4 + 1] = c[i * 4 + 1] + d[i * 4 + 1]; + b[i * 4 + 2] = c[i * 4 + 3] + d[i * 4 + 2]; + b[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + } +} + +int +main (void) +{ +#define RUN(NUM) \ + float a_##NUM[NUM * 4 + 4] = {0}; \ + float a_golden_##NUM[NUM * 4 + 4] = {0}; \ + float b_##NUM[NUM * 4 + 4] = {0}; \ + float b_golden_##NUM[NUM * 4 + 4] = {0}; \ + float c_##NUM[NUM * 4 + 4] = {0}; \ + float d_##NUM[NUM * 4 + 4] = {0}; \ + for (int i = 0; i < NUM * 4 + 4; i++) \ + { \ + c_##NUM[i] = i * 3.789 - 987.135; \ + d_##NUM[i] = i * -13.789 + 1987.135; \ + } \ + f (a_##NUM, b_##NUM, c_##NUM, d_##NUM, NUM); \ + f_golden (a_golden_##NUM, b_golden_##NUM, c_##NUM, d_##NUM, NUM); \ + for (int i = 0; i < NUM * 4 + 4; i++) \ + { \ + if (a_##NUM[i] != a_golden_##NUM[i]) \ + __builtin_abort (); \ + if (b_##NUM[i] != b_golden_##NUM[i]) \ + __builtin_abort (); \ + } + + RUN (3); + RUN (5); + RUN (15); + RUN (16); + RUN (17); + RUN (31); + RUN (32); + RUN (33); + RUN (63); + RUN (64); + RUN (65); + RUN (127); + RUN (128); + RUN (129); + RUN (239); + RUN (359); + RUN (498); + RUN (799); + RUN (977); + RUN (5789); + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-19.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-19.c new file mode 100644 index 00000000000..5cd7156e3d8 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp_run-19.c @@ -0,0 +1,69 @@ +/* { dg-do run { target { riscv_vector } } } */ +/* { dg-additional-options "--param riscv-autovec-preference=scalable" } */ + +#include "slp-19.c" + +void __attribute__ ((optimize (0))) +f_golden (float *restrict a, float *restrict b, float *restrict c, + float *restrict d, int n) +{ + for (int i = 0; i < n; ++i) + { + a[i * 4] = c[i * 4] + d[i * 4]; + a[i * 4 + 1] = c[i * 4] + d[i * 4 + 1]; + a[i * 4 + 2] = c[i * 4 + 2] + d[i * 4 + 2]; + a[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + b[i * 4] = c[i * 4 + 2] + d[i * 4]; + b[i * 4 + 1] = c[i * 4 + 1] + d[i * 4 + 1]; + b[i * 4 + 2] = c[i * 4 + 3] + d[i * 4 + 2]; + b[i * 4 + 3] = c[i * 4 + 3] + d[i * 4 + 3]; + } +} + +int +main (void) +{ +#define RUN(NUM) \ + float a_##NUM[NUM * 4 + 4] = {0}; \ + float a_golden_##NUM[NUM * 4 + 4] = {0}; \ + float b_##NUM[NUM * 4 + 4] = {0}; \ + float b_golden_##NUM[NUM * 4 + 4] = {0}; \ + float c_##NUM[NUM * 4 + 4] = {0}; \ + float d_##NUM[NUM * 4 + 4] = {0}; \ + for (int i = 0; i < NUM * 4 + 4; i++) \ + { \ + c_##NUM[i] = i * 3.789 - 987.135; \ + d_##NUM[i] = i * -13.789 + 1987.135; \ + } \ + f (a_##NUM, b_##NUM, c_##NUM, d_##NUM, NUM); \ + f_golden (a_golden_##NUM, b_golden_##NUM, c_##NUM, d_##NUM, NUM); \ + for (int i = 0; i < NUM * 4 + 4; i++) \ + { \ + if (a_##NUM[i] != a_golden_##NUM[i]) \ + __builtin_abort (); \ + if (b_##NUM[i] != b_golden_##NUM[i]) \ + __builtin_abort (); \ + } + + RUN (3); + RUN (5); + RUN (15); + RUN (16); + RUN (17); + RUN (31); + RUN (32); + RUN (33); + RUN (63); + RUN (64); + RUN (65); + RUN (127); + RUN (128); + RUN (129); + RUN (239); + RUN (359); + RUN (498); + RUN (799); + RUN (977); + RUN (5789); + return 0; +} -- 2.36.1