| commit | c4ac073d4fc7474e29d085bbd10971138ee7478e | |
| author | Juzhe-Zhong <juzhe.zhong@rivai.ai> | |
| Wed, 27 Dec 2023 08:16:41 +0000 (27 16:16 +0800) | ||
| committer | Pan Li <pan2.li@intel.com> | |
| Wed, 27 Dec 2023 09:19:35 +0000 (27 17:19 +0800) | ||
| tree | 36a87b171618fa99c6555098cbec67218a5c8300 | treesnapshot (tar.gz zip) |
| parent | feaff27b290f4635df3c374fd4106259c6c654df | commitdiff |
RISC-V: Make known NITERS loop be aware of dynamic lmul cost model liveness information
Consider this following case:
int f[12][100];
void bad1(int v1, int v2)
{
for (int r = 0; r < 100; r += 4)
{
int i = r + 1;
f[0][r] = f[1][r] * (f[2][r]) - f[1][i] * (f[2][i]);
f[0][i] = f[1][r] * (f[2][i]) + f[1][i] * (f[2][r]);
f[0][r+2] = f[1][r+2] * (f[2][r+2]) - f[1][i+2] * (f[2][i+2]);
f[0][i+2] = f[1][r+2] * (f[2][i+2]) + f[1][i+2] * (f[2][r+2]);
}
}
Pick up LMUL = 8 VLS blindly:
lui a4,%hi(f)
addi a4,a4,%lo(f)
addi sp,sp,-592
addi a3,a4,800
lui a5,%hi(.LANCHOR0)
vl8re32.v v24,0(a3)
addi a5,a5,%lo(.LANCHOR0)
addi a1,a4,400
addi a3,sp,140
vl8re32.v v16,0(a1)
vl4re16.v v4,0(a5)
addi a7,a5,192
vs4r.v v4,0(a3)
addi t0,a5,64
addi a3,sp,336
li t2,32
addi a2,a5,128
vsetvli a5,zero,e32,m8,ta,ma
vrgatherei16.vv v8,v16,v4
vmul.vv v8,v8,v24
vl8re32.v v0,0(a7)
vs8r.v v8,0(a3)
vmsltu.vx v8,v0,t2
addi a3,sp,12
addi t2,sp,204
vsm.v v8,0(t2)
vl4re16.v v4,0(t0)
vl4re16.v v0,0(a2)
vs4r.v v4,0(a3)
addi t0,sp,336
vrgatherei16.vv v8,v24,v4
addi a3,sp,208
vrgatherei16.vv v24,v16,v0
vs4r.v v0,0(a3)
vmul.vv v8,v8,v24
vlm.v v0,0(t2)
vl8re32.v v24,0(t0)
addi a3,sp,208
vsub.vv v16,v24,v8
addi t6,a4,528
vadd.vv v8,v24,v8
addi t5,a4,928
vmerge.vvm v8,v8,v16,v0
addi t3,a4,128
vs8r.v v8,0(a4)
addi t4,a4,1056
addi t1,a4,656
addi a0,a4,256
addi a6,a4,1184
addi a1,a4,784
addi a7,a4,384
addi a4,sp,140
vl4re16.v v0,0(a3)
vl8re32.v v24,0(t6)
vl4re16.v v4,0(a4)
vrgatherei16.vv v16,v24,v0
addi a3,sp,12
vs8r.v v16,0(t0)
vl8re32.v v8,0(t5)
vrgatherei16.vv v16,v24,v4
vl4re16.v v4,0(a3)
vrgatherei16.vv v24,v8,v4
vmul.vv v16,v16,v8
vl8re32.v v8,0(t0)
vmul.vv v8,v8,v24
vsub.vv v24,v16,v8
vlm.v v0,0(t2)
addi a3,sp,208
vadd.vv v8,v8,v16
vl8re32.v v16,0(t4)
vmerge.vvm v8,v8,v24,v0
vrgatherei16.vv v24,v16,v4
vs8r.v v24,0(t0)
vl4re16.v v28,0(a3)
addi a3,sp,464
vs8r.v v8,0(t3)
vl8re32.v v8,0(t1)
vrgatherei16.vv v0,v8,v28
vs8r.v v0,0(a3)
addi a3,sp,140
vl4re16.v v24,0(a3)
addi a3,sp,464
vrgatherei16.vv v0,v8,v24
vl8re32.v v24,0(t0)
vmv8r.v v8,v0
vl8re32.v v0,0(a3)
vmul.vv v8,v8,v16
vmul.vv v24,v24,v0
vsub.vv v16,v8,v24
vadd.vv v8,v8,v24
vsetivli zero,4,e32,m8,ta,ma
vle32.v v24,0(a6)
