fmt.Fprintf(w, "    AKA ======================== %s\n", name)
		}
		fmt.Fprintf(w, "%10s %10s (flat, cum) %s of Total\n",
			rpt.formatValue(flatSum), rpt.formatValue(cumSum),
			measurement.Percentage(cumSum, rpt.total))

		function, file, line := "", "", 0
		for _, n := range ns {
			locStr := ""
			// Skip loc information if it hasn't changed from previous instruction.

TEXT runtime·switchToCrashStack0(SB), NOSPLIT, $0-8
	MOVV	fn+0(FP), REGCTXT	// context register
	MOVV	g_m(g), R2	// curm

	// set g to gcrash
	MOVV	$runtime·gcrash(SB), g	// g = &gcrash
	CALL	runtime·save_g(SB)
	MOVV	R2, g_m(g)	// g.m = curm
	MOVV	g, m_g0(R2)	// curm.g0 = g

	// switch to crashstack
	MOVV	(g_stack+stack_hi)(g), R2
	ADDV	$(-4*8), R2, R29

	// call target function

TEXT runtime·switchToCrashStack0(SB), NOSPLIT, $0-8
	MOVV	fn+0(FP), REGCTXT	// context register
	MOVV	g_m(g), R4	// curm

	// set g to gcrash
	MOVV	$runtime·gcrash(SB), g	// g = &gcrash
	JAL	runtime·save_g(SB)
	MOVV	R4, g_m(g)	// g.m = curm
	MOVV	g, m_g0(R4)	// curm.g0 = g

	// switch to crashstack
	MOVV	(g_stack+stack_hi)(g), R4
	ADDV	$(-4*8), R4, R3

	// call target function

TEXT runtime·switchToCrashStack0(SB), NOSPLIT, $0-4
	MOVW	fn+0(FP), REGCTXT	// context register
	MOVW	g_m(g), R2	// curm

	// set g to gcrash
	MOVW	$runtime·gcrash(SB), g	// g = &gcrash
	CALL	runtime·save_g(SB)
	MOVW	R2, g_m(g)	// g.m = curm
	MOVW	g, m_g0(R2)	// curm.g0 = g

	// switch to crashstack
	MOVW	(g_stack+stack_hi)(g), R2
	ADDU	$(-4*8), R2, R29

	// call target function

TEXT runtime·switchToCrashStack0<ABIInternal>(SB), NOSPLIT, $0-8
	MOV	X10, CTXT			// context register
	MOV	g_m(g), X11			// curm

	// set g to gcrash
	MOV	$runtime·gcrash(SB), g	// g = &gcrash
	CALL	runtime·save_g(SB)	// clobbers X31
	MOV	X11, g_m(g)			// g.m = curm
	MOV	g, m_g0(X11)			// curm.g0 = g

	// switch to crashstack
	MOV	(g_stack+stack_hi)(g), X11
	SUB	$(4*8), X11
	MOV	X11, X2

TEXT runtime·switchToCrashStack0<ABIInternal>(SB), NOSPLIT, $0-8
	MOVD	fn+0(FP), R12	// context
	MOVD	g_m(g), R4	// curm

	// set g to gcrash
	MOVD	$runtime·gcrash(SB), g	// g = &gcrash
	BL	runtime·save_g(SB)
	MOVD	R4, g_m(g)	// g.m = curm
	MOVD	g, m_g0(R4)	// curm.g0 = g

	// switch to crashstack
	MOVD	(g_stack+stack_hi)(g), R4
	ADD	$(-4*8), R4, R15

	// call target function

  // CHECK-LABEL: tranpose_arg64
  // CHECK: "tfl.transpose"
}

func.func @cumsum(%arg0: tensor<3x3xf32>, %arg1: tensor<i32>) -> tensor<3x3xf32> {
  %0 = "tf.Cumsum"(%arg0, %arg1) {exclusive = false, reverse = false} : (tensor<3x3xf32>, tensor<i32>) -> tensor<3x3xf32>
  func.return %0 : tensor<3x3xf32>
  // CHECK-LABEL: cumsum

// func switchToCrashStack0(fn func())
TEXT runtime·switchToCrashStack0(SB), NOSPLIT, $0-4
	MOVW	fn+0(FP), R7 // context register
	MOVW	g_m(g), R1 // curm

	// set g to gcrash
	MOVW	$runtime·gcrash(SB), R0
	BL	setg<>(SB)	// g = &gcrash
	MOVW	R1, g_m(g)	// g.m = curm
	MOVW	g, m_g0(R1)	// curm.g0 = g

	// switch to crashstack
	MOVW	(g_stack+stack_hi)(g), R1
	SUB	$(4*8), R1
	MOVW	R1, R13

	// call target function

TEXT runtime·switchToCrashStack0<ABIInternal>(SB), NOSPLIT, $0-8
	MOVD	R3, R11				// context register
	MOVD	g_m(g), R3			// curm

	// set g to gcrash
	MOVD	$runtime·gcrash(SB), g	// g = &gcrash
	CALL	runtime·save_g(SB)	// clobbers R31
	MOVD	R3, g_m(g)			// g.m = curm
	MOVD	g, m_g0(R3)			// curm.g0 = g

	// switch to crashstack
	MOVD	(g_stack+stack_hi)(g), R3
	SUB	$(4*8), R3
	MOVD	R3, R1

TEXT runtime·switchToCrashStack0(SB), NOSPLIT, $0-4
	MOVL 	fn+0(FP), AX

	get_tls(CX)
	MOVL	g(CX), BX	// BX = g
	MOVL	g_m(BX), DX	// DX = curm

	// set g to gcrash
	LEAL	runtime·gcrash(SB), BX // g = &gcrash
	MOVL	DX, g_m(BX)            // g.m = curm
	MOVL	BX, m_g0(DX)           // curm.g0 = g
	get_tls(CX)
	MOVL	BX, g(CX)

	// switch to crashstack
	MOVL	(g_stack+stack_hi)(BX), DX
	SUBL	$(4*8), DX
	MOVL	DX, SP