Committed, thanks Juzhe. Pan From: juzhe.zhong@rivai.ai Sent: Monday, April 22, 2024 2:40 PM To: Li, Pan2 ; gcc-patches Cc: kito.cheng ; Robin Dapp ; Li, Pan2 Subject: Re: [PATCH v1] RISC-V: Add xfail test case for highest-number regno ternary overlap LGTM. ________________________________ juzhe.zhong@rivai.ai From: pan2.li Date: 2024-04-22 14:35 To: gcc-patches CC: juzhe.zhong; kito.cheng; rdapp.gcc; Pan Li Subject: [PATCH v1] RISC-V: Add xfail test case for highest-number regno ternary overlap From: Pan Li > We reverted below patch for register group overlap, add the related insn test and mark it as xfail. And we will remove the xfail after we support the register overlap in GCC-15. 27fde325d64 RISC-V: Support highest-number regno overlap for widen ternary The below test suites are passed. * The rv64gcv fully regression test. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/pr112431-37.c: New test. * gcc.target/riscv/rvv/base/pr112431-38.c: New test. Signed-off-by: Pan Li > --- .../gcc.target/riscv/rvv/base/pr112431-37.c | 103 ++++++++++++++++++ .../gcc.target/riscv/rvv/base/pr112431-38.c | 82 ++++++++++++++ 2 files changed, 185 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-37.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-38.c diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-37.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-37.c new file mode 100644 index 00000000000..66e81ea905a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-37.c @@ -0,0 +1,103 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */ + +#include "riscv_vector.h" + +void +foo (void *in, void *out) +{ + vint16m2_t accum = __riscv_vle16_v_i16m2 (in, 4); + vint16m1_t high_eew16 = __riscv_vget_v_i16m2_i16m1 (accum, 1); + vint8m1_t high_eew8 = __riscv_vreinterpret_v_i16m1_i8m1 (high_eew16); + vint16m2_t result = __riscv_vwmacc_vx_i16m2 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m2 (out, result, 4); +} + +void +foo2 (void *in, void *out) +{ + vint16m4_t accum = __riscv_vle16_v_i16m4 (in, 4); + vint16m2_t high_eew16 = __riscv_vget_v_i16m4_i16m2 (accum, 1); + vint8m2_t high_eew8 = __riscv_vreinterpret_v_i16m2_i8m2 (high_eew16); + vint16m4_t result = __riscv_vwmacc_vx_i16m4 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m4 (out, result, 4); +} + +void +foo3 (void *in, void *out) +{ + vint16m8_t accum = __riscv_vle16_v_i16m8 (in, 4); + vint16m4_t high_eew16 = __riscv_vget_v_i16m8_i16m4 (accum, 1); + vint8m4_t high_eew8 = __riscv_vreinterpret_v_i16m4_i8m4 (high_eew16); + vint16m8_t result = __riscv_vwmacc_vx_i16m8 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m8 (out, result, 4); +} + +void +foo4 (void *in, void *out) +{ + vint16m2_t accum = __riscv_vle16_v_i16m2 (in, 4); + vint16m1_t high_eew16 = __riscv_vget_v_i16m2_i16m1 (accum, 1); + vint8m1_t high_eew8 = __riscv_vreinterpret_v_i16m1_i8m1 (high_eew16); + vint16m2_t result = __riscv_vwmaccus_vx_i16m2 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m2 (out, result, 4); +} + +void +foo5 (void *in, void *out) +{ + vint16m4_t accum = __riscv_vle16_v_i16m4 (in, 4); + vint16m2_t high_eew16 = __riscv_vget_v_i16m4_i16m2 (accum, 1); + vint8m2_t high_eew8 = __riscv_vreinterpret_v_i16m2_i8m2 (high_eew16); + vint16m4_t result = __riscv_vwmaccus_vx_i16m4 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m4 (out, result, 4); +} + +void +foo6 (void *in, void *out) +{ + vint16m8_t accum = __riscv_vle16_v_i16m8 (in, 4); + vint16m4_t high_eew16 = __riscv_vget_v_i16m8_i16m4 (accum, 1); + vint8m4_t high_eew8 = __riscv_vreinterpret_v_i16m4_i8m4 (high_eew16); + vint16m8_t result = __riscv_vwmaccus_vx_i16m8 (accum, 16, high_eew8, 4); + __riscv_vse16_v_i16m8 (out, result, 4); +} + +void +foo7 (void *in, void *out) +{ + vint16m2_t accum = __riscv_vle16_v_i16m2 (in, 4); + vint16m1_t high_eew16 = __riscv_vget_v_i16m2_i16m1 (accum, 1); + vint8m1_t high_eew8 = __riscv_vreinterpret_v_i16m1_i8m1 (high_eew16); + vuint8m1_t high_ueew8 = __riscv_vreinterpret_v_i8m1_u8m1 (high_eew8); + vint16m2_t result = __riscv_vwmaccsu_vx_i16m2 (accum, 16, high_ueew8, 4); + __riscv_vse16_v_i16m2 (out, result, 4); +} + +void +foo8 (void *in, void *out) +{ + vint16m4_t accum = __riscv_vle16_v_i16m4 (in, 4); + vint16m2_t high_eew16 = __riscv_vget_v_i16m4_i16m2 (accum, 1); + vint8m2_t high_eew8 = __riscv_vreinterpret_v_i16m2_i8m2 (high_eew16); + vuint8m2_t high_ueew8 = __riscv_vreinterpret_v_i8m2_u8m2 (high_eew8); + vint16m4_t result = __riscv_vwmaccsu_vx_i16m4 (accum, 16, high_ueew8, 