vsetvli a4,zero,e32,m8,ta,ma
addi a4,sp,12
vlm.v v0,0(t2)
vmerge.vvm v8,v8,v16,v0
vl4re16.v v16,0(a4)
vrgatherei16.vv v0,v24,v16
vsetivli zero,4,e32,m8,ta,ma
vs8r.v v0,0(a4)
addi a4,sp,208
vl4re16.v v0,0(a4)
vs8r.v v8,0(a0)
vle32.v v16,0(a1)
vsetvli a5,zero,e32,m8,ta,ma
vrgatherei16.vv v8,v16,v0
vs8r.v v8,0(a4)
addi a4,sp,140
vl4re16.v v4,0(a4)
addi a5,sp,12
vrgatherei16.vv v8,v16,v4
vl8re32.v v0,0(a5)
vsetivli zero,4,e32,m8,ta,ma
addi a5,sp,208
vmv8r.v v16,v8
vl8re32.v v8,0(a5)
vmul.vv v24,v24,v16
vmul.vv v8,v0,v8
vsub.vv v16,v24,v8
vadd.vv v8,v8,v24
vsetvli a5,zero,e8,m2,ta,ma
vlm.v v0,0(t2)
vsetivli zero,4,e32,m8,ta,ma
vmerge.vvm v8,v8,v16,v0
vse32.v v8,0(a7)
addi sp,sp,592
jr ra
This patch makes loop with known NITERS be aware of liveness estimation, after this patch, choosing LMUL = 4:
lui a5,%hi(f)
addi a5,a5,%lo(f)
addi a3,a5,400
addi a4,a5,800
vsetivli zero,8,e32,m2,ta,ma
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v8,v16
addi a3,a5,528
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a4,a5,928
vmul.vv v2,v12,v22
vmul.vv v6,v8,v18
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmul.vv v4,v12,v20
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
vsseg4e32.v v24,(a5)
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v8,v16
addi a6,a5,128
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a0,a5,656
vmul.vv v2,v12,v22
addi a1,a5,1056
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmul.vv v6,v8,v18
vmul.vv v4,v12,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
vsseg4e32.v v24,(a6)
vlseg4e32.v v16,(a0)
vlseg4e32.v v8,(a1)
vmul.vv v2,v8,v16
addi a2,a5,256
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a3,a5,784
vmul.vv v2,v12,v22
addi a4,a5,1184
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmul.vv v6,v8,v18
vmul.vv v4,v12,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
addi a5,a5,384
vsseg4e32.v v24,(a2)
vsetivli zero,1,e32,m2,ta,ma
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v16,v8
vmul.vv v6,v18,v8
vmv.v.v v24,v18
vnmsub.vv v24,v10,v2
vmul.vv v4,v20,v12
vmul.vv v2,v22,v12
vmv.v.v v26,v6
vmacc.vv v26,v16,v10
vmv.v.v v28,v22
vnmsub.vv v28,v14,v4
vmv.v.v v30,v2
vmacc.vv v30,v20,v14
vsseg4e32.v v24,(a5)
ret
Tested on both RV32 and RV64 no regressions.
PR target/113112
gcc/ChangeLog:
* config/riscv/riscv-vector-costs.cc (is_gimple_assign_or_call): New function.
(get_first_lane_point): Ditto.
(get_last_lane_point): Ditto.
(max_number_of_live_regs): Refine live point dump.
(compute_estimated_lmul): Make unknown NITERS loop be aware of liveness.
(costs::better_main_loop_than_p): Ditto.
