[llvm] [AArch64][SME] Fix restoring callee-saves from FP with hazard padding (PR #143371)
Benjamin Maxwell via llvm-commits
llvm-commits at lists.llvm.org
Tue Jun 10 04:25:02 PDT 2025
================
@@ -3143,3 +3143,428 @@ entry:
call void @bar(ptr noundef nonnull %b)
ret i32 0
}
+
+
+define i32 @svecc_call_dynamic_alloca(<4 x i16> %P0, i32 %P1, i32 %P2, <vscale x 16 x i8> %P3, i16 %P4) "aarch64_pstate_sm_compatible" {
+; CHECK0-LABEL: svecc_call_dynamic_alloca:
+; CHECK0: // %bb.0: // %entry
+; CHECK0-NEXT: stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK0-NEXT: .cfi_def_cfa_offset 64
+; CHECK0-NEXT: cntd x9
+; CHECK0-NEXT: stp x27, x26, [sp, #32] // 16-byte Folded Spill
+; CHECK0-NEXT: stp x9, x28, [sp, #16] // 16-byte Folded Spill
+; CHECK0-NEXT: stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK0-NEXT: mov x29, sp
+; CHECK0-NEXT: .cfi_def_cfa w29, 64
+; CHECK0-NEXT: .cfi_offset w19, -8
+; CHECK0-NEXT: .cfi_offset w20, -16
+; CHECK0-NEXT: .cfi_offset w26, -24
+; CHECK0-NEXT: .cfi_offset w27, -32
+; CHECK0-NEXT: .cfi_offset w28, -40
+; CHECK0-NEXT: .cfi_offset w30, -56
+; CHECK0-NEXT: .cfi_offset w29, -64
+; CHECK0-NEXT: addvl sp, sp, #-18
+; CHECK0-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 64 - 8 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 64 - 16 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 64 - 24 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 64 - 32 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 64 - 40 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 64 - 48 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 64 - 56 * VG
+; CHECK0-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 64 - 64 * VG
+; CHECK0-NEXT: mov w9, w0
+; CHECK0-NEXT: mov x8, sp
+; CHECK0-NEXT: mov w2, w1
+; CHECK0-NEXT: add x9, x9, #15
+; CHECK0-NEXT: mov x19, sp
+; CHECK0-NEXT: and x9, x9, #0x1fffffff0
+; CHECK0-NEXT: sub x8, x8, x9
+; CHECK0-NEXT: mov sp, x8
+; CHECK0-NEXT: //APP
+; CHECK0-NEXT: //NO_APP
+; CHECK0-NEXT: bl __arm_sme_state
+; CHECK0-NEXT: and x20, x0, #0x1
+; CHECK0-NEXT: .cfi_offset vg, -48
+; CHECK0-NEXT: tbz w20, #0, .LBB35_2
+; CHECK0-NEXT: // %bb.1: // %entry
+; CHECK0-NEXT: smstop sm
+; CHECK0-NEXT: .LBB35_2: // %entry
+; CHECK0-NEXT: mov x0, x8
+; CHECK0-NEXT: mov w1, #45 // =0x2d
+; CHECK0-NEXT: bl memset
+; CHECK0-NEXT: tbz w20, #0, .LBB35_4
+; CHECK0-NEXT: // %bb.3: // %entry
+; CHECK0-NEXT: smstart sm
+; CHECK0-NEXT: .LBB35_4: // %entry
+; CHECK0-NEXT: mov w0, #22647 // =0x5877
+; CHECK0-NEXT: movk w0, #59491, lsl #16
+; CHECK0-NEXT: .cfi_restore vg
+; CHECK0-NEXT: addvl sp, x29, #-18
+; CHECK0-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK0-NEXT: .cfi_restore z8
+; CHECK0-NEXT: .cfi_restore z9
+; CHECK0-NEXT: .cfi_restore z10
+; CHECK0-NEXT: .cfi_restore z11
+; CHECK0-NEXT: .cfi_restore z12
+; CHECK0-NEXT: .cfi_restore z13
+; CHECK0-NEXT: .cfi_restore z14
+; CHECK0-NEXT: .cfi_restore z15
+; CHECK0-NEXT: mov sp, x29
+; CHECK0-NEXT: .cfi_def_cfa wsp, 64
+; CHECK0-NEXT: ldp x20, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK0-NEXT: ldr x28, [sp, #24] // 8-byte Folded Reload
+; CHECK0-NEXT: ldp x27, x26, [sp, #32] // 16-byte Folded Reload
+; CHECK0-NEXT: ldp x29, x30, [sp], #64 // 16-byte Folded Reload
+; CHECK0-NEXT: .cfi_def_cfa_offset 0
+; CHECK0-NEXT: .cfi_restore w19
+; CHECK0-NEXT: .cfi_restore w20
+; CHECK0-NEXT: .cfi_restore w26
+; CHECK0-NEXT: .cfi_restore w27
+; CHECK0-NEXT: .cfi_restore w28