4); + __riscv_vse16_v_i16m4 (out, result, 4); +} + +void +foo9 (void *in, void *out) +{ + vint16m8_t accum = __riscv_vle16_v_i16m8 (in, 4); + vint16m4_t high_eew16 = __riscv_vget_v_i16m8_i16m4 (accum, 1); + vint8m4_t high_eew8 = __riscv_vreinterpret_v_i16m4_i8m4 (high_eew16); + vuint8m4_t high_ueew8 = __riscv_vreinterpret_v_i8m4_u8m4 (high_eew8); + vint16m8_t result = __riscv_vwmaccsu_vx_i16m8 (accum, 16, high_ueew8, 4); + __riscv_vse16_v_i16m8 (out, result, 4); +} + +/* { dg-final { scan-assembler-not {vmv1r} } } */ +/* { dg-final { scan-assembler-not {vmv2r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {vmv4r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {vmv8r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {csrr} } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-38.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-38.c new file mode 100644 index 00000000000..a0cf9afc88e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-38.c @@ -0,0 +1,82 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */ + +#include "riscv_vector.h" + +void +foo (void *in, void *out) +{ + vfloat64m2_t accum = __riscv_vle64_v_f64m2 (in, 4); + vfloat64m1_t high_eew64 = __riscv_vget_v_f64m2_f64m1 (accum, 1); + vint64m1_t high_eew64_i = __riscv_vreinterpret_v_f64m1_i64m1 (high_eew64); + vint32m1_t high_eew32_i = __riscv_vreinterpret_v_i64m1_i32m1 (high_eew64_i); + vfloat32m1_t high_eew32 = __riscv_vreinterpret_v_i32m1_f32m1 (high_eew32_i); + vfloat64m2_t result = __riscv_vfwmacc_vf_f64m2 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m2 (out, result, 4); +} + +void +foo2 (void *in, void *out) +{ + vfloat64m4_t accum = __riscv_vle64_v_f64m4 (in, 4); + vfloat64m2_t high_eew64 = __riscv_vget_v_f64m4_f64m2 (accum, 1); + vint64m2_t high_eew64_i = __riscv_vreinterpret_v_f64m2_i64m2 (high_eew64); + vint32m2_t high_eew32_i = __riscv_vreinterpret_v_i64m2_i32m2 (high_eew64_i); + vfloat32m2_t high_eew32 = __riscv_vreinterpret_v_i32m2_f32m2 (high_eew32_i); + vfloat64m4_t result = __riscv_vfwmacc_vf_f64m4 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m4 (out, result, 4); +} + +void +foo3 (void *in, void *out) +{ + vfloat64m8_t accum = __riscv_vle64_v_f64m8 (in, 4); + vfloat64m4_t high_eew64 = __riscv_vget_v_f64m8_f64m4 (accum, 1); + vint64m4_t high_eew64_i = __riscv_vreinterpret_v_f64m4_i64m4 (high_eew64); + vint32m4_t high_eew32_i = __riscv_vreinterpret_v_i64m4_i32m4 (high_eew64_i); + vfloat32m4_t high_eew32 = __riscv_vreinterpret_v_i32m4_f32m4 (high_eew32_i); + vfloat64m8_t result = __riscv_vfwmacc_vf_f64m8 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m8 (out, result, 4); +} + +void +foo4 (void *in, void *out) +{ + vfloat64m2_t accum = __riscv_vle64_v_f64m2 (in, 4); + vfloat64m1_t high_eew64 = __riscv_vget_v_f64m2_f64m1 (accum, 1); + vint64m1_t high_eew64_i = __riscv_vreinterpret_v_f64m1_i64m1 (high_eew64); + vint32m1_t high_eew32_i = __riscv_vreinterpret_v_i64m1_i32m1 (high_eew64_i); + vfloat32m1_t high_eew32 = __riscv_vreinterpret_v_i32m1_f32m1 (high_eew32_i); + vfloat64m2_t result = __riscv_vfwnmsac_vf_f64m2 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m2 (out, result, 4); +} + +void +foo5 (void *in, void *out) +{ + vfloat64m4_t accum = __riscv_vle64_v_f64m4 (in, 4); + vfloat64m2_t high_eew64 = __riscv_vget_v_f64m4_f64m2 (accum, 1); + vint64m2_t high_eew64_i = __riscv_vreinterpret_v_f64m2_i64m2 (high_eew64); + vint32m2_t high_eew32_i = __riscv_vreinterpret_v_i64m2_i32m2 (high_eew64_i); + vfloat32m2_t high_eew32 = __riscv_vreinterpret_v_i32m2_f32m2 (high_eew32_i); + vfloat64m4_t result = __riscv_vfwnmsac_vf_f64m4 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m4 (out, result, 4); +} + +void +foo6 (void *in, void *out) +{ + vfloat64m8_t accum = __riscv_vle64_v_f64m8 (in, 4); + vfloat64m4_t high_eew64 = __riscv_vget_v_f64m8_f64m4 (accum, 1); + vint64m4_t high_eew64_i = __riscv_vreinterpret_v_f64m4_i64m4 (high_eew64); + vint32m4_t high_eew32_i = __riscv_vreinterpret_v_i64m4_i32m4 (high_eew64_i); + vfloat32m4_t high_eew32 = __riscv_vreinterpret_v_i32m4_f32m4 (high_eew32_i); + vfloat64m8_t result = __riscv_vfwnmsac_vf_f64m8 (accum, 64, high_eew32, 4); + __riscv_vse64_v_f64m8 (out, result, 4); +} + +/* { dg-final { scan-assembler-not {vmv1r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {vmv2r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {vmv4r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {vmv8r} { xfail riscv*-*-* } } } */ +/* { dg-final { scan-assembler-not {csrr} } } */ -- 2.34.1