[RISCV] Another length changing shuffle lowering case
"32" is currently a special number - it's one past the maximum representable immediate on a vslidedown.vi and thus the first sub-vector we do *not* consider "cheap" in RISCVTargetLowering::isExtractSubvectorCheap.
This commit is contained in:
Philip Reames
committed by
Philip Reames
Philip Reames
parent
e9de53875b
commit
22db91c5e8
@@ -308,3 +308,244 @@ define <32 x i32> @v32i32_v4i32(<4 x i32>) {
|
||||
%2 = shufflevector <4 x i32> %0, <4 x i32> poison, <32 x i32> <i32 2, i32 3, i32 0, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 0, i32 1, i32 1, i32 2, i32 0, i32 3, i32 1, i32 1, i32 2, i32 0, i32 3, i32 1, i32 2, i32 0, i32 3, i32 1, i32 1, i32 2, i32 0, i32 3>
|
||||
ret <32 x i32> %2
|
||||
}
|
||||
|
||||
; TODO: This case should be a simple vnsrl, but gets scalarized instead
|
||||
define <32 x i8> @vnsrl_v32i8_v64i8(<64 x i8> %in) {
|
||||
; RV32-LABEL: v32i8_v64i8:
|
||||
; RV32: # %bb.0:
|
||||
; RV32-NEXT: addi sp, sp, -128
|
||||
; RV32-NEXT: .cfi_def_cfa_offset 128
|
||||
; RV32-NEXT: sw ra, 124(sp) # 4-byte Folded Spill
|
||||
; RV32-NEXT: sw s0, 120(sp) # 4-byte Folded Spill
|
||||
; RV32-NEXT: .cfi_offset ra, -4
|
||||
; RV32-NEXT: .cfi_offset s0, -8
|
||||
; RV32-NEXT: addi s0, sp, 128
|
||||
; RV32-NEXT: .cfi_def_cfa s0, 0
|
||||
; RV32-NEXT: andi sp, sp, -64
|
||||
; RV32-NEXT: li a0, 64
|
||||
; RV32-NEXT: mv a1, sp
|
||||
; RV32-NEXT: vsetvli zero, a0, e8, m4, ta, ma
|
||||
; RV32-NEXT: vse8.v v8, (a1)
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v10, v8, 1
|
||||
; RV32-NEXT: vmv.x.s a0, v10
|
||||
; RV32-NEXT: li a1, 32
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vmv.v.x v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 3
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 5
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 7
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 9
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 11
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 13
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 15
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 17
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 19
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 21
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 23
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 25
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 27
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v12, v8, 29
|
||||
; RV32-NEXT: vmv.x.s a0, v12
|
||||
; RV32-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV32-NEXT: vslidedown.vi v8, v8, 31
|
||||
; RV32-NEXT: vmv.x.s a0, v8
|
||||
; RV32-NEXT: vslide1down.vx v8, v10, a0
|
||||
; RV32-NEXT: lbu a0, 33(sp)
|
||||
; RV32-NEXT: lbu a1, 35(sp)
|
||||
; RV32-NEXT: lbu a2, 37(sp)
|
||||
; RV32-NEXT: lbu a3, 39(sp)
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV32-NEXT: lbu a0, 41(sp)
|
||||
; RV32-NEXT: lbu a1, 43(sp)
|
||||
; RV32-NEXT: lbu a2, 45(sp)
|
||||
; RV32-NEXT: lbu a3, 47(sp)
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV32-NEXT: lbu a0, 49(sp)
|
||||
; RV32-NEXT: lbu a1, 51(sp)
|
||||
; RV32-NEXT: lbu a2, 53(sp)
|
||||
; RV32-NEXT: lbu a3, 55(sp)
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV32-NEXT: lbu a0, 57(sp)
|
||||
; RV32-NEXT: lbu a1, 59(sp)
|
||||
; RV32-NEXT: lbu a2, 61(sp)
|
||||
; RV32-NEXT: lbu a3, 63(sp)
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV32-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV32-NEXT: addi sp, s0, -128