+; CHECK0-NEXT: .cfi_restore w30
+; CHECK0-NEXT: .cfi_restore w29
+; CHECK0-NEXT: ret
+;
+; CHECK64-LABEL: svecc_call_dynamic_alloca:
+; CHECK64: // %bb.0: // %entry
+; CHECK64-NEXT: sub sp, sp, #128
+; CHECK64-NEXT: .cfi_def_cfa_offset 128
+; CHECK64-NEXT: cntd x9
+; CHECK64-NEXT: stp x29, x30, [sp, #64] // 16-byte Folded Spill
+; CHECK64-NEXT: stp x9, x28, [sp, #80] // 16-byte Folded Spill
+; CHECK64-NEXT: stp x27, x26, [sp, #96] // 16-byte Folded Spill
+; CHECK64-NEXT: stp x20, x19, [sp, #112] // 16-byte Folded Spill
+; CHECK64-NEXT: add x29, sp, #64
+; CHECK64-NEXT: .cfi_def_cfa w29, 64
+; CHECK64-NEXT: .cfi_offset w19, -8
+; CHECK64-NEXT: .cfi_offset w20, -16
+; CHECK64-NEXT: .cfi_offset w26, -24
+; CHECK64-NEXT: .cfi_offset w27, -32
+; CHECK64-NEXT: .cfi_offset w28, -40
+; CHECK64-NEXT: .cfi_offset w30, -56
+; CHECK64-NEXT: .cfi_offset w29, -64
+; CHECK64-NEXT: addvl sp, sp, #-18
+; CHECK64-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK64-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: .cfi_escape 0x10, 0x48, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 128 - 8 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x49, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 128 - 16 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4a, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 128 - 24 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4b, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 128 - 32 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4c, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 128 - 40 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4d, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 128 - 48 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4e, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 128 - 56 * VG
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4f, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 128 - 64 * VG
+; CHECK64-NEXT: sub sp, sp, #64
+; CHECK64-NEXT: mov w9, w0
+; CHECK64-NEXT: mov x8, sp
+; CHECK64-NEXT: mov w2, w1
+; CHECK64-NEXT: add x9, x9, #15
+; CHECK64-NEXT: mov x19, sp
+; CHECK64-NEXT: and x9, x9, #0x1fffffff0
+; CHECK64-NEXT: sub x8, x8, x9
+; CHECK64-NEXT: mov sp, x8
+; CHECK64-NEXT: //APP
+; CHECK64-NEXT: //NO_APP
+; CHECK64-NEXT: bl __arm_sme_state
+; CHECK64-NEXT: and x20, x0, #0x1
+; CHECK64-NEXT: .cfi_offset vg, -48
+; CHECK64-NEXT: tbz w20, #0, .LBB35_2
+; CHECK64-NEXT: // %bb.1: // %entry
+; CHECK64-NEXT: smstop sm
+; CHECK64-NEXT: .LBB35_2: // %entry
+; CHECK64-NEXT: mov x0, x8
+; CHECK64-NEXT: mov w1, #45 // =0x2d
+; CHECK64-NEXT: bl memset
+; CHECK64-NEXT: tbz w20, #0, .LBB35_4
+; CHECK64-NEXT: // %bb.3: // %entry
+; CHECK64-NEXT: smstart sm
+; CHECK64-NEXT: .LBB35_4: // %entry
+; CHECK64-NEXT: mov w0, #22647 // =0x5877
+; CHECK64-NEXT: movk w0, #59491, lsl #16
+; CHECK64-NEXT: .cfi_restore vg
+; CHECK64-NEXT: sub sp, x29, #64
+; CHECK64-NEXT: addvl sp, sp, #-18
----------------
MacDue wrote:
I see, I've reworked this so the base pointer will always be available in this case. Which means if there's no realignment we can use the base pointer to get to the start of the SVE callee saves, and if there is we can use the base pointer as a temporary (as at this point it should not be used anyway, since it's pointing to free'd stack).
https://github.com/llvm/llvm-project/pull/143371
More information about the llvm-commits
mailing list