* config/riscv/riscv-vector-costs.h (struct stmt_point): Add new member.
gcc/testsuite/ChangeLog:
* gcc.dg/vect/costmodel/riscv/rvv/pr113112-1.c:
* gcc.dg/vect/costmodel/riscv/rvv/pr113112-3.c: New test.
Consider this following case:
int f[12][100];
void bad1(int v1, int v2)
{
for (int r = 0; r < 100; r += 4)
{
int i = r + 1;
f[0][r] = f[1][r] * (f[2][r]) - f[1][i] * (f[2][i]);
f[0][i] = f[1][r] * (f[2][i]) + f[1][i] * (f[2][r]);
f[0][r+2] = f[1][r+2] * (f[2][r+2]) - f[1][i+2] * (f[2][i+2]);
f[0][i+2] = f[1][r+2] * (f[2][i+2]) + f[1][i+2] * (f[2][r+2]);
}
}
Pick up LMUL = 8 VLS blindly:
lui a4,%hi(f)
addi a4,a4,%lo(f)
addi sp,sp,-592
addi a3,a4,800
lui a5,%hi(.LANCHOR0)
vl8re32.v v24,0(a3)
addi a5,a5,%lo(.LANCHOR0)
addi a1,a4,400
addi a3,sp,140
vl8re32.v v16,0(a1)
vl4re16.v v4,0(a5)
addi a7,a5,192
vs4r.v v4,0(a3)
addi t0,a5,64
addi a3,sp,336
li t2,32
addi a2,a5,128
vsetvli a5,zero,e32,m8,ta,ma
vrgatherei16.vv v8,v16,v4
vmul.vv v8,v8,v24
vl8re32.v v0,0(a7)
vs8r.v v8,0(a3)
vmsltu.vx v8,v0,t2
addi a3,sp,12
addi t2,sp,204
vsm.v v8,0(t2)
vl4re16.v v4,0(t0)
vl4re16.v v0,0(a2)
vs4r.v v4,0(a3)
addi t0,sp,336
vrgatherei16.vv v8,v24,v4
addi a3,sp,208
vrgatherei16.vv v24,v16,v0
vs4r.v v0,0(a3)
vmul.vv v8,v8,v24
vlm.v v0,0(t2)
vl8re32.v v24,0(t0)
addi a3,sp,208
vsub.vv v16,v24,v8
addi t6,a4,528
vadd.vv v8,v24,v8
addi t5,a4,928
vmerge.vvm v8,v8,v16,v0
addi t3,a4,128
vs8r.v v8,0(a4)
addi t4,a4,1056
addi t1,a4,656
addi a0,a4,256
addi a6,a4,1184
addi a1,a4,784
addi a7,a4,384
addi a4,sp,140
vl4re16.v v0,0(a3)
vl8re32.v v24,0(t6)
vl4re16.v v4,0(a4)
vrgatherei16.vv v16,v24,v0
addi a3,sp,12
vs8r.v v16,0(t0)
vl8re32.v v8,0(t5)
vrgatherei16.vv v16,v24,v4
vl4re16.v v4,0(a3)
vrgatherei16.vv v24,v8,v4
vmul.vv v16,v16,v8
vl8re32.v v8,0(t0)
vmul.vv v8,v8,v24
vsub.vv v24,v16,v8
vlm.v v0,0(t2)
addi a3,sp,208
vadd.vv v8,v8,v16
vl8re32.v v16,0(t4)
vmerge.vvm v8,v8,v24,v0
vrgatherei16.vv v24,v16,v4
vs8r.v v24,0(t0)
vl4re16.v v28,0(a3)
addi a3,sp,464
vs8r.v v8,0(t3)
vl8re32.v v8,0(t1)
vrgatherei16.vv v0,v8,v28
vs8r.v v0,0(a3)
addi a3,sp,140
vl4re16.v v24,0(a3)
addi a3,sp,464
vrgatherei16.vv v0,v8,v24
vl8re32.v v24,0(t0)
vmv8r.v v8,v0
vl8re32.v v0,0(a3)
vmul.vv v8,v8,v16
vmul.vv v24,v24,v0
vsub.vv v16,v8,v24
vadd.vv v8,v8,v24
vsetivli zero,4,e32,m8,ta,ma
vle32.v v24,0(a6)
vsetvli a4,zero,e32,m8,ta,ma
addi a4,sp,12
vlm.v v0,0(t2)
vmerge.vvm v8,v8,v16,v0
vl4re16.v v16,0(a4)
vrgatherei16.vv v0,v24,v16
vsetivli zero,4,e32,m8,ta,ma
vs8r.v v0,0(a4)
addi a4,sp,208
vl4re16.v v0,0(a4)
vs8r.v v8,0(a0)
vle32.v v16,0(a1)