|
||||
; RV32-NEXT: lw ra, 124(sp) # 4-byte Folded Reload
|
||||
; RV32-NEXT: lw s0, 120(sp) # 4-byte Folded Reload
|
||||
; RV32-NEXT: addi sp, sp, 128
|
||||
; RV32-NEXT: ret
|
||||
;
|
||||
; RV64-LABEL: v32i8_v64i8:
|
||||
; RV64: # %bb.0:
|
||||
; RV64-NEXT: addi sp, sp, -128
|
||||
; RV64-NEXT: .cfi_def_cfa_offset 128
|
||||
; RV64-NEXT: sd ra, 120(sp) # 8-byte Folded Spill
|
||||
; RV64-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
|
||||
; RV64-NEXT: .cfi_offset ra, -8
|
||||
; RV64-NEXT: .cfi_offset s0, -16
|
||||
; RV64-NEXT: addi s0, sp, 128
|
||||
; RV64-NEXT: .cfi_def_cfa s0, 0
|
||||
; RV64-NEXT: andi sp, sp, -64
|
||||
; RV64-NEXT: li a0, 64
|
||||
; RV64-NEXT: mv a1, sp
|
||||
; RV64-NEXT: vsetvli zero, a0, e8, m4, ta, ma
|
||||
; RV64-NEXT: vse8.v v8, (a1)
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v10, v8, 1
|
||||
; RV64-NEXT: vmv.x.s a0, v10
|
||||
; RV64-NEXT: li a1, 32
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vmv.v.x v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 3
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 5
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 7
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 9
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 11
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 13
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 15
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 17
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 19
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 21
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 23
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 25
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 27
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v12, v8, 29
|
||||
; RV64-NEXT: vmv.x.s a0, v12
|
||||
; RV64-NEXT: vslide1down.vx v10, v10, a0
|
||||
; RV64-NEXT: vslidedown.vi v8, v8, 31
|
||||
; RV64-NEXT: vmv.x.s a0, v8
|
||||
; RV64-NEXT: vslide1down.vx v8, v10, a0
|
||||
; RV64-NEXT: lbu a0, 33(sp)
|
||||
; RV64-NEXT: lbu a1, 35(sp)
|
||||
; RV64-NEXT: lbu a2, 37(sp)
|
||||
; RV64-NEXT: lbu a3, 39(sp)
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV64-NEXT: lbu a0, 41(sp)
|
||||
; RV64-NEXT: lbu a1, 43(sp)
|
||||
; RV64-NEXT: lbu a2, 45(sp)
|
||||
; RV64-NEXT: lbu a3, 47(sp)
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV64-NEXT: lbu a0, 49(sp)
|
||||
; RV64-NEXT: lbu a1, 51(sp)
|
||||
; RV64-NEXT: lbu a2, 53(sp)
|
||||
; RV64-NEXT: lbu a3, 55(sp)
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV64-NEXT: lbu a0, 57(sp)
|
||||
; RV64-NEXT: lbu a1, 59(sp)
|
||||
; RV64-NEXT: lbu a2, 61(sp)
|
||||
; RV64-NEXT: lbu a3, 63(sp)
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a0
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a1
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a2
|
||||
; RV64-NEXT: vslide1down.vx v8, v8, a3
|
||||
; RV64-NEXT: addi sp, s0, -128
|
||||
; RV64-NEXT: ld ra, 120(sp) # 8-byte Folded Reload
|
||||
; RV64-NEXT: ld s0, 112(sp) # 8-byte Folded Reload
|
||||
; RV64-NEXT: addi sp, sp, 128
|
||||
; RV64-NEXT: ret
|
||||
%res = shufflevector <64 x i8> %in, <64 x i8> poison, <32 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31, i32 33, i32 35, i32 37, i32 39, i32 41, i32 43, i32 45, i32 47, i32 49, i32 51, i32 53, i32 55, i32 57, i32 59, i32 61, i32 63>
|
||||
ret <32 x i8> %res
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user