vsetvli a5,zero,e32,m8,ta,ma
vrgatherei16.vv v8,v16,v0
vs8r.v v8,0(a4)
addi a4,sp,140
vl4re16.v v4,0(a4)
addi a5,sp,12
vrgatherei16.vv v8,v16,v4
vl8re32.v v0,0(a5)
vsetivli zero,4,e32,m8,ta,ma
addi a5,sp,208
vmv8r.v v16,v8
vl8re32.v v8,0(a5)
vmul.vv v24,v24,v16
vmul.vv v8,v0,v8
vsub.vv v16,v24,v8
vadd.vv v8,v8,v24
vsetvli a5,zero,e8,m2,ta,ma
vlm.v v0,0(t2)
vsetivli zero,4,e32,m8,ta,ma
vmerge.vvm v8,v8,v16,v0
vse32.v v8,0(a7)
addi sp,sp,592
jr ra
This patch makes loop with known NITERS be aware of liveness estimation, after this patch, choosing LMUL = 4:
lui a5,%hi(f)
addi a5,a5,%lo(f)
addi a3,a5,400
addi a4,a5,800
vsetivli zero,8,e32,m2,ta,ma
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v8,v16
addi a3,a5,528
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a4,a5,928
vmul.vv v2,v12,v22
vmul.vv v6,v8,v18
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmul.vv v4,v12,v20
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
vsseg4e32.v v24,(a5)
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v8,v16
addi a6,a5,128
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a0,a5,656
vmul.vv v2,v12,v22
addi a1,a5,1056
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmul.vv v6,v8,v18
vmul.vv v4,v12,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
vsseg4e32.v v24,(a6)
vlseg4e32.v v16,(a0)
vlseg4e32.v v8,(a1)
vmul.vv v2,v8,v16
addi a2,a5,256
vmv.v.v v24,v10
vnmsub.vv v24,v18,v2
addi a3,a5,784
vmul.vv v2,v12,v22
addi a4,a5,1184
vmv.v.v v30,v2
vmacc.vv v30,v14,v20
vmul.vv v6,v8,v18
vmul.vv v4,v12,v20
vmv.v.v v26,v6
vmacc.vv v26,v10,v16
vmv.v.v v28,v14
vnmsub.vv v28,v22,v4
addi a5,a5,384
vsseg4e32.v v24,(a2)
vsetivli zero,1,e32,m2,ta,ma
vlseg4e32.v v16,(a3)
vlseg4e32.v v8,(a4)
vmul.vv v2,v16,v8
vmul.vv v6,v18,v8
vmv.v.v v24,v18
vnmsub.vv v24,v10,v2
vmul.vv v4,v20,v12
vmul.vv v2,v22,v12
vmv.v.v v26,v6
vmacc.vv v26,v16,v10
vmv.v.v v28,v22
vnmsub.vv v28,v14,v4
vmv.v.v v30,v2
vmacc.vv v30,v20,v14
vsseg4e32.v v24,(a5)
ret
Tested on both RV32 and RV64 no regressions.
PR target/113112
gcc/ChangeLog:
* config/riscv/riscv-vector-costs.cc (is_gimple_assign_or_call): New function.
(get_first_lane_point): Ditto.
(get_last_lane_point): Ditto.
(max_number_of_live_regs): Refine live point dump.
(compute_estimated_lmul): Make unknown NITERS loop be aware of liveness.
(costs::better_main_loop_than_p): Ditto.
* config/riscv/riscv-vector-costs.h (struct stmt_point): Add new member.
gcc/testsuite/ChangeLog:
* gcc.dg/vect/costmodel/riscv/rvv/pr113112-1.c:
* gcc.dg/vect/costmodel/riscv/rvv/pr113112-3.c: